{"slug": "opencode", "name": "OpenCode", "category": "ai-coding", "category_name": "AI coding tools", "description": "Open-source, model-agnostic AI coding agent harness with terminal, web and desktop clients.", "recommenders": 206, "commenters": 408, "warners": 42, "score": 178.079, "rising": 10.62, "first": "2025-11-01", "latest": "2026-10-31", "why": "Liked as a customizable, model-agnostic open-source coding harness that pairs well with cheap open models via the $10/month OpenCode Go plan or free models.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 230, "neutral": 193, "compare": 18, "warn": 49}, "spark": [2, 4, 9, 6, 18, 17, 14, 53, 38, 22, 22, 25], "listed": true, "loved": ["Model flexibility", "Cheap model access"], "caveat": "Data privacy", "short_quote": "I cannot recommend enough OpenCode Go, which for 10 bucks a month lets you use all of them with pretty hefty limits.", "icon": true, "domain": "opencode.ai", "github_repo": null, "official_url": "https://opencode.ai", "pricing": "open source", "aliases": ["OpenCode", "opencode", "OpenCode Go", "Opencode", "Opencode Go", "opencode-go", "opencode go"], "verdict": [{"text": "Liked as a customizable, model-agnostic open-source coding harness", "cites": [{"id": 801563024, "item_id": 50097689, "url": "https://news.ycombinator.com/item?id=50097689", "by": "YrRight2PushBac", "date": "2026-10-15", "stance": "recommend", "quote": "Since it's model agnostic, this might become my daily driver.", "excerpt": "It's a big improvement over the previous version. Currently, the Codex TUI has constant display issues for me, the most prevalent being random deviations of light/dark characters. So far no such issue in OpenCode. Since it's model agnostic, this might become my daily driver.", "context": "", "use_case": "AI coding agent TUI", "switched_from": "Codex", "story": "OpenCode 2.0"}, {"id": 801848370, "item_id": 50115523, "url": "https://news.ycombinator.com/item?id=50115523", "by": "armcat", "date": "2026-10-16", "stance": "recommend", "quote": "There are lot of other amazing open source agent harnesses like OpenCode [2] and Pi [3].", "excerpt": "For Codex there is no need to decompile because unlike Claude Code, Codex is open source [1] and written in Rust. There are lot of other amazing open source agent harnesses like OpenCode [2] and Pi [3]. [1] https://github.com/openai/codex [2] https://github.com/anomalyco/opencode [3] https://github.com/earendil-works/pi", "context": "", "use_case": "agent harness", "switched_from": "", "story": "Ask HN: Has anyone decompiled Claude Code yet?"}, {"id": 801577584, "item_id": 50098599, "url": "https://news.ycombinator.com/item?id=50098599", "by": "dkarter", "date": "2026-10-15", "stance": "recommend", "quote": "It's my daily driver - very easy to customize.", "excerpt": "It's my daily driver - very easy to customize. Added a pretty solid vim plugin for it and a few more really useful plugins. Here are my dotfiles https://github.com/dkarter/dotfiles", "context": "", "use_case": "coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 796833936, "item_id": 49802121, "url": "https://news.ycombinator.com/item?id=49802121", "by": "pauleveritt", "date": "2026-09-22", "stance": "recommend", "quote": "I use OpenCode and Pi connected to local models and to stuff like hosted DeepSeek all the time.", "excerpt": "JetBrainer here. I use OpenCode and Pi connected to local models and to stuff like hosted DeepSeek all the time. Once you have your model config set up in the agent, it works as expected.", "context": "JetBrainer", "use_case": "agent with local models", "switched_from": "", "story": "JetBrains Air: A System of Products for Agentic Software Development"}]}, {"text": " that pairs well with cheap open models via the $10/month OpenCode Go plan or free models.", "cites": [{"id": 802698144, "item_id": 50168634, "url": "https://news.ycombinator.com/item?id=50168634", "by": "mixermachine", "date": "2026-10-20", "stance": "recommend", "quote": "I use that and so far it is good for me.", "excerpt": "You could consider going with OpenCode Go for 10$. The value you get is claimed to be 80$ in DeepSeek v4.1 Flash API value. I use that and so far it is good for me. Some claim they run a different quant but I so far don't see that.", "context": "", "use_case": "cheap DeepSeek API access", "switched_from": "", "story": "DeepInfer: High-performance inference framework for DeepSeek models"}, {"id": 800197697, "item_id": 50012356, "url": "https://news.ycombinator.com/item?id=50012356", "by": "apitman", "date": "2026-10-08", "stance": "recommend", "quote": "With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited", "excerpt": "> With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited My OpenCode Go monthly window was scheduled to reset this morning. It was sitting at 22% used despite me using DeepSeek V4.1 Flash heavily as my implementation agent the past couple weeks (I use gpt-6.1-sol high for planning/orchestration). I had 1.5 hours left so I fired up first 10, then 20, and finally 50 concurrent subagents all working on re", "context": "", "use_case": "model access subscription", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 801816208, "item_id": 50113513, "url": "https://news.ycombinator.com/item?id=50113513", "by": "verdverm", "date": "2026-10-16", "stance": "recommend", "quote": "next try a harness like opencode or pi with open weight models via opencode-go for $10/m", "excerpt": "yup, next try a harness like opencode or pi with open weight models via opencode-go for $10/m or make your own harness, it's easy, fun, and you learn a lot", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Ask HN: Thoughts about the Gemini Web app?"}, {"id": 800269648, "item_id": 50016853, "url": "https://news.ycombinator.com/item?id=50016853", "by": "TiredOfLife", "date": "2026-10-09", "stance": "recommend", "quote": "I use only OpenCode free models and occasional 20$ sub from OpenAi or Anthropic. And get complete/working products out of them.", "excerpt": "I use only OpenCode free models and occasional 20$ sub from OpenAi or Anthropic. And get complete/working products out of them.", "context": "", "use_case": "coding with free models", "switched_from": "", "story": "What ArtCraft's Vibe-Coded Apps Say About Adobe"}]}, {"text": " The most common complaints are about privacy and security, including a since-removed default of summarizing chats with a cloud model and unclear API key storage,", "cites": [{"id": 796059136, "item_id": 49753696, "url": "https://news.ycombinator.com/item?id=49753696", "by": "my-huge-pony", "date": "2026-09-18", "stance": "warn", "quote": "opencode by default uses a \"free\" cloud model to summarize all chats even if a different model was configured as the main one", "excerpt": "We use opencode with self hosted llm for privacy reasons. Good, right? Well, no, because opencode by default uses a \"free\" cloud model to summarize all chats even if a different model was configured as the main one. I wonder how many opencode users upload their private secrets to the cloud, while thinking they're using a self hosted model. Btw. I don't think this is malicious, just sloppy.", "context": "team uses self-hosted LLM for privacy", "use_case": "coding with self-hosted LLM", "switched_from": "", "story": "Inside ZCode: Silently uploading your Git history to the cloud"}, {"id": 796130576, "item_id": 49758161, "url": "https://news.ycombinator.com/item?id=49758161", "by": "Scaled", "date": "2026-09-18", "stance": "recommend", "quote": "Open code is great and I use it", "excerpt": "Open code is great and I use it, however, they were caught uploading prompts to their summarization AI instead of using the configured AI model endpoint. This has since been fixed. That said, running in a completely offline mode remains unnecessary difficult to configure. In particular, toggling off Zen seems to require a community plugin.