{"slug": "kimi-code", "name": "Kimi Code", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 8, "commenters": 20, "warners": 2, "score": 7.883, "rising": 0.04, "first": "2026-01-27", "latest": "2026-10-17", "why": "So I personally like/stick with the kimi cli for kimi coding.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 8, "neutral": 12, "compare": 1, "warn": 2}, "spark": [0, 0, 2, 1, 1, 0, 1, 0, 1, 1, 0, 1], "listed": true, "loved": [], "caveat": "", "short_quote": "So I personally like/stick with the kimi cli for kimi coding.", "kind": "", "icon": true, "domain": "kimi.com", "github_repo": null, "official_url": "https://kimi.com", "pricing": "", "aliases": ["Kimi Code", "Kimi CLI", "Kimi Code CLI", "KimiCode", "kimi-cli", "kimi-code"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 799681042, "item_id": 49980065, "url": "https://news.ycombinator.com/item?id=49980065", "by": "dools", "date": "2026-10-06", "stance": "recommend", "quote": "Kimi Code and Pi kept winning", "excerpt": "This is interesting to me because I only started using JetBrains IntelliJ IDEA specifically to do AI coding. It was the first time I'd used an IDE, the first time I'd built a cross platform app, first time I'd used Kotlin, and the first time I'd tried AI coding. The journey started with choosing KMP as the stack, then I figured \"here's the company that released KMP, they have an IDE, they have AI, I'll use that\". It ", "context": "", "use_case": "parallel background coding agents", "switched_from": "Junie CLI", "story": "JetBrains reports revenue growth, net financial loss for 2025"}, {"id": 788624932, "item_id": 49289058, "url": "https://news.ycombinator.com/item?id=49289058", "by": "SwellJoe", "date": "2026-08-13", "stance": "recommend", "quote": "Kimi Code is also very good", "excerpt": "DeepSeek is more fun, because it's cheap-as-free, Good Enough, quite fast. I use it for all API stuff, automated runs, testing of the security auditing harness and benchmarks I'm working on, etc. Kimi K3 is smarter, though. At least smarter than DeepSeek V4 Flash 0731. I haven't tried the new Pro version, but will this weekend when I'm working on my personal projects But, K3 has been what I've been using for the actu", "context": "", "use_case": "agent harness", "switched_from": "", "story": "Qwen/Qwen3.8-2.4T-A95B"}, {"id": 783005856, "item_id": 48937866, "url": "https://news.ycombinator.com/item?id=48937866", "by": "igravious", "date": "2026-07-16", "stance": "recommend", "quote": "Kimi has Kimi Code :)", "excerpt": "Kimi has Kimi Code :) kimi-code https://www.kimi.com/code/en", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 773152993, "item_id": 48322062, "url": "https://news.ycombinator.com/item?id=48322062", "by": "mariopt", "date": "2026-05-29", "stance": "recommend", "quote": "Kimi performs better with kimi-cli and also save a bit of quota", "excerpt": "I use opencode with all of them except Kimi, I noticed Kimi performs better with kimi-cli and also save a bit of quota. Z.ai does recommend to use claude cli as a harness for GLM5.1, I still get good results with opencode.", "context": "", "use_case": "harness for Kimi models", "switched_from": "", "story": "Claude Opus 4.8"}, {"id": 756608401, "item_id": 47288025, "url": "https://news.ycombinator.com/item?id=47288025", "by": "igravious", "date": "2026-03-07", "stance": "recommend", "quote": "I use Claude Code and Kimi CLI", "excerpt": "two AIs -- I use Claude Code and Kimi CLI -- I got them to build an agent relay so they can communicate with each other (one plans, the other reviews the plan; one builds, the other reviews the build) -- while one is working on one thing, I'll be chatting and exploring with the other one \u2026 they can build anything in any language so if you are a skilled and experienced code you should be able to guide a pair of coding", "context": "", "use_case": "", "switched_from": "", "story": "I'm 60 years old. Claude Code has ignited a passion again"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 796342275, "item_id": 