{"slug": "continue", "name": "Continue", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 4, "commenters": 17, "warners": 6, "score": -0.347, "rising": -1.31, "first": "2025-11-01", "latest": "2026-06-24", "why": "We copied a lot of code from Continue.dev (best open source autocomplete in our view).", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 8, "compare": 0, "warn": 7}, "spark": [2, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "We copied a lot of code from Continue.dev (best open source autocomplete in our view).", "kind": "", "icon": true, "domain": "continue.dev", "github_repo": null, "official_url": "https://www.continue.dev", "pricing": "", "aliases": ["Continue", "Continue.dev", "continue.dev"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 756837553, "item_id": 47302347, "url": "https://news.ycombinator.com/item?id=47302347", "by": "esafak", "date": "2026-03-08", "version": null, "stance": "recommend", "quote": "or https://www.continue.dev/", "excerpt": "If you have CI hooked up to AI you could you just use a SLM to do that in a periodic job with https://github.github.com/gh-aw/ or https://www.continue.dev/. You could also have it detect architectural drift.", "context": "", "use_case": "", "switched_from": "", "story": "We should revisit literate programming in the agent era"}, {"id": 750266496, "item_id": 46891656, "url": "https://news.ycombinator.com/item?id=46891656", "by": "alexhans", "date": "2026-02-04", "version": null, "stance": "recommend", "quote": "is easy to try out and see if it meets your needs", "excerpt": "What are your needs/constraints (hardware constraints definitely a big one)? The one I mentioned called continue.dev [1] is easy to try out and see if it meets your needs. Hitting local models with it should be very easy (it calls APIs at a specific port) [1] - https://github.com/continuedev/continue", "context": "", "use_case": "local-model coding assistant", "switched_from": "", "story": "Claude Code: connect to a local model when your quota runs out"}, {"id": 736463588, "item_id": 46028974, "url": "https://news.ycombinator.com/item?id=46028974", "by": "sytse", "date": "2025-11-23", "version": null, "stance": "recommend", "quote": "We copied a lot of code from Continue.dev (best open source autocomplete in our view).", "excerpt": "At Kilo (VScode plugin, BYOK so works with Claude Pro) we just rolled out autocomplete to 10% of our user base on Friday and we're happy with what we're seeing. The autocomplete is based a Mistal model (Codestral) that is fast and accurate https://mistral.ai/news/codestral We copied a lot of code from Continue.dev (best open source autocomplete in our view). We plan to roll it out to 100% of our users no later than T", "context": "", "use_case": "", "switched_from": "", "story": "Sunsetting Supermaven"}, {"id": 733160048, "item_id": 45822503, "url": "https://news.ycombinator.com/item?id=45822503", "by": "lolive", "date": "2025-11-05", "version": null, "stance": "recommend", "quote": "Isn't Continue supposed to help you do that, in VSCode?", "excerpt": "Isn't Continue supposed to help you do that, in VSCode? https://marketplace.visualstudio.com/items?itemName=Continue.continue", "context": "", "use_case": "switching between AI models", "switched_from": "", "story": "Developers are choosing older AI models"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 778675073, "item_id": 48667192, "url": "https://news.ycombinator.com/item?id=48667192", "by": "anigbrowl", "date": "2026-06-24", "version": null, "stance": "warn", "quote": "Second headache was a lot of frustration with the Continue plugin in my IDE.", "excerpt": "So a couple weeks ago I decided to pay some money for the Gemini API cause I'd found myself getting a lot of use out of the free tier chat and figured they deserved some of my cash. First headache was a lot of delays and 'service unavailable due to excessive load messages'. Second headache was a lot of frustration with the Continue plugin in my IDE. Gemini chat suggests I try the Antigravity app. I do so. IT's OK. La", "context": "", "use_case": "IDE AI plugin", "switched_from": "", "story": "Computer use in Gemini 3.5 Flash"}, {"id": 776936482, "item_id": 