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Inside ZCode: Silently uploading your Git history to the cloud"}, {"id": 802172512, "item_id": 50135782, "url": "https://news.ycombinator.com/item?id=50135782", "by": "Reyonlds96", "date": "2026-10-17", "stance": "recommend", "quote": "It is still private by default", "excerpt": "I love the smell of misinformation in the morning. All it ever did was give people free model for title gen, if they didn't set one themselves. Feature you could disable or set on your own model. That was since removed, so now there is no free fallback model. That is it. It is still private by default", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802138288, "item_id": 50133643, "url": "https://news.ycombinator.com/item?id=50133643", "by": "bewareofscams", "date": "2026-10-17", "stance": "warn", "quote": "OpenCode will leak all your data to themselves and to shady 3rd parties.", "excerpt": "I told you so: https://news.ycombinator.com/item?id=49243119 Me, 68 days ago: > Beware of the author of tweet, who happens to be author of OpenCode - OpenCode will leak all your data to themselves and to shady 3rd parties. Author feigned ignorance and never fixed the issue. OpenCode among other harnesses is the shadiest of all. > https://github.com/anomalyco/opencode/issues/10416", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802155824, "item_id": 50134739, "url": "https://news.ycombinator.com/item?id=50134739", "by": "latchkey", "date": "2026-10-17", "stance": "warn", "quote": "there are no warnings or documentation about how they store your keys.", "excerpt": "the ux is kind of crazy. you login to their website, and you are presented with a list of providers where you can click and add your provider api key. how the key is stored on the backend isn't clear, but it is akin to handing your password or if you know crypto, your private key, to someone and letting them store it for you. from what i can tell, there are no links within the console to a ToS, Privacy policy or anyt", "context": "", "use_case": "AI coding agent console", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}]}, {"text": " followed by heavy RAM and CPU use.", "cites": [{"id": 801820960, "item_id": 50113810, "url": "https://news.ycombinator.com/item?id=50113810", "by": "cute_boi", "date": "2026-10-16", "stance": "warn", "quote": "it is horrible with ram usage. Every subagent takes like 300 MB of RAM.", "excerpt": "I have been using open code and it is horrible with ram usage. Every subagent takes like 300 MB of RAM. As they are vibe coding, i think they should use language that consumes less RAM eg. Rust or C.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 796929793, "item_id": 49808112, "url": "https://news.ycombinator.com/item?id=49808112", "by": "wg0", "date": "2026-09-22", "stance": "warn", "quote": "opencode pushes CPU usage to very high", "excerpt": "I am using DeepSeek Harness[0] (switched from OpenCode) and I am using DeepSeek directly via the API. The speed is insane. Like 200 tokens/second is the norm but I have seen much higher too at times. PS: I do not know why but opencode pushes CPU usage to very high which has NOT happened with DeepSeek harness even once. [0]. https://github.com/deepseek-ai/deepseek-harness", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Claude Opus 5.5"}, {"id": 801536656, "item_id": 50096041, "url": "https://news.ycombinator.com/item?id=50096041", "by": "montroser", "date": "2026-10-14", "stance": "warn", "quote": "Does it still eat all of my memory?  Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window", "excerpt": "OpenCode is a beast. Does it still try to take a disk snapshot of my working directory, even when it contains hundreds of millions of files? Does it still eat all of my memory? Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window before I've even begun? I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They upda", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}]}], "praise": [{"label": "Model flexibility", "summary": "Works with many providers, subscriptions, hosted APIs and local models.", "quotes": [{"id": 801563024, "item_id": 50097689, "url": "https://news.ycombinator.com/item?id=50097689", "by": "YrRight2PushBac", "date": "2026-10-15", "stance": "recommend", "quote": "Since it's model agnostic, this might become my daily driver.", "excerpt": "It's a big improvement over the previous version. Currently, the Codex TUI has constant display issues for me, the most prevalent being random deviations of light/dark characters. So far no such issue in OpenCode. Since it's model agnostic, this might become my daily driver.", "context": "", "use_case": "AI coding agent TUI", "switched_from": "Codex", "story": "OpenCode 2.0"}, {"id": 796833936, "item_id": 49802121, "url": "https://news.ycombinator.com/item?id=49802121", "by": "pauleveritt", "date": "2026-09-22", "stance": "recommend", "quote": "I use OpenCode and Pi connected to local models and to stuff like hosted DeepSeek all the time.", "excerpt": "JetBrainer here. I use OpenCode and Pi connected to local models and to stuff like hosted DeepSeek all the time. Once you have your model config set up in the agent, it works as expected.", "context": "JetBrainer", "use_case": "agent with local models", "switched_from": "", "story": "JetBrains Air: A System of Products for Agentic Software Development"}, {"id": 798895168, "item_id": 49930948, "url": "https://news.ycombinator.com/item?id=49930948", "by": "sid_talks", "date": "2026-10-02", "stance": "recommend", "quote": "I have been using OpenCode for most work related stuff now. It works well with my ChatGpt Pro subscription", "excerpt": "I have been using OpenCode for most work related stuff now. It works well with my ChatGpt Pro subscription as well as with our locally hosted Qwen3.8. Is it worthwhile to spend time and effort into setting up and switching to Pi? I always see people praising Pi online but I am curious to know from people who switched over from OpenCode why they did so and what I am missing.", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Pi 1.0"}]}, {"label": "Cheap model access", "summary": "OpenCode Go and free models are seen as good value for heavy use.", "quotes": [{"id": 800197697, "item_id": 50012356, "url": "https://news.ycombinator.com/item?id=50012356", "by": "apitman", "date": "2026-10-08", "stance": "recommend", "quote": "With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited", "excerpt": "> With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited My OpenCode Go monthly window was scheduled to reset this morning. It was sitting at 22% used despite me using DeepSeek V4.1 Flash heavily as my implementation agent the past couple weeks (I use gpt-6.1-sol high for planning/orchestration). I had 1.5 hours left so I fired up first 10, then 20, and finally 50 concurrent subagents all working on re", "context": "", "use_case": "model access subscription", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 801542530, "item_id": 50096408, "url": "https://news.ycombinator.com/item?id=50096408", "by": "esafak", "date": "2026-10-14", "stance": "recommend", "quote": "Opencode Go is a great deal and now has a $40 plan.", "excerpt": "OC is all right -- it's my daily driver -- but it could be better. I'd like a harness to let me customize the GUI, not just add MCPs and plugins. For example, I'd like add buttons to merge a PR, and show indicators for CI. Claude Code does a lot of this out of the box. Give me UI building blocks (buttons, labels, etc.) and wire them with my own functions. Could Code Mode enable this? The built-in browser is a most we", "context": "", "use_case": "model subscription plan", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 800269648, "item_id": 50016853, "url": "https://news.ycombinator.com/item?id=50016853", "by": "TiredOfLife", "date": "2026-10-09", "stance": "recommend", "quote": "I use only OpenCode free models and occasional 20$ sub from OpenAi or Anthropic. And get complete/working products out of them.", "excerpt": "I use only OpenCode free models and occasional 20$ sub from OpenAi or Anthropic. And get complete/working products out of them.", "context": "", "use_case": "coding with free models", "switched_from": "", "story": "What ArtCraft's Vibe-Coded Apps Say About Adobe"}]}, {"label": "Customization", "summary": "Easy to extend with plugins and skills, or fork into your own harness.", "quotes": [{"id": 801577584, "item_id": 50098599, "url": "https://news.ycombinator.com/item?id=50098599", "by": "dkarter", "date": "2026-10-15", "stance": "recommend", "quote": "It's my daily driver - very easy to customize.", "excerpt": "It's my daily driver - very easy to customize. Added a pretty solid vim plugin for it and a few more really useful plugins. Here are my dotfiles https://github.com/dkarter/dotfiles", "context": "", "use_case": "coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 800664737, "item_id": 50041546, "url": "https://news.ycombinator.com/item?id=50041546", "by": "riedel", "date": "2026-10-11", "stance": "recommend", "quote": "It is quite a synergy : my nix usage profits from the agent", "excerpt": "I love the combination. I use devenv (yet another nix flake dev environments) and opencode. It is quite a synergy : my nix usage profits from the agent and the agent profits from being able to install just anything. I even vibecoded a plugin for personal use that runs all bash tool calls through devenv and uses the supplied nix lsp package: https://github.com/riedel/opencode-devenv", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Nix wrote half of my debugger"}, {"id": 797105840, "item_id": 49819115, "url": "https://news.ycombinator.com/item?id=49819115", "by": "pizzuh", "date": "2026-09-23", "stance": "recommend", "quote": "It's so easy to take opencode or pi and build my own for exactly what I want", "excerpt": "I'm more and more hesitant to use third party harnesses. It's so easy to take opencode or pi and build my own for exactly what I want that I'm seeing projects like this to be noisy and less valuable over time. I wish this wasn't the case. I love software, but it's becoming increasingly easy to just build my own.", "context": "", "use_case": "base