49771392, "url": "https://news.ycombinator.com/item?id=49771392", "by": "muzani", "date": "2026-09-20", "stance": "warn", "quote": "Kimi code and similar which can't keep up with the existing demand", "excerpt": "I've moved to Codex lately, Astra does better with less bugs. When GPT does poorly, I use Cursor. The autocomplete itself is extremely good. And then there's Kimi code and similar which can't keep up with the existing demand, much less the demand if all other tools go down. Then Opencode, which would probably be a year or so behind SOTA but it's good enough.", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What happens when Claude Code goes away?"}, {"id": 784045012, "item_id": 49002813, "url": "https://news.ycombinator.com/item?id=49002813", "by": "KronisLV", "date": "2026-07-22", "stance": "warn", "quote": "Kimi Code and OpenCode desktop/web offerings still aren't great", "excerpt": "> How much time do you spend on your setup vs getting a lot of stuff shipped by paying for Fable 5? Relatively speaking, quite little (and it's more interesting than some of the stuff I'm otherwise shipping). I did write a tool to manage 3rd party providers for Claude Code: https://ccode.kronis.dev/ However, in the end I figured out that for the terminal use cases OpenCode is really comfy (provider TUI solutions are ", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"}, {"id": 783747969, "item_id": 48984248, "url": "https://news.ycombinator.com/item?id=48984248", "by": "KronisLV", "date": "2026-07-20", "stance": "warn", "quote": "really slows down with long conversations to the point where keyboard input lags by seconds", "excerpt": "I wish they'd embed the Code UI as a tab, similar to Claude Code Desktop. There's really no real reason for those tools to be separate and for them not to give me something a bit nicer than just a TUI in the terminal. They already have a locally runnable web UI when you have Kimi (the CLI) installed: https://www.kimi.com/help/kimi-code/cli-getting-started kimi server run --foreground Though it's ever so slightly brok", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Work"}]}], "who": [], "tags": [], "use_cases": ["running kimi for coding", "parallel background coding agents", "agent harness", "coding agent", "harness for kimi models", "coding agent cli"], "compared": [{"slug": "kimi", "name": "Kimi", "co": 13, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "pi", "name": "Pi", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46826597", "title": "Kimi K2.5 Technical Report [pdf]", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49101852", "title": "Kimi K3-256k", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48981703", "title": "Kimi Work", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46775961", "title": "Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50129045", "title": "DeepSeek-v4.1-Flash-1017", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50063427", "title": "AI is a tool and using it well takes skill", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 2, "neutral": 4}, "2026-02": {"recommend": 1}, "2026-03": {"recommend": 1}, "2026-04": {"neutral": 2}, "2026-05": {"neutral": 1, "recommend": 1}, "2026-06": {}, "2026-07": {"recommend": 1, "compare": 1, "warn": 1, "neutral": 3}, "2026-08": {"recommend": 1}, "2026-09": {"warn": 1}, "2026-10": {"recommend": 1, "neutral": 2}}, "quotes": [{"id": 802074019, "item_id": 50129626, "url": "https://news.ycombinator.com/item?id=50129626", "by": "nickludlam", "date": "2026-10-17", "stance": "neutral", "quote": "I use each of them in their own respective coding harnesses, deepseek-harness and kimi-code", "excerpt": "This and (the not quite yet open) Kimi K2.8 are my main coding engines, and I find them incredibly cost efficient. I find Deepseek in particular is really good with Svelte work. Right now I use each of them in their own respective coding harnesses, deepseek-harness and kimi-code, but I do wonder what they are like inside something like opencode.", "context": "", "use_case": "running Kimi for