48558530, "url": "https://news.ycombinator.com/item?id=48558530", "by": "cornhole", "date": "2026-06-16", "version": null, "stance": "warn", "quote": "continue is eol after being acquired by cursor/spacex", "excerpt": "continue is eol after being acquired by cursor/spacex https://www.continue.dev/", "context": "", "use_case": "", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776783584, "item_id": 48548974, "url": "https://news.ycombinator.com/item?id=48548974", "by": "rvz", "date": "2026-06-15", "version": null, "stance": "warn", "quote": "The continuedev/continue repository is no longer actively maintained and is read-only for all users.", "excerpt": "From https://github.com/continuedev/continue > \"Note: The continuedev/continue repository is no longer actively maintained and is read-only for all users.\"", "context": "", "use_case": "", "switched_from": "", "story": "Continue has been acquired by Cursor"}, {"id": 766834530, "item_id": 47927158, "url": "https://news.ycombinator.com/item?id=47927158", "by": "notatoad", "date": "2026-04-27", "version": null, "stance": "warn", "quote": "i tried the continue vscode extension, and it seemed kind of janky.", "excerpt": "so what's everybody using to get autocompletions in vscode? i've been using copilot just because $10 is cheap, but i use opencode for everything other than completions. i tried the continue vscode extension, and it seemed kind of janky. are there better options?", "context": "", "use_case": "autocompletions in VS Code", "switched_from": "", "story": "GitHub Copilot is moving to usage-based billing"}]}], "who": [], "tags": [], "use_cases": ["ide ai plugin", "autocompletions in vs code", "vs code ai assistant", "code autocompletion", "vs code code completion", "local-model coding assistant"], "compared": [{"slug": "cline", "name": "Cline", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "qwen", "name": "Qwen", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "ollama", "name": "Ollama", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "aider", "name": "Aider", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "cursor", "name": "Cursor", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "github-copilot", "name": "GitHub Copilot", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 752810816, "item_id": 47050676, "url": "https://news.ycombinator.com/item?id=47050676", "by": "sestinj", "date": "2026-02-17", "version": null, "stance": "recommend", "quote": "our checks product is powered by an open-source CLI (we think this is important), which we recommend for jetbrains users", "excerpt": "That's us! I figure others will wonder the same, so we wrote about what exactly we're doing here: https://blog.continue.dev/from-extension-to-mission-control tl;dr - a _lot_ of people still use the VS Code extension and so we're still putting energy toward keeping it polished (this becomes easier with checks : )) - our checks product is powered by an open-source CLI (we think this is important), which we recommend fo", "context": "", "use_case": "source-controlled AI checks in CI", "switched_from": "", "story": "Show HN: Continue \u2013 Source-controlled AI checks, enforceable in CI"}], "threads": [{"url": "https://news.ycombinator.com/item?id=47049848", "title": "Show HN: Continue \u2013 Source-controlled AI checks, enforceable in CI", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46845845", "title": "Claude Code: connect to a local model when your quota runs out", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48662999", "title": "Computer use in Gemini 3.5 Flash", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48553224", "title": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48548758", "title": "Continue has been acquired by Cursor", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47923357", "title": "GitHub Copilot is moving to usage-based billing", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 3, "recommend": 2}, "2025-12": {"warn": 1, "neutral": 1}, "2026-01": {}, "2026-02": {"recommend": 1, "neutral": 3}, "2026-03": {"recommend": 1, "warn": 1}, "2026-04": {"warn": 2, "neutral": 1}, "2026-05": {}, "2026-06": {"warn": 3}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 778675073, "item_id": 