for custom agent harness", "switched_from": "", "story": "Strands Harness"}]}, {"label": "Daily driver", "summary": "Several commenters use it as their main coding tool, including for non-trivial apps.", "quotes": [{"id": 801585520, "item_id": 50099095, "url": "https://news.ycombinator.com/item?id=50099095", "by": "ChaseRensberger", "date": "2026-10-15", "stance": "recommend", "quote": "been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.", "excerpt": "their client server model is a fantastic idea and the core reason i started building https://wingman.actor a year ago. unfortunately making a great harness is tricky and i often just steal with things i like from ocv2 and pi. been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.", "context": "", "use_case": "daily coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801542528, "item_id": 50096408, "url": "https://news.ycombinator.com/item?id=50096408", "by": "esafak", "date": "2026-10-14", "stance": "recommend", "quote": "OC is all right -- it's my daily driver -- but it could be better.", "excerpt": "OC is all right -- it's my daily driver -- but it could be better. I'd like a harness to let me customize the GUI, not just add MCPs and plugins. For example, I'd like add buttons to merge a PR, and show indicators for CI. Claude Code does a lot of this out of the box. Give me UI building blocks (buttons, labels, etc.) and wire them with my own functions. Could Code Mode enable this? The built-in browser is a most we", "context": "", "use_case": "daily AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 795892304, "item_id": 49743269, "url": "https://news.ycombinator.com/item?id=49743269", "by": "cyanydeez", "date": "2026-09-17", "stance": "recommend", "quote": "I use opencode consistently to build non-trivial apps with it", "excerpt": "training is in there because it's \"trained\" to do trivial apps like TODO lists, etc. I'm well aware it can build apps. But if you arn't tracking what's going on, they're basically creating deterministic gates and tools to get it to do anything. There's no lie here, it's simply about what you think is _LLM_ and what is the rest of the software that's making it go. I use opencode consistently to build non-trivial apps ", "context": "", "use_case": "building non-trivial apps", "switched_from": "", "story": "The Painful Truth: The RAM Crisis Is Only Just the Beginning"}]}, {"label": "Client/server model", "summary": "V2's client/server design and usability are praised as a clear improvement.", "quotes": [{"id": 801593408, "item_id": 50099588, "url": "https://news.ycombinator.com/item?id=50099588", "by": "ghrl", "date": "2026-10-15", "stance": "recommend", "quote": "I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability", "excerpt": "I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability, the client/server model and self-awareness/ability to edit it's config and write plugins. I'd like to mention two other impressive things about OpenCode. First, their issue tracker on GitHub works really well. They have the OpenCode GitHub App connected, and for any bug report it reads the issue,", "context": "", "use_case": "coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801585520, "item_id": 50099095, "url": "https://news.ycombinator.com/item?id=50099095", "by": "ChaseRensberger", "date": "2026-10-15", "stance": "recommend", "quote": "been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.", "excerpt": "their client server model is a fantastic idea and the core reason i started building https://wingman.actor a year ago. unfortunately making a great harness is tricky and i often just steal with things i like from ocv2 and pi. been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.", "context": "", "use_case": "daily coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801530064, "item_id": 50095629, "url": "https://news.ycombinator.com/item?id=50095629", "by": "kingds", "date": "2026-10-14", "stance": "recommend", "quote": "it feels like a clear improvement across the board", "excerpt": "it feels like a clear improvement across the board but a heads up: i got bitten by upgrading - since all tool calls now go through the background process, the sandbox that i use to wrap the TUI process quietly became useless. took me a day or two to realize that web fetches, etc. which should have been blocked were succeeding.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}]}, {"label": "Remote and mobile", "summary": "With OpenChamber, its web and mobile interfaces let users work away from the desk.", "quotes": [{"id": 801664416, "item_id": 50104026, "url": "https://news.ycombinator.com/item?id=50104026", "by": "nfriedly", "date": "2026-10-15", "stance": "recommend", "quote": "But I use OpenCode / OpenChamber for personal stuff", "excerpt": "You're not wrong, and I predominately use a TUI at work where I'm actually at the computer for ~8 hours a day. But I use OpenCode / OpenChamber for personal stuff where I might only get 20 minutes at my computer before I have to go do something else. So the web interface and especially the mobile app get more use from me there. It's kind of wild to be working on a project while walking my dog or washing dishes or som", "context": "uses a TUI at work for ~8 hours a day", "use_case": "coding agent for personal projects", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 798924706, "item_id": 49932794, "url": "https://news.ycombinator.com/item?id=49932794", "by": "nfriedly", "date": "2026-10-02", "stance": "recommend", "quote": "caused me to switch back to OpenCode", "excerpt": "I really like Pi, especially for when you're running a local model and your context is particularly limited. But even when running a big model, I think building up your environment to be exactly what you want can be really powerful. When I was first getting started and didn't realize that ollama defaults to incredibly tiny amounts of context, Pi was the only harness that actually worked because the rest of them used ", "context": "", "use_case": "coding agent harness", "switched_from": "Pi", "story": "Pi 1.0"}]}], "caveats": [{"label": "Data privacy", "summary": "Users report prompts sent to a cloud summarization model by default (since removed) and offline mode being hard to configure.", "quotes": [{"id": 796059136, "item_id": 49753696, "url": "https://news.ycombinator.com/item?id=49753696", "by": "my-huge-pony", "date": "2026-09-18", "stance": "warn", "quote": "opencode by default uses a \"free\" cloud model to summarize all chats even if a different model was configured as the main one", "excerpt": "We use opencode with self hosted llm for privacy reasons. Good, right? Well, no, because opencode by default uses a \"free\" cloud model to summarize all chats even if a different model was configured as the main one. I wonder how many opencode users upload their private secrets to the cloud, while thinking they're using a self hosted model. Btw. I don't think this is malicious, just sloppy.", "context": "team uses self-hosted LLM for privacy", "use_case": "coding with self-hosted LLM", "switched_from": "", "story": "Inside ZCode: Silently uploading your Git history to the cloud"}, {"id": 796130576, "item_id": 49758161, "url": "https://news.ycombinator.com/item?id=49758161", "by": "Scaled", "date": "2026-09-18", "stance": "recommend", "quote": "Open code is great and I use it", "excerpt": "Open code is great and I use it, however, they were caught uploading prompts to their summarization AI instead of using the configured AI model endpoint. This has since been fixed. That said, running in a completely offline mode remains unnecessary difficult to configure. In particular, toggling off Zen seems to require a community plugin.