coding", "switched_from": "", "story": "DeepSeek-v4.1-Flash-1017"}, {"id": 801021441, "item_id": 50063840, "url": "https://news.ycombinator.com/item?id=50063840", "by": "schleck8", "date": "2026-10-12", "stance": "neutral", "quote": "https://github.com/MoonshotAI/kimi-code", "excerpt": "> It\u2019s a shame I cannot inspect the tool. It\u2019s a shame I cannot modify it as I see fit. https://github.com/openai/codex https://github.com/MoonshotAI/kimi-code https://github.com/mistralai/mistral-vibe https://github.com/earendil-works/pi https://claude.com/de/resources/articles/claude-code-mods", "context": "", "use_case": "", "switched_from": "", "story": "AI is a tool and using it well takes skill"}, {"id": 799681042, "item_id": 49980065, "url": "https://news.ycombinator.com/item?id=49980065", "by": "dools", "date": "2026-10-06", "stance": "recommend", "quote": "Kimi Code and Pi kept winning", "excerpt": "This is interesting to me because I only started using JetBrains IntelliJ IDEA specifically to do AI coding. It was the first time I'd used an IDE, the first time I'd built a cross platform app, first time I'd used Kotlin, and the first time I'd tried AI coding. The journey started with choosing KMP as the stack, then I figured \"here's the company that released KMP, they have an IDE, they have AI, I'll use that\". It ", "context": "", "use_case": "parallel background coding agents", "switched_from": "Junie CLI", "story": "JetBrains reports revenue growth, net financial loss for 2025"}, {"id": 796342275, "item_id": 49771392, "url": "https://news.ycombinator.com/item?id=49771392", "by": "muzani", "date": "2026-09-20", "stance": "warn", "quote": "Kimi code and similar which can't keep up with the existing demand", "excerpt": "I've moved to Codex lately, Astra does better with less bugs. When GPT does poorly, I use Cursor. The autocomplete itself is extremely good. And then there's Kimi code and similar which can't keep up with the existing demand, much less the demand if all other tools go down. Then Opencode, which would probably be a year or so behind SOTA but it's good enough.", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What happens when Claude Code goes away?"}, {"id": 788624932, "item_id": 49289058, "url": "https://news.ycombinator.com/item?id=49289058", "by": "SwellJoe", "date": "2026-08-13", "stance": "recommend", "quote": "Kimi Code is also very good", "excerpt": "DeepSeek is more fun, because it's cheap-as-free, Good Enough, quite fast. I use it for all API stuff, automated runs, testing of the security auditing harness and benchmarks I'm working on, etc. Kimi K3 is smarter, though. At least smarter than DeepSeek V4 Flash 0731. I haven't tried the new Pro version, but will this weekend when I'm working on my personal projects But, K3 has been what I've been using for the actu", "context": "", "use_case": "agent harness", "switched_from": "", "story": "Qwen/Qwen3.8-2.4T-A95B"}, {"id": 785665552, "item_id": 49104097, "url": "https://news.ycombinator.com/item?id=49104097", "by": "vidarh", "date": "2026-07-29", "stance": "neutral", "quote": "What Kimi CLI does is insert <system> tags", "excerpt": "No. Prefix caching is just an optimisation on the server side. What Kimi CLI does is insert <system> tags that include a checkpoint marker with an id. The model is then given a tool that allows the model to decide to roll back to a checkpoint + a message containing any additional useful information. It's specifically instructed to use that tool[1] in cases like when it has inadvertendly read a large file where most o", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3-256k"}, {"id": 785665553, "item_id": 49104097, "url": "https://news.ycombinator.com/item?id=49104097", "by": "vidarh", "date": "2026-07-29", "stance": "neutral", "quote": "they seem to be abandoning it in their new CLI (kimi-code)", "excerpt": "No. Prefix caching is just an optimisation on the server side. What Kimi CLI does is insert <system> tags that include a checkpoint marker with an id. The model is then given a tool that allows the model to decide to