48667192, "url": "https://news.ycombinator.com/item?id=48667192", "by": "anigbrowl", "date": "2026-06-24", "version": null, "stance": "warn", "quote": "Second headache was a lot of frustration with the Continue plugin in my IDE.", "excerpt": "So a couple weeks ago I decided to pay some money for the Gemini API cause I'd found myself getting a lot of use out of the free tier chat and figured they deserved some of my cash. First headache was a lot of delays and 'service unavailable due to excessive load messages'. Second headache was a lot of frustration with the Continue plugin in my IDE. Gemini chat suggests I try the Antigravity app. I do so. IT's OK. La", "context": "", "use_case": "IDE AI plugin", "switched_from": "", "story": "Computer use in Gemini 3.5 Flash"}, {"id": 776936482, "item_id": 48558530, "url": "https://news.ycombinator.com/item?id=48558530", "by": "cornhole", "date": "2026-06-16", "version": null, "stance": "warn", "quote": "continue is eol after being acquired by cursor/spacex", "excerpt": "continue is eol after being acquired by cursor/spacex https://www.continue.dev/", "context": "", "use_case": "", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776783584, "item_id": 48548974, "url": "https://news.ycombinator.com/item?id=48548974", "by": "rvz", "date": "2026-06-15", "version": null, "stance": "warn", "quote": "The continuedev/continue repository is no longer actively maintained and is read-only for all users.", "excerpt": "From https://github.com/continuedev/continue > \"Note: The continuedev/continue repository is no longer actively maintained and is read-only for all users.\"", "context": "", "use_case": "", "switched_from": "", "story": "Continue has been acquired by Cursor"}, {"id": 766834530, "item_id": 47927158, "url": "https://news.ycombinator.com/item?id=47927158", "by": "notatoad", "date": "2026-04-27", "version": null, "stance": "warn", "quote": "i tried the continue vscode extension, and it seemed kind of janky.", "excerpt": "so what's everybody using to get autocompletions in vscode? i've been using copilot just because $10 is cheap, but i use opencode for everything other than completions. i tried the continue vscode extension, and it seemed kind of janky. are there better options?", "context": "", "use_case": "autocompletions in VS Code", "switched_from": "", "story": "GitHub Copilot is moving to usage-based billing"}, {"id": 766302657, "item_id": 47893916, "url": "https://news.ycombinator.com/item?id=47893916", "by": "y42", "date": "2026-04-24", "version": null, "stance": "neutral", "quote": "Continue in VS Code", "excerpt": "I am trying Qwen3.5-9B-Claude-4.6 since a couple of days now locally coming from OMLX. Either via Hermes or Continue in VS Code. It's oka'ish, even performance-wise. [1] https://huggingface.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF", "context": "", "use_case": "VS Code AI assistant", "switched_from": "", "story": "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"}, {"id": 764697104, "item_id": 47793569, "url": "https://news.ycombinator.com/item?id=47793569", "by": "dataflow", "date": "2026-04-16", "version": null, "stance": "warn", "quote": "When I use them with Continue in VSCode and start typing basic C", "excerpt": "I'm a newbie here and lost how I'm supposed to use these models for coding. When I use them with Continue in VSCode and start typing basic C: #include <stdio.h> int m I get nonsensical autocompletions like: #include <stdio.h> int m</fim_prefix> What is going on?", "context": "newbie", "use_case": "code autocompletion", "switched_from": "", "story": "Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All"}, {"id": 758353824, "item_id": 47397114, "url": "https://news.ycombinator.com/item?id=47397114", "by": "KronisLV", "date": "2026-03-16", "version": null, "stance": "warn", "quote": "Continue.dev (kind of broken regardless of models)", "excerpt": "Previously, both tools and providers: - Continue.dev (kind of broken regardless of models) - Aider (unpleasant for me to use, too much busywork) - GitHub Copilot (tbh nice plugins and generous quotas + the only working autocomplete that's actually good I've tried) - JetBrains AI and Junie (since I already pay for their IDEs, that came bundled), also nice but quotas are quite limiting - local models with Ollama or lla", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: How is AI-assisted coding going for you professionally?"