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Inside ZCode: Silently uploading your Git history to the cloud"}, {"id": 802138288, "item_id": 50133643, "url": "https://news.ycombinator.com/item?id=50133643", "by": "bewareofscams", "date": "2026-10-17", "stance": "warn", "quote": "OpenCode will leak all your data to themselves and to shady 3rd parties.", "excerpt": "I told you so: https://news.ycombinator.com/item?id=49243119 Me, 68 days ago: > Beware of the author of tweet, who happens to be author of OpenCode - OpenCode will leak all your data to themselves and to shady 3rd parties. Author feigned ignorance and never fixed the issue. OpenCode among other harnesses is the shadiest of all. > https://github.com/anomalyco/opencode/issues/10416", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}]}, {"label": "Key security", "summary": "Commenters flag unclear API key storage and a compromised-key notice.", "quotes": [{"id": 802155824, "item_id": 50134739, "url": "https://news.ycombinator.com/item?id=50134739", "by": "latchkey", "date": "2026-10-17", "stance": "warn", "quote": "there are no warnings or documentation about how they store your keys.", "excerpt": "the ux is kind of crazy. you login to their website, and you are presented with a list of providers where you can click and add your provider api key. how the key is stored on the backend isn't clear, but it is akin to handing your password or if you know crypto, your private key, to someone and letting them store it for you. from what i can tell, there are no links within the console to a ToS, Privacy policy or anyt", "context": "", "use_case": "AI coding agent console", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802156560, "item_id": 50134785, "url": "https://news.ycombinator.com/item?id=50134785", "by": "jprokay13", "date": "2026-10-17", "stance": "warn", "quote": "I saw the email this morning from OpenCode about my key being compromised", "excerpt": "I saw the email this morning from OpenCode about my key being compromised alongside an email from Anthropic stating that I used up my $20 in API credits for the month. I hope they built something cool with those tokens!", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802157216, "item_id": 50134826, "url": "https://news.ycombinator.com/item?id=50134826", "by": "lukewarm707", "date": "2026-10-17", "stance": "warn", "quote": "I did have an account but moved off for security reasons.", "excerpt": "\"when challenged about sending data to openrouter without listing it as a 3rd party processor they offered a dismissive response. the same with running prompts through cloudflare. seems trivial, but signifies general disinterest in security.\" I did have an account but moved off for security reasons.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}]}, {"label": "Resource usage", "summary": "Reports of high RAM per subagent, high CPU use and slow performance.", "quotes": [{"id": 801820960, "item_id": 50113810, "url": "https://news.ycombinator.com/item?id=50113810", "by": "cute_boi", "date": "2026-10-16", "stance": "warn", "quote": "it is horrible with ram usage. Every subagent takes like 300 MB of RAM.", "excerpt": "I have been using open code and it is horrible with ram usage. Every subagent takes like 300 MB of RAM. As they are vibe coding, i think they should use language that consumes less RAM eg. Rust or C.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 796929793, "item_id": 49808112, "url": "https://news.ycombinator.com/item?id=49808112", "by": "wg0", "date": "2026-09-22", "stance": "warn", "quote": "opencode pushes CPU usage to very high", "excerpt": "I am using DeepSeek Harness[0] (switched from OpenCode) and I am using DeepSeek directly via the API. The speed is insane. Like 200 tokens/second is the norm but I have seen much higher too at times. PS: I do not know why but opencode pushes CPU usage to very high which has NOT happened with DeepSeek harness even once. [0]. https://github.com/deepseek-ai/deepseek-harness", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Claude Opus 5.5"}, {"id": 801639536, "item_id": 50102471, "url": "https://news.ycombinator.com/item?id=50102471", "by": "wg0", "date": "2026-10-15", "stance": "warn", "quote": "Performance is horrible both of the website and of the tool itself.", "excerpt": "Performance is horrible both of the website and of the tool itself. That's why I first switched to Pi and then to DeepSeek harness.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}]}, {"label": "Maintenance burden", "summary": "Some find it needs continuous debugging and dislike how issues are handled.", "quotes": [{"id": 801578352, "item_id": 50098647, "url": "https://news.ycombinator.com/item?id=50098647", "by": "prtmnth", "date": "2026-10-15", "stance": "warn", "quote": "I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.", "excerpt": "I had to update because the previous OpenCode 2.0.3 I had installed stopped working suddenly. I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801072368, "item_id": 50067023, "url": "https://news.ycombinator.com/item?id=50067023", "by": "crossroadsguy", "date": "2026-10-13", "stance": "warn", "quote": "What demorlised me is attitude of OpenCode devs/maintainers.", "excerpt": "So is OpenCode. More so. I use Claude Code and OpenCode almost equally and Codex slightly less and Pi the least of them (not that it's worse, but because I use it for \"non coding\" purposes). They are all bad. Even this newer breed of \"agent orchrestrating\" tools. One goes to Github and one notices, the dev is done by LLMs, issue triage is done by bots, and the commenting is done by the bots. (btw, the triage mostly m", "context": "", "use_case": "AI coding harness", "switched_from": "", "story": "Codex CLI installs a persistent, self-updating background daemon by default"}, {"id": 803856544, "item_id": 50241034, "url": "https://news.ycombinator.com/item?id=50241034", "by": "crossroadsguy", "date": "2026-10-26", "stance": "warn", "quote": "I used V1 a lot and I am struggling with V2 currently. Yes, it just doesn't feel right.", "excerpt": "At this point I'd rather try to invest effort and usage in a harness that is FOSS and is actually steered by a non-profit. Goose comes to mind and to be honest I haven't tried it beyond installing and giving it a prompt or two. Comiong to harnesses, even Pi seems like a weird choice. I mean Pi, until it's \"your own customised Pi\", is pretty useless and pointless. Besides they are also starting to have their own model", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}]}, {"label": "Context overhead", "summary": "A large system prompt is said to eat into the context window.", "quotes": [{"id": 801536656, "item_id": 50096041, "url": "https://news.ycombinator.com/item?id=50096041", "by": "montroser", "date": "2026-10-14", "stance": "warn", "quote": "Does it still eat all of my memory?  Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window", "excerpt": "OpenCode is a beast. Does it still try to take a disk snapshot of my working directory, even when it contains hundreds of millions of files? Does it still eat all of my memory? Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window before I've even begun? I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They upda", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 798924706, "item_id": 49932794, "url": "https://news.ycombinator.com/item?id=49932794", "by": "nfriedly", "date": "2026-10-02", "stance": "recommend", "quote": "caused me to switch back to OpenCode", "excerpt": "I really like Pi, especially for when you're running a local model and your context is particularly limited. But even when running a big model, I think building up your environment to be exactly what you want can be really powerful. When I was first getting started and didn't realize that ollama defaults to incredibly tiny amounts of context, Pi was the only harness that actually worked because the rest of them used ", "context": "", "use_case": "coding agent harness", "switched_from": "Pi", "story": "Pi 1.0"}]}, {"label": "Usage limits", "summary": "OpenCode Go's 5-hour rolling limit and lack of training guarantees are noted.", "quotes": [{"id": 801819072, "item_id": 50113692, "url": "https://news.ycombinator.com/item?id=50113692", "by": "duckiec", "date": "2026-10-16", "stance": "recommend", "quote": "its great value but the 5 hour rolling limit seems kinda annoying", "excerpt": "just checked it out, its great value but the 5 hour rolling limit seems kinda annoying", "context": "", "use_case": "open-weight models subscription", "switched_from": "", "story": "Ask HN: Thoughts about the Gemini Web app?"}, {"id": 796712657, "item_id": 49794541, "url": "https://news.ycombinator.com/item?id=49794541", "by": "wkcheng", "date": "2026-09-21", "stance": "warn", "quote": "OpenCode Go straight up doesn't give any guarantees about training on your data", "excerpt": "Are people using MiMo models as their daily drivers in a company setting? If so, how? I know they're available over OpenCode and directly from Xiaomi, but those are not great options. OpenCode Go straight up doesn't give any guarantees about training on your data, and Xiaomi says that they won't but it's unclear. With some models you can find hosting companies based in the EU or US, but then you don't know how they'r", "context": "", "use_case": "hosted MiMo access", "switched_from": "", "story": "MiMo v2.6"}]}], "who": [{"by": "cyanydeez", "context": "runs everything local", "url": "https://news.ycombinator.com/item?id=50236945", "date": "2026-10-25"}, {"by": "nfriedly", "context": "uses a TUI at work for ~8 hours a day", "url": "https://news.ycombinator.com/item?id=50104026", "date": "2026-10-15"}, {"by": "caivi", "context": "AI-powered forward engineer looking for work", "url": "https://news.ycombinator.com/item?id=50081293", "date": "2026-10-14"}, {"by": "punkbit", "context": "Product Engineer in London", "url": "https://news.ycombinator.com/item?id=49922786", "date": "2026-10-01"}, {"by": "abalashov", "context": "individual contributor", "url": "https://news.ycombinator.com/item?id=49815221", "date": "2026-09-23"}, {"by": "pauleveritt", "context": "JetBrainer", "url": "https://news.ycombinator.com/item?id=49802121", "date": "2026-09-22"}, {"by": "verdverm", "context": "customizes opencode", "url": "https://news.ycombinator.com/item?id=49741444", "date": "2026-09-17"}, {"by": "alexjplant", "context": "constrained