roll back to a checkpoint + a message containing any additional useful information. It's specifically instructed to use that tool[1] in cases like when it has inadvertendly read a large file where most o", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3-256k"}, {"id": 784668369, "item_id": 49041773, "url": "https://news.ycombinator.com/item?id=49041773", "by": "SwellJoe", "date": "2026-07-24", "stance": "neutral", "quote": "I used Kimi Code with K3 to add support for Kimi Code to flar", "excerpt": "I have no idea. Seems like normal stuff. I used Kimi Code with K3 to add support for Kimi Code to flar (https://swelljoe.com/post/i-let-every-agent-implement-its-own-flar-backend/), a task I've done with almost every major model/agent combo. Most show up as a blip on the usage chart...it's basically usually one file, a README update, and adding the agent name to the CLI. Then, I added it to my benchmark of security v", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Claude Opus 5"}, {"id": 784045012, "item_id": 49002813, "url": "https://news.ycombinator.com/item?id=49002813", "by": "KronisLV", "date": "2026-07-22", "stance": "warn", "quote": "Kimi Code and OpenCode desktop/web offerings still aren't great", "excerpt": "> How much time do you spend on your setup vs getting a lot of stuff shipped by paying for Fable 5? Relatively speaking, quite little (and it's more interesting than some of the stuff I'm otherwise shipping). I did write a tool to manage 3rd party providers for Claude Code: https://ccode.kronis.dev/ However, in the end I figured out that for the terminal use cases OpenCode is really comfy (provider TUI solutions are ", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"}, {"id": 783759440, "item_id": 48984965, "url": "https://news.ycombinator.com/item?id=48984965", "by": "alexjameson", "date": "2026-07-20", "stance": "neutral", "quote": "Most docs are here", "excerpt": "Most docs are here https://www.kimi.com/code/docs/en/kimi-code-cli/customization/plugins.html#kimi-datasource Not sure about the feature you mentioned but one can see in their app that they use IMF, World Bank, SEC EDGAR, and Yahoo Finance.", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Work"}, {"id": 783747969, "item_id": 48984248, "url": "https://news.ycombinator.com/item?id=48984248", "by": "KronisLV", "date": "2026-07-20", "stance": "warn", "quote": "really slows down with long conversations to the point where keyboard input lags by seconds", "excerpt": "I wish they'd embed the Code UI as a tab, similar to Claude Code Desktop. There's really no real reason for those tools to be separate and for them not to give me something a bit nicer than just a TUI in the terminal. They already have a locally runnable web UI when you have Kimi (the CLI) installed: https://www.kimi.com/help/kimi-code/cli-getting-started kimi server run --foreground Though it's ever so slightly brok", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Work"}, {"id": 783386577, "item_id": 48961661, "url": "https://news.ycombinator.com/item?id=48961661", "by": "esafak", "date": "2026-07-18", "stance": "compare", "quote": "", "excerpt": "OpenAI measures token efficiency. Look at the API cost charts in their announcement: https://openai.com/index/gpt-5-6/", "context": "", "use_case": "", "switched_from": "", "story": "The Kimi K3 Moment"}, {"id": 783005856, "item_id": 48937866, "url": "https://news.ycombinator.com/item?id=48937866", "by": "igravious", "date": "2026-07-16", "stance": "recommend", "quote": "Kimi has Kimi Code :)", "excerpt": "Kimi has Kimi Code :) kimi-code https://www.kimi.com/code/en", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 773152993, "item_id": 48322062, "url": "https://news.ycombinator.com/item?id=48322062", "by": "mariopt", "date": "2026-05-29", "stance": "recommend", "quote": "Kimi performs better with kimi-cli and also save a bit of quota", "excerpt": "I use opencode with all of them except Kimi, I noticed Kimi performs better with kimi-cli and also save a bit of quota. Z.ai does recommend to use claude cli as a