}, {"id": 756837553, "item_id": 47302347, "url": "https://news.ycombinator.com/item?id=47302347", "by": "esafak", "date": "2026-03-08", "version": null, "stance": "recommend", "quote": "or https://www.continue.dev/", "excerpt": "If you have CI hooked up to AI you could you just use a SLM to do that in a periodic job with https://github.github.com/gh-aw/ or https://www.continue.dev/. You could also have it detect architectural drift.", "context": "", "use_case": "", "switched_from": "", "story": "We should revisit literate programming in the agent era"}, {"id": 752812432, "item_id": 47050777, "url": "https://news.ycombinator.com/item?id=47050777", "by": "esafak", "date": "2026-02-17", "version": null, "stance": "neutral", "quote": "Do you support exporting metrics to something standard like CSV?", "excerpt": "This looks likes a more configurable version of the code review tools out there, for running arbitrary AI-powered tasks. Do you support exporting metrics to something standard like CSV? https://docs.continue.dev/mission-control/metrics A brief demo would be nice too.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Continue \u2013 Source-controlled AI checks, enforceable in CI"}, {"id": 750335072, "item_id": 46895942, "url": "https://news.ycombinator.com/item?id=46895942", "by": "seanmcdirmid", "date": "2026-02-04", "version": null, "stance": "neutral", "quote": "For VS Code code completion in Continue", "excerpt": "I have a M3 max 64GB. For VS Code code completion in Continue using a Qwen3-coder 7b model. For CLI work Qwen coder 32b for sidebar. 8 bit quant for both. I need to take a look at Qwen3-coder-next, it is supposed to have made things much faster with a larger model.", "context": "", "use_case": "VS Code code completion", "switched_from": "", "story": "Claude Code: connect to a local model when your quota runs out"}, {"id": 750308704, "item_id": 46894294, "url": "https://news.ycombinator.com/item?id=46894294", "by": "eek2121", "date": "2026-02-04", "version": null, "stance": "neutral", "quote": "you more than likely will need to understand things like https://continue.dev", "excerpt": "I do feel like many folks here and elsewhere are missing the mark with LLMs. 1) Yes, they are absolutely useless in a consumer setting. 2) If you want to be a software developer, you absolutely need to know how to understand/interact with one, and you more than likely will need to understand things like https://continue.dev. I am no longer in software development due to my body slowly (quickly) dying, however I see i", "context": "", "use_case": "", "switched_from": "", "story": "Claude Is a Space to Think"}, {"id": 750266496, "item_id": 46891656, "url": "https://news.ycombinator.com/item?id=46891656", "by": "alexhans", "date": "2026-02-04", "version": null, "stance": "recommend", "quote": "is easy to try out and see if it meets your needs", "excerpt": "What are your needs/constraints (hardware constraints definitely a big one)? The one I mentioned called continue.dev [1] is easy to try out and see if it meets your needs. Hitting local models with it should be very easy (it calls APIs at a specific port) [1] - https://github.com/continuedev/continue", "context": "", "use_case": "local-model coding assistant", "switched_from": "", "story": "Claude Code: connect to a local model when your quota runs out"}, {"id": 741943956, "item_id": 46371497, "url": "https://news.ycombinator.com/item?id=46371497", "by": "reactordev", "date": "2025-12-23", "version": null, "stance": "neutral", "quote": "I use continue.dev in VSCode", "excerpt": "I\u2019ll chime in and say I run LM Studio on my 2021 MacBook Pro M1 with no issues. I have 16GB ram. I use unsloth quantized models like qwen3 and gpt-oss. I have some MCP servers like Context7 and Fetch that make sure the models have up to date information. I use continue.dev in VSCode or OpenCode Agent with LM Studio and write C++ code against Vulkan. It\u2019s more than capable. Is it fast? Not necessarily. Does it get stu", "context": "", "use_case": "", "switched_from": "", "story": "Local