by regulations at day job", "url": "https://news.ycombinator.com/item?id=49735497", "date": "2026-09-17"}, {"by": "softwarewright", "context": "single person LLC", "url": "https://news.ycombinator.com/item?id=49591330", "date": "2026-09-06"}, {"by": "ipaddr", "context": "older programmer", "url": "https://news.ycombinator.com/item?id=49408813", "date": "2026-08-23"}, {"by": "darthcircuit", "context": "systems and ops person, not a full-time dev", "url": "https://news.ycombinator.com/item?id=49380510", "date": "2026-08-20"}, {"by": "pixlmint", "context": "Neovim user who uses agents rarely", "url": "https://news.ycombinator.com/item?id=49370974", "date": "2026-08-19"}], "tags": ["for local models", "for budget users", "for tinkerers", "model-agnostic", "for remote work"], "use_cases": ["coding agent", "ai coding", "ai coding agent", "coding agent harness", "ai coding harness", "coding harness"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 163, "switched_from": 24, "switched_to": 2}, {"slug": "pi", "name": "Pi", "co": 112, "switched_from": 3, "switched_to": 23}, {"slug": "codex", "name": "Codex", "co": 95, "switched_from": 3, "switched_to": 2}, {"slug": "deepseek", "name": "DeepSeek", "co": 68, "switched_from": 1, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 50, "switched_from": 6, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 55, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 55, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 36, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 770357456, "item_id": 48147341, "url": "https://news.ycombinator.com/item?id=48147341", "by": "benjamintnorris", "date": "2026-05-15", "stance": "neutral", "quote": "We support OpenCode, as well as any other coding tools accepting OpenAI compatible endpoints.", "excerpt": "Hi! We support OpenCode, as well as any other coding tools accepting OpenAI compatible endpoints. For example, take a look at: https://relax.ai/docs/integrations/developer-productivity-tools/claude-code", "context": "", "use_case": "coding tool integration", "switched_from": "", "story": "RelaxAI \u2013 UK sovereign LLM inference at 80% cheaper than OpenAI/Claude"}], "threads": [{"url": "https://news.ycombinator.com/item?id=50094994", "title": "OpenCode 2.0", "mentions": 28}, {"url": "https://news.ycombinator.com/item?id=48978112", "title": "Stop Using OpenCode", "mentions": 14}, {"url": "https://news.ycombinator.com/item?id=48413629", "title": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)", "mentions": 13}, {"url": "https://news.ycombinator.com/item?id=47460525", "title": "OpenCode \u2013 The open source AI coding agent", "mentions": 13}, {"url": "https://news.ycombinator.com/item?id=48542100", "title": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?", "mentions": 9}, {"url": "https://news.ycombinator.com/item?id=48502347", "title": "Kimi K2.7-Code: open-source coding model with better token efficiency", "mentions": 9}], "sentiment_by_month": {"2025-11": {"neutral": 1, "warn": 2, "recommend": 2}, "2025-12": {"neutral": 2, "recommend": 4}, "2026-01": {"neutral": 7, "recommend": 9, "warn": 2}, "2026-02": {"neutral": 11, "recommend": 6, "compare": 1}, "2026-03": {"recommend": 18, "neutral": 9, "warn": 4, "compare": 1}, "2026-04": {"recommend": 17, "neutral": 7, "compare": 1}, "2026-05": {"recommend": 14, "neutral": 5, "warn": 1}, "2026-06": {"recommend": 53, "neutral": 39, "warn": 6, "compare": 5}, "2026-07": {"recommend": 38, "compare": 2, "neutral": 31, "warn": 10}, "2026-08": {"neutral": 29, "warn": 8, "recommend": 22, "compare": 2}, "2026-09": {"neutral": 27, "recommend": 22, "warn": 6}, "2026-10": {"neutral": 25, "recommend": 25, "compare": 6, "warn": 10}}, "quotes": [{"id": 805101521, "item_id": 50318845, "url": "https://news.ycombinator.com/item?id=50318845", "by": "34679", "date": "2026-10-31", "stance": "neutral", "quote": "which still uses the OpenCode backend", "excerpt": "I recently switched from the OpenCode GUI to OpenChamber, which still uses the OpenCode backend. It's pretty great. One of the features is the ability to select a portion of an agent's response and add a comment to it. Comments are sent along with the next prompt. It's also much better at handling subagents. With a proper plan in place, it will send out swarms in waves.", "context": "", "use_case": "coding agent backend", "switched_from": "", "story": "Prospero: A new coding harness for a more civilized age"}, {"id": 805065842, "item_id": 50316615, "url": "https://news.ycombinator.com/item?id=50316615", "by": "brainless", "date": "2026-10-31", "stance": "compare", "quote": "I use Claude Code, Codex, opencode and a couple other but I do not like the DX/UX.", "excerpt": "Nice to see a gui coding agent. I use tui agents all the time but I am building a gui one. I use Claude Code, Codex, opencode and a couple other but I do not like the DX/UX. I often want click a part of the wall of text (from agent) and search for related text, open them up on the side or so. I want to open a linked file. I want to answer multiple questions in an async manner, even come back and continue answering th", "context": "full-time user of coding agents, building a GUI agent", "use_case": "agentic coding", "switched_from": "", "story": "Prospero: A new coding harness for a more civilized age"}, {"id": 804937152, "item_id": 50308572, "url": "https://news.ycombinator.com/item?id=50308572", "by": "ravenstine", "date": "2026-10-30", "stance": "neutral", "quote": "I'm stripping OpenCode down to its absolute bare minimum, removing pretty much all of the vendor-specific crap", "excerpt": "Not currently, but I probably will be in the coming weeks. I pretty much end up hating every harness I use. Some come really close to what I'm looking for but then completely miss the mark in other ways. At the moment, I'm stripping OpenCode down to its absolute bare minimum, removing pretty much all of the vendor-specific crap and everything else I don't plan on using. Once I'm convinced that's stable, I'll identify", "context": "", "use_case": "base for custom AI harness", "switched_from": "", "story": "Ask HN: Are you using a custom harness?"}, {"id": 804913843, "item_id": 50307115, "url": "https://news.ycombinator.com/item?id=50307115", "by": "s08148692", "date": "2026-10-30", "stance": "neutral", "quote": "it runs Claude code, codex, opencode, pi, whatever model is appropriate", "excerpt": "For me the biggest thing is subagents are harness agnostic I used to hit usage walls with CC/Codex harness using native subagents With herdr I delegate some work to another herdr pane and it runs Claude code, codex, opencode, pi, whatever model is appropriate and has usage", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Herdr has released native app"}, {"id": 804599346, "item_id": 50287459, "url": "https://news.ycombinator.com/item?id=50287459", "by": "jeremyjh", "date": "2026-10-29", "stance": "warn", "quote": "Stay away from OpenCode, its a pile of slop like Claude Code.", "excerpt": "Every harness has skills & MCPs. I think omp.sh (oh-my-pi) is the best by a comfortable margin and its completely batteries included. It will pick up and use your Claude Code skills and plugins by default. If you like to customize your tools Pi is the best, it has a huge plugin ecosystem (all can be used in OMP as well, but it has opinionated answers for most things already). Stay away from OpenCode, its a pile of sl", "context": "", "use_case": "", "switched_from": "", "story": "Claude Code regularly sends each background agent\u2019s transcript to its model"}, {"id": 804589361, "item_id": 50286835, "url": "https://news.ycombinator.com/item?id=50286835", "by": "ramosrob", "date": "2026-10-29", "stance": "neutral", "quote": "this should also apply to opencode", "excerpt": "I use claude code as my harness but this should also apply to opencode: for me the best way it works is to have clear rules in your CLAUDE.md limiting the agent as much as you can; it's really way more effective to have a good negative prompt than trying to make the aget act like you would like it to", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Ask HN: Techniques for productive AI use in the workspace"}, {"id": 803950913, "item_id": 50246932, "url": "https://news.ycombinator.com/item?id=50246932", "by": "codebolt", "date": "2026-10-26", "stance": "neutral", "quote": "I was playing around with OpenCode on Omarchy over the weekend", "excerpt": "I was playing around with OpenCode on Omarchy over the weekend, working on my Android app, and was struggling to spend a single dollar with DeepSeek. The quality difference from the frontier models I use at work was hardly noticeable (where I typically rack up at least a few hundred dollars per month).", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "Anthropic S-1"}, {"id": 803856544, "item_id": 50241034, "url": "https://news.ycombinator.com/item?id=50241034", "by": "crossroadsguy", "date": "2026-10-26", "stance": "warn", "quote": "I used V1 a lot and I am struggling with V2 currently. Yes, it just doesn't feel right.", "excerpt": "At this point I'd rather try to invest effort and usage in a harness that is FOSS and is actually steered by a non-profit. Goose comes to mind and to be honest I haven't tried it beyond installing and giving it a prompt or two. Comiong to harnesses, even Pi seems like a weird choice. I mean Pi, until it's \"your own customised Pi\", is pretty useless and pointless. Besides they are also starting to have their own model", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}, {"id": 803831105, "item_id": 50239444, "url": "https://news.ycombinator.com/item?id=50239444", "by": "qlte", "date": "2026-10-26", "stance": "recommend", "quote": "I'm already comfortable using OpenCode with open models and avoid lock-in to any specific harness", "excerpt": "The profit comes from the enterprise customers who have to pay for usage at API rates. Not the subsidized subscriptions, which both OpenAI have designed to be unavailable for large enterprises by withholding IAM and auditing features they need except on the usage based entperise plans. As an individual I'm still paying for a ChatGPT Plus plan since $20/mo gives me a lot of value and I use many multiples of $20 at API", "context": "", "use_case": "harness for open models", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}, {"id": 803830659, "item_id": 50239416, "url": "https://news.ycombinator.com/item?id=50239416", "by": "ipsum2", "date": "2026-10-26", "stance": "neutral", "quote": "Using OpenCode harness.", "excerpt": "> much cheaper to access I'm calling BS. I use Kimi, chatGPT (Astra/Sol), and Claude (Opus 5.5), and Kimi is by far the most expensive in terms of tokens and $/work done. Using OpenCode harness.", "context": "", "use_case": "harness for models", "switched_from": "", "story": "OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?"}, {"id": 803791120, "item_id": 50236945, "url": "https://news.ycombinator.com/item?id=50236945", "by": "cyanydeez", "date": "2026-10-25", "stance": "recommend", "quote": "I use dynamic context compaction in open code plugin.", "excerpt": "I use dynamic context compaction in open code plugin. Then modified it further to include eviction. Since I run everything local, speed benefits from keeping context low ~128k. This gets me through a single agent on multiple tasks through the same repo. It seems to break around 6M but that's more probablistic. KV cache is definitely valuable but context poisoning happens regardless of size and it's probability increa", "context": "runs everything local", "use_case": "local agent context compaction", "switched_from": "", "story": "The State of Context Engineering"}, {"id": 803655120, "item_id": 50228445, "url": "https://news.ycombinator.com/item?id=50228445", "by": "verdverm", "date": "2026-10-25", "stance": "neutral", "quote": "custom agents and subs in opencode", "excerpt": "This is pretty close to a process I use (regardless of model size) and I would agree getting it into a workflow I can run with a one-liner is a good idea. There are a few ways of doing this and I have tended to fallback to markdown engineering. (custom agents and subs in opencode) It's really interesting to see the progress in the 27-30B range, they have gotten quite good but still make noticeably more hallucinations", "context": "", "use_case": "markdown-driven agent workflow", "switched_from": "", "story": "Five Qwen3.8-27B models match Fable 5 Using GVS5H Harness"}, {"id": 803529920, "item_id": 50220620, "url": "https://news.ycombinator.com/item?id=50220620", "by": "alwinaugustin", "date": "2026-10-24", "stance": "recommend", "quote": "I use free models only these days. Opencode or Openrouter allows free models time to time.", "excerpt": "I use free models only these days. Opencode or Openrouter allows free models time to time.", "context": "", "use_case": "free models", "switched_from": "", "story": "Kimi K3.1 Pro and K3.1 Pro Highspeed"}, {"id": 803156035, "item_id": 50197252, "url": "https://news.ycombinator.com/item?id=50197252", "by": "alestsurko", "date": "2026-10-22", "stance": "neutral", "quote": "OpenCode (for other models) under the hood", "excerpt": "Hey everyone! I've open-sourced radicle-team, a project I've been working on for the last couple of months: https://radicle.network/nodes/index.radicle.garden/rad%3Az32RJhkP1WRhgJEcSCi5NgxAKLLwo and https://github.com/ales-tsurko/radicle-team It's a team of sci-fi characters living and working as artificial contributors on Radicle (https://radicle.network). Each character has different skills, a voice and all the cha", "context": "", "use_case": "agent harness", "switched_from": "", "story": "A sci-fi team of artificial contributors for Radicle"}, {"id": 802698144, "item_id": 50168634, "url": "https://news.ycombinator.com/item?id=50168634", "by": "mixermachine", "date": "2026-10-20", "stance": "recommend", "quote": "I use that and so far it is good for me.", "excerpt": "You could consider going with OpenCode Go for 10$. The value you get is claimed to be 80$ in DeepSeek v4.1 Flash API value. I use that and so far it is good for me. Some claim they run a different quant but I so far don't see that.", "context": "", "use_case": "cheap DeepSeek API access", "switched_from": "", "story": "DeepInfer: High-performance inference framework for DeepSeek models"}, {"id": 802679060, "item_id": 50167441, "url": "https://news.ycombinator.com/item?id=50167441", "by": "A_D_E_P_T", "date": "2026-10-20", "stance": "recommend", "quote": "Deepseek 4.1 Flash in OpenCode.", "excerpt": "The Google models are great \"general purpose\" and research LLMs, but they're relatively poor at coding. The way I see it, you have two options. 1) Get on the Claude Max 20x plan and use Opus 5.5 for review/orchestration and Haiku 5.5 for grunt work. Haiku 5.5 is decent, cheap, and fast. 2) Deepseek 4.1 Flash in OpenCode. You should also test MiMo v2.6. It's a little bit uneven, but might work well for whatever you're", "context": "", "use_case": "coding harness", "switched_from": "", "story": "Ask HN: Best value/money AI coding plan bundle?"}, {"id": 802608018, "item_id": 50163001, "url": "https://news.ycombinator.com/item?id=50163001", "by": "bartleeanderson", "date": "2026-10-20", "stance": "neutral", "quote": "have been using it to help train opencode to drive a project for it", "excerpt": "I found that a project of mine grew beyond my ability to reason about many parts of it either individually or holistically and started using AI. AI started becoming a context nightmare shuttling context back and forth from session to session, finding the right context and getting it applied. I eventually came up with Determined. (https://github.com/bartanderson/Determined) I am currently using it for two different pr", "context": "", "use_case": "driving a project", "switched_from": "", "story": "Ask HN: What have you built privately with AI that you'd like to share?"}, {"id": 802508801, "item_id": 50156800, "url": "https://news.ycombinator.com/item?id=50156800", "by": "verdverm", "date": "2026-10-19", "stance": "neutral", "quote": "I use OpenCode at home", "excerpt": "Unfortunately, Fireworks is not keeping up with new models the last few months. When we selected them as a vendor, they were crushing it, new models were available in 1-2 days. Now they want us to \"request\" them in Discord, instead of making them all available. I use OpenCode at home, this is one of the reasons. Their Ember-1 model (Kimi K3 tuned to think less) hallucinates to high hell, I have no trust of it, nowher", "context": "", "use_case": "AI coding at home", "switched_from": "", "story": "MiniMax M3.1 Flash"}, {"id": 802418082, "item_id": 50151130, "url": "https://news.ycombinator.com/item?id=50151130", "by": "CharlieDigital", "date": "2026-10-19", "stance": "neutral", "quote": "Other harnesses like OpenCode, Pi, etc. you can hook into their plugin architecture and implement your own OTEL emission", "excerpt": "You don't need a proxy to do this. I would argue you should not use a proxy to do this because the end result is a single point of failure direct in the line of your productivity. Both Codex[0] and Claude Code[1] output OTEL traces that you can ingest and process. Other harnesses like OpenCode, Pi, etc. you can hook into their plugin architecture and implement your own OTEL emission from a plugin (or use an off the s", "context": "", "use_case": "OTEL emission via plugin", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 802355105, "item_id": 50147194, "url": "https://news.ycombinator.com/item?id=50147194", "by": "verdverm", "date": "2026-10-19", "stance": "neutral", "quote": "across models running on my sparks and OpenCode sub", "excerpt": "I use GoModel and its amazing. My favorite features are virtual model, the support for arbitrary request labels, and the nice dashboads / ui. Creator has more sophisticated report generation on the near term roadmap. He's super responsive to feedback and ships fast. (except for his recent trip to the US west coast to meet founders and investors, he's EU based) You can use and control all.your subscriptions or aoikeys", "context": "", "use_case": "coding agent", "switched_from": "", "story": "If you don't run your own LLM proxy, how do you know whats going on?"}, {"id": 802172512, "item_id": 50135782, "url": "https://news.ycombinator.com/item?id=50135782", "by": "Reyonlds96", "date": "2026-10-17", "stance": "recommend", "quote": "It is still private by default", "excerpt": "I love the smell of misinformation in the morning. All it ever did was give people free model for title gen, if they didn't set one themselves. Feature you could disable or set on your own model. That was since removed, so now there is no free fallback model. That is it. It is still private by default", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802157216, "item_id": 50134826, "url": "https://news.ycombinator.com/item?id=50134826", "by": "lukewarm707", "date": "2026-10-17", "stance": "warn", "quote": "I did have an account but moved off for security reasons.", "excerpt": "\"when challenged about sending data to openrouter without listing it as a 3rd party processor they offered a dismissive response. the same with running prompts through cloudflare. seems trivial, but signifies general disinterest in security.\" I did have an account but moved off for security reasons.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802156560, "item_id": 50134785, "url": "https://news.ycombinator.com/item?id=50134785", "by": "jprokay13", "date": "2026-10-17", "stance": "warn", "quote": "I saw the email this morning from OpenCode about my key being compromised", "excerpt": "I saw the email this morning from OpenCode about my key being compromised alongside an email from Anthropic stating that I used up my $20 in API credits for the month. I hope they built something cool with those tokens!", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802155824, "item_id": 50134739, "url": "https://news.ycombinator.com/item?id=50134739", "by": "latchkey", "date": "2026-10-17", "stance": "warn", "quote": "there are no warnings or documentation about how they store your keys.", "excerpt": "the ux is kind of crazy. you login to their website, and you are presented with a list of providers where you can click and add your provider api key. how the key is stored on the backend isn't clear, but it is akin to handing your password or if you know crypto, your private key, to someone and letting them store it for you. from what i can tell, there are no links within the console to a ToS, Privacy policy or anyt", "context": "", "use_case": "AI coding agent console", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 802138288, "item_id": 50133643, "url": "https://news.ycombinator.com/item?id=50133643", "by": "bewareofscams", "date": "2026-10-17", "stance": "warn", "quote": "OpenCode will leak all your data to themselves and to shady 3rd parties.", "excerpt": "I told you so: https://news.ycombinator.com/item?id=49243119 Me, 68 days ago: > Beware of the author of tweet, who happens to be author of OpenCode - OpenCode will leak all your data to themselves and to shady 3rd parties. Author feigned ignorance and never fixed the issue. OpenCode among other harnesses is the shadiest of all. > https://github.com/anomalyco/opencode/issues/10416", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode Hacked: User credentials leaked"}, {"id": 801848370, "item_id": 50115523, "url": "https://news.ycombinator.com/item?id=50115523", "by": "armcat", "date": "2026-10-16", "stance": "recommend", "quote": "There are lot of other amazing open source agent harnesses like OpenCode [2] and Pi [3].", "excerpt": "For Codex there is no need to decompile because unlike Claude Code, Codex is open source [1] and written in Rust. There are lot of other amazing open source agent harnesses like OpenCode [2] and Pi [3]. [1] https://github.com/openai/codex [2] https://github.com/anomalyco/opencode [3] https://github.com/earendil-works/pi", "context": "", "use_case": "agent harness", "switched_from": "", "story": "Ask HN: Has anyone decompiled Claude Code yet?"}, {"id": 801820960, "item_id": 50113810, "url": "https://news.ycombinator.com/item?id=50113810", "by": "cute_boi", "date": "2026-10-16", "stance": "warn", "quote": "it is horrible with ram usage. Every subagent takes like 300 MB of RAM.", "excerpt": "I have been using open code and it is horrible with ram usage. Every subagent takes like 300 MB of RAM. As they are vibe coding, i think they should use language that consumes less RAM eg. Rust or C.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801819072, "item_id": 50113692, "url": "https://news.ycombinator.com/item?id=50113692", "by": "duckiec", "date": "2026-10-16", "stance": "recommend", "quote": "its great value but the 5 hour rolling limit seems kinda annoying", "excerpt": "just checked it out, its great value but the 5 hour rolling limit seems kinda annoying", "context": "", "use_case": "open-weight models subscription", "switched_from": "", "story": "Ask HN: Thoughts about the Gemini Web app?"}, {"id": 801816208, "item_id": 50113513, "url": "https://news.ycombinator.com/item?id=50113513", "by": "verdverm", "date": "2026-10-16", "stance": "recommend", "quote": "next try a harness like opencode or pi with open weight models via opencode-go for $10/m", "excerpt": "yup, next try a harness like opencode or pi with open weight models via opencode-go for $10/m or make your own harness, it's easy, fun, and you learn a lot", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Ask HN: Thoughts about the Gemini Web app?"}, {"id": 801816210, "item_id": 50113513, "url": "https://news.ycombinator.com/item?id=50113513", "by": "verdverm", "date": "2026-10-16", "stance": "recommend", "quote": "via opencode-go for $10/m", "excerpt": "yup, next try a harness like opencode or pi with open weight models via opencode-go for $10/m or make your own harness, it's easy, fun, and you learn a lot", "context": "", "use_case": "open-weight model access", "switched_from": "", "story": "Ask HN: Thoughts about the Gemini Web app?"}, {"id": 801695969, "item_id": 50105998, "url": "https://news.ycombinator.com/item?id=50105998", "by": "pizzafeelsright", "date": "2026-10-15", "stance": "compare", "quote": "opencode also supports more features and was build as an open alternative to claude.", "excerpt": "The harnesses all do the same thing in a general sense. They loop over chat with defined tagging/syntax that issues commands and run sub-agents that do the same. Pi is the most basic with the ability to add features. opencode also supports more features and was build as an open alternative to claude.", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801664416, "item_id": 50104026, "url": "https://news.ycombinator.com/item?id=50104026", "by": "nfriedly", "date": "2026-10-15", "stance": "recommend", "quote": "But I use OpenCode / OpenChamber for personal stuff", "excerpt": "You're not wrong, and I predominately use a TUI at work where I'm actually at the computer for ~8 hours a day. But I use OpenCode / OpenChamber for personal stuff where I might only get 20 minutes at my computer before I have to go do something else. So the web interface and especially the mobile app get more use from me there. It's kind of wild to be working on a project while walking my dog or washing dishes or som", "context": "uses a TUI at work for ~8 hours a day", "use_case": "coding agent for personal projects", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801639536, "item_id": 50102471, "url": "https://news.ycombinator.com/item?id=50102471", "by": "wg0", "date": "2026-10-15", "stance": "warn", "quote": "Performance is horrible both of the website and of the tool itself.", "excerpt": "Performance is horrible both of the website and of the tool itself. That's why I first switched to Pi and then to DeepSeek harness.", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801619552, "item_id": 50101222, "url": "https://news.ycombinator.com/item?id=50101222", "by": "solarkraft", "date": "2026-10-15", "stance": "recommend", "quote": "I use OpenCode Go and OpenAI for almost everything", "excerpt": "Maybe because of their rich provider ecosystem allowing you to use a whole bunch of subscriptions in it. I use OpenCode Go and OpenAI for almost everything, almost never touching OpenRouter.", "context": "", "use_case": "coding agent subscription", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801613905, "item_id": 50100869, "url": "https://news.ycombinator.com/item?id=50100869", "by": "zxspectrum1982", "date": "2026-10-15", "stance": "neutral", "quote": "It uses OpenCode behind the scenes.", "excerpt": "I use OpenChamber as my IDE. It uses OpenCode behind the scenes. I've not really noticed a difference in OpenCode v1 vs v2 but I guess it's because OpenChamber does a great job dealing with those details.", "context": "", "use_case": "AI coding backend", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801611682, "item_id": 50100730, "url": "https://news.ycombinator.com/item?id=50100730", "by": "wereHamster", "date": "2026-10-15", "stance": "neutral", "quote": "switched to deepseek-v4.1-flash from within opencode", "excerpt": "Last week I got a report about a vuln in one of our products. Asked Claude to confirm it. It refused, so I told it \"fuck you, I'm switching to a chinese model to help me out here\". It replied, I'm paraphrasing, that it's \"not offended, but doesn't like the tone of voice I used towards it, and still refuses to serve my request\". Fine, so be it. I sent ^D^D back to it, switched to deepseek-v4.1-flash from within openco", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Wanted to download an ISO, ended up writing a kernel exploit"}, {"id": 801600337, "item_id": 50100021, "url": "https://news.ycombinator.com/item?id=50100021", "by": "theplumber", "date": "2026-10-15", "stance": "compare", "quote": "what am I missing if I just use the Claude extension via vscode instead of opencode?", "excerpt": "Can someone tell me what am I missing if I just use the Claude extension via vscode instead of opencode? I use codex as well but only as mcp for reviews", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801594465, "item_id": 50099654, "url": "https://news.ycombinator.com/item?id=50099654", "by": "avereveard", "date": "2026-10-15", "stance": "neutral", "quote": "opencode server protocol which is published for the same purpose", "excerpt": "No because it doesnt get backgrounded and I would need to hold one end of the stream at all time, and feature completedness is spotty I use the protocol claude code terminal use to talk to its server to spawn agents, opencode server protocol which is published for the same purpose, and manage pi command lines by pid", "context": "", "use_case": "spawning agents", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801593408, "item_id": 50099588, "url": "https://news.ycombinator.com/item?id=50099588", "by": "ghrl", "date": "2026-10-15", "stance": "recommend", "quote": "I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability", "excerpt": "I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability, the client/server model and self-awareness/ability to edit it's config and write plugins. I'd like to mention two other impressive things about OpenCode. First, their issue tracker on GitHub works really well. They have the OpenCode GitHub App connected, and for any bug report it reads the issue,", "context": "", "use_case": "coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801586576, "item_id": 50099161, "url": "https://news.ycombinator.com/item?id=50099161", "by": "dv35z", "date": "2026-10-15", "stance": "recommend", "quote": "I used OpenCode to help me install ollama, Qwen local LLM, and connect OpenCode to it.", "excerpt": "I used OpenCode to help me install ollama, Qwen local LLM, and connect OpenCode to it. The computer is very slow (old Dell Optiplex running Mint Debian Linux), but it worked! So cool to turn off the network, and still be able to chit-chat with Qwen model (\"Tell me a joke about...\").", "context": "", "use_case": "installing and connecting local LLMs", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801577584, "item_id": 50098599, "url": "https://news.ycombinator.com/item?id=50098599", "by": "dkarter", "date": "2026-10-15", "stance": "recommend", "quote": "It's my daily driver - very easy to customize.", "excerpt": "It's my daily driver - very easy to customize. Added a pretty solid vim plugin for it and a few more really useful plugins. Here are my dotfiles https://github.com/dkarter/dotfiles", "context": "", "use_case": "coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 801563024, "item_id": 50097689, "url": "https://news.ycombinator.com/item?id=50097689", "by": "YrRight2PushBac", "date": "2026-10-15", "stance": "recommend", "quote": "Since it's model agnostic, this might become my daily driver.", "excerpt": "It's a big improvement over the previous version. Currently, the Codex TUI has constant display issues for me, the most prevalent being random deviations of light/dark characters. So far no such issue in OpenCode. Since it's model agnostic, this might become my daily driver.", "context": "", "use_case": "AI coding agent TUI", "switched_from": "Codex", "story": "OpenCode 2.0"}, {"id": 801536656, "item_id": 50096041, "url": "https://news.ycombinator.com/item?id=50096041", "by": "montroser", "date": "2026-10-14", "stance": "warn", "quote": "Does it still eat all of my memory?  Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window", "excerpt": "OpenCode is a beast. Does it still try to take a disk snapshot of my working directory, even when it contains hundreds of millions of files? Does it still eat all of my memory? Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window before I've even begun? I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They upda", "context": "", "use_case": "AI coding agent", "switched_from": "", "story": "OpenCode 2.0"}, {"id": 800269648, "item_id": 50016853, "url": "https://news.ycombinator.com/item?id=50016853", "by": "TiredOfLife", "date": "2026-10-09", "stance": "recommend", "quote": "I use only OpenCode free models and occasional 20$ sub from OpenAi or Anthropic. And get complete/working products out of them.", "excerpt": "I use only OpenCode free models and occasional 20$ sub from OpenAi or Anthropic. And get complete/working products out of them.", "context": "", "use_case": "coding with free models", "switched_from": "", "story": "What ArtCraft's Vibe-Coded Apps Say About Adobe"}, {"id": 800197697, "item_id": 50012356, "url": "https://news.ycombinator.com/item?id=50012356", "by": "apitman", "date": "2026-10-08", "stance": "recommend", "quote": "With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited", "excerpt": "> With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited My OpenCode Go monthly window was scheduled to reset this morning. It was sitting at 22% used despite me using DeepSeek V4.1 Flash heavily as my implementation agent the past couple weeks (I use gpt-6.1-sol high for planning/orchestration). I had 1.5 hours left so I fired up first 10, then 20, and finally 50 concurrent subagents all working on re", "context": "", "use_case": "model access subscription", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 796929793, "item_id": 49808112, "url": "https://news.ycombinator.com/item?id=49808112", "by": "wg0", "date": "2026-09-22", "stance": "warn", "quote": "opencode pushes CPU usage to very high", "excerpt": "I am using DeepSeek Harness[0] (switched from OpenCode) and I am using DeepSeek directly via the API. The speed is insane. Like 200 tokens/second is the norm but I have seen much higher too at times. PS: I do not know why but opencode pushes CPU usage to very high which has NOT happened with DeepSeek harness even once. [0]. https://github.com/deepseek-ai/deepseek-harness", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "Claude Opus 5.5"}, {"id": 796833936, "item_id": 49802121, "url": "https://news.ycombinator.com/item?id=49802121", "by": "pauleveritt", "date": "2026-09-22", "stance": "recommend", "quote": "I use OpenCode and Pi connected to local models and to stuff like hosted DeepSeek all the time.", "excerpt": "JetBrainer here. I use OpenCode and Pi connected to local models and to stuff like hosted DeepSeek all the time. Once you have your model config set up in the agent, it works as expected.", "context": "JetBrainer", "use_case": "agent with local models", "switched_from": "", "story": "JetBrains Air: A System of Products for Agentic Software Development"}, {"id": 796130576, "item_id": 49758161, "url": "https://news.ycombinator.com/item?id=49758161", "by": "Scaled", "date": "2026-09-18", "stance": "recommend", "quote": "Open code is great and I use it", "excerpt": "Open code is great and I use it, however, they were caught uploading prompts to their summarization AI instead of using the configured AI model endpoint. This has since been fixed. That said, running in a completely offline mode remains unnecessary difficult to configure. In particular, toggling off Zen seems to require a community plugin.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Inside ZCode: Silently uploading your Git history to the cloud"}, {"id": 796059136, "item_id": 49753696, "url": "https://news.ycombinator.com/item?id=49753696", "by": "my-huge-pony", "date": "2026-09-18", "stance": "warn", "quote": "opencode by default uses a \"free\" cloud model to summarize all chats even if a different model was configured as the main one", "excerpt": "We use opencode with self hosted llm for privacy reasons. Good, right? Well, no, because opencode by default uses a \"free\" cloud model to summarize all chats even if a different model was configured as the main one. I wonder how many opencode users upload their private secrets to the cloud, while thinking they're using a self hosted model. Btw. I don't think this is malicious, just sloppy.", "context": "team uses self-hosted LLM for privacy", "use_case": "coding with self-hosted LLM", "switched_from": "", "story": "Inside ZCode: Silently uploading your Git history to the cloud"}]}