harness for GLM5.1, I still get good results with opencode.", "context": "", "use_case": "harness for Kimi models", "switched_from": "", "story": "Claude Opus 4.8"}, {"id": 767896017, "item_id": 47993501, "url": "https://news.ycombinator.com/item?id=47993501", "by": "zorked", "date": "2026-05-02", "stance": "neutral", "quote": "I use Kimi via a kimi.com subscription and Kimi CLI", "excerpt": "I use Kimi via a kimi.com subscription and Kimi CLI (sometimes running inside Zed, sometimes not). My favorite model by far. And it's just $20.", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge"}, {"id": 765772832, "item_id": 47860802, "url": "https://news.ycombinator.com/item?id=47860802", "by": "dv_dt", "date": "2026-04-22", "stance": "neutral", "quote": "I know of kimi code https://www.kimi.com/code", "excerpt": "Some do, I know of kimi code https://www.kimi.com/code", "context": "", "use_case": "", "switched_from": "", "story": "Claude Code removed from Anthropic's Pro plan"}, {"id": 765765489, "item_id": 47860343, "url": "https://news.ycombinator.com/item?id=47860343", "by": "nekitamo", "date": "2026-04-22", "stance": "neutral", "quote": "Kimi K2.5 used through KimiCode was comparable to Sonnet in my tests", "excerpt": "That's interesting, Kimi K2.5 used through KimiCode was comparable to Sonnet in my tests, and is an excellent alternative to Anthropic models That being said, I noticed that Kimi being served through Openrouter providers was trash. Whatever they do on the backend to optimize for throughput really compromised the intelligence of the model. You have to work with Kimi directly if you want the best results, and that's al", "context": "", "use_case": "", "switched_from": "", "story": "SpaceX and Cursor partnership. Right to acquire Cursor later this year"}, {"id": 756608401, "item_id": 47288025, "url": "https://news.ycombinator.com/item?id=47288025", "by": "igravious", "date": "2026-03-07", "stance": "recommend", "quote": "I use Claude Code and Kimi CLI", "excerpt": "two AIs -- I use Claude Code and Kimi CLI -- I got them to build an agent relay so they can communicate with each other (one plans, the other reviews the plan; one builds, the other reviews the build) -- while one is working on one thing, I'll be chatting and exploring with the other one \u2026 they can build anything in any language so if you are a skilled and experienced code you should be able to guide a pair of coding", "context": "", "use_case": "", "switched_from": "", "story": "I'm 60 years old. Claude Code has ignited a passion again"}, {"id": 753014865, "item_id": 47063429, "url": "https://news.ycombinator.com/item?id=47063429", "by": "crystal_revenge", "date": "2026-02-18", "stance": "recommend", "quote": "it\u2019s been pretty much flawless", "excerpt": "I\u2019ve been running K2.5 (through the API) as my daily driver for coding through Kimi Code CLI and it\u2019s been pretty much flawless. It\u2019s also notably cheaper and I like the option that if my vibe coded side projects became more than side projects I could run everything in house. I\u2019ve been pretty active in the open model space and 2 years ago you would have had to pay 20k to run models that were nowhere near as powerful.", "context": "", "use_case": "Coding agent CLI", "switched_from": "", "story": "Why AI Velocity Is Becoming a Debt Accelerator"}, {"id": 749302705, "item_id": 46831419, "url": "https://news.ycombinator.com/item?id=46831419", "by": "Imanari", "date": "2026-01-30", "stance": "recommend", "quote": "A true competitor to Claude Code with Opus.", "excerpt": "I have been very impressed with this model and also with the Kimi CLI. I have been using it with the 'Moderato' plan (7 days free, then 19$). A true competitor to Claude Code with Opus.