AI is driving the biggest change in laptops in decades"}, {"id": 739299307, "item_id": 46206206, "url": "https://news.ycombinator.com/item?id=46206206", "by": "KronisLV", "date": "2025-12-09", "version": null, "stance": "warn", "quote": "Continue.dev is trash", "excerpt": "> User feedback was consistent: If you already work with IntelliJ IDEA, Rider, WebStorm, PyCharm, or any other JetBrains IDE, switching to Fleet required a strong reason \u2013 and Fleet did not offer enough value to justify the transition from IDEs you already know and love. My problem was that Fleet just wasn't very good when compared with VSC. For my more serious development I use JetBrains IDEs (one of the few pieces ", "context": "", "use_case": "", "switched_from": "", "story": "JetBrains cancels Fleet"}, {"id": 736669393, "item_id": 46041837, "url": "https://news.ycombinator.com/item?id=46041837", "by": "aiandsons", "date": "2025-11-24", "version": null, "stance": "neutral", "quote": "Continue.dev in VS Code", "excerpt": "Author here. This is a write-up of how I replaced most of my usage of Gemini CLI / Copilot / Claude-CLI with a local stack built on: - Ollama (Nemotron-9B, Qwen3-8B, etc.) - Continue.dev in VS Code - MCP servers (Filesystem, Git, Fetch, XRAY, SQLite, Snyk\u2026) It includes: - Actual hardware specs (Win 11 laptop, 8 GB VRAM) - Model selection from Hugging Face GGUF \u2192 Ollama - Step-by-step setup and maintenance - Some agen", "context": "", "use_case": "", "switched_from": "", "story": null}, {"id": 736463588, "item_id": 46028974, "url": "https://news.ycombinator.com/item?id=46028974", "by": "sytse", "date": "2025-11-23", "version": null, "stance": "recommend", "quote": "We copied a lot of code from Continue.dev (best open source autocomplete in our view).", "excerpt": "At Kilo (VScode plugin, BYOK so works with Claude Pro) we just rolled out autocomplete to 10% of our user base on Friday and we're happy with what we're seeing. The autocomplete is based a Mistal model (Codestral) that is fast and accurate https://mistral.ai/news/codestral We copied a lot of code from Continue.dev (best open source autocomplete in our view). We plan to roll it out to 100% of our users no later than T", "context": "", "use_case": "", "switched_from": "", "story": "Sunsetting Supermaven"}, {"id": 733280932, "item_id": 45830058, "url": "https://news.ycombinator.com/item?id=45830058", "by": "woustachemax", "date": "2025-11-05", "version": null, "stance": "neutral", "quote": "auto-generates context files for tools like Cursor, Windsurf, Cline, Continue & Aider", "excerpt": "I built QuackStack to solve a simple problem: getting lost in giant codebases. It indexes your project using local AI embeddings and lets you ask questions directly to your code. No API calls. No leaks. No vendor lock-in. It auto-generates context files for tools like Cursor, Windsurf, Cline, Continue & Aider, so your AI assistants instantly understand your codebase\u2019s structure. Check it out: https://quackstack.siddh", "context": "", "use_case": "", "switched_from": "", "story": "QuackStack"}, {"id": 733160048, "item_id": 45822503, "url": "https://news.ycombinator.com/item?id=45822503", "by": "lolive", "date": "2025-11-05", "version": null, "stance": "recommend", "quote": "Isn't Continue supposed to help you do that, in VSCode?", "excerpt": "Isn't Continue supposed to help you do that, in VSCode? https://marketplace.visualstudio.com/items?itemName=Continue.continue", "context": "", "use_case": "switching between AI models", "switched_from": "", "story": "Developers are choosing older AI models"}, {"id": 732508577, "item_id": 45781786, "url": "https://news.ycombinator.com/item?id=45781786", "by": "Balinares", "date": "2025-11-01", "version": null, "stance": "neutral", "quote": "Does Qwen3 Coder do a good job invoking its tools as appropriate for you? Under continue.dev at least, I've found I need to remind it constantly.", "excerpt": "Does Qwen3 Coder do a good job invoking its tools as appropriate for you? Under continue.dev at least, I've found I need to remind it constantly.", "context": "", "use_case": "IDE AI integration", "switched_from": "", "story": "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"}]}