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Kimi K2.5 Technical Report [pdf]"}, {"id": 749276512, "item_id": 46829782, "url": "https://news.ycombinator.com/item?id=46829782", "by": "esafak", "date": "2026-01-30", "stance": "neutral", "quote": "starts at $19/month, which is same as the big boys.", "excerpt": "Where? https://www.kimi.com/code starts at $19/month, which is same as the big boys.", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K2.5 Technical Report [pdf]"}, {"id": 749269345, "item_id": 46829334, "url": "https://news.ycombinator.com/item?id=46829334", "by": "Imustaskforhelp", "date": "2026-01-30", "stance": "recommend", "quote": "So I personally like/stick with the kimi cli for kimi coding.", "excerpt": "I tried to use opencode for kimi k2.5 too but recently they changed their pricing from 200 tool requests/5 hour to token based pricing. I can only speak from the tool request based but for some reason anecdotally opencode took like 10 requests in like 3-4 minutes where Kimi cli took 2-3 So I personally like/stick with the kimi cli for kimi coding. I haven't tested it out again with OpenAI with teh new token based pri", "context": "", "use_case": "kimi coding", "switched_from": "", "story": "Kimi K2.5 Technical Report [pdf]"}, {"id": 748817616, "item_id": 46801101, "url": "https://news.ycombinator.com/item?id=46801101", "by": "Imustaskforhelp", "date": "2026-01-28", "stance": "neutral", "quote": "which I am thinking of downloading & working with kimi-cli", "excerpt": "Indian high school senior here about to start CS in college here. Your project feels phenomenal. Definitely starred. I was actually trying to create a browser (in golang) myself as well (using LLM assistance) & I really couldn't do it after countless efforts. https://github.com/SerJaimeLannister/golang-browser Much of it was just curiosity towards if LLM's could port the rust project by emsh https://emsh.cat/one-huma", "context": "", "use_case": "Agent CLI", "switched_from": "", "story": "Show HN: I built a small browser engine from scratch in C++"}, {"id": 748600961, "item_id": 46787560, "url": "https://news.ycombinator.com/item?id=46787560", "by": "Imustaskforhelp", "date": "2026-01-27", "stance": "neutral", "quote": "I ate through all of my 200 queries in kimi code", "excerpt": "Haha yea, Me and emsh were actually talking about it on bluesky (which I saw after seeing your bluesky, I didn't know both you and emsh were on bsky haha) https://bsky.app/profile/emsh.cat/post/3mdgobfq4as2p But basically I got curious and you can see from my other comments on you how much I love golang so decided to port the project from rust to golang and emsh predicts that the project's codebase can even shrink to", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: One Human + One Agent = One Browser From Scratch in 20K LOC"}, {"id": 748479216, "item_id": 46779951, "url": "https://news.ycombinator.com/item?id=46779951", "by": "vinhnx", "date": "2026-01-27", "stance": "recommend", "quote": "I really like their CLI.", "excerpt": "It is, Kimi Code CLI supports Zed' Agent Client Protocol (http://agentclientprotocol.com/), so it can acts as an external agent that could run in any ACP-compatible client, eg: Zed, Jetbrain, Toad CLI, Minano Notebook. Also, it supports Agent Skills. Moonshot AI developers are actively update the agent and every active. I really like their CLI.", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model"}, {"id": 748460128, "item_id": 46778758, "url": "https://news.ycombinator.com/item?id=46778758", "by": "mynti", "date": "2026-01-27", "stance": "neutral", "quote": "They gave it a soul: https://github.com/MoonshotAI/kimi-cli/blob/main/src/kimi_cli/soul/kimisoul.py", "excerpt": "They gave it a soul: https://github.com/MoonshotAI/kimi-cli/blob/main/src/kimi_cli/soul/kimisoul.py", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Code CLI"}, {"id": 748455921, "item_id": 46778495, "url": "https://news.ycombinator.com/item?id=46778495", "by": "JustinXie", "date": "2026-01-27", "stance": "neutral", "quote": "plus a CLI tool (Kimi Code) for VSCode/Cursor/Zed", "excerpt": "Key highlights from the blog post (https://www.kimi.com/blog/kimi-k2-5.html): - Agent Swarm: K2.5 can spawn up to 100 sub-agents autonomously, executing 1,500+ parallel tool calls with 4.5x speedup over single-agent. - Video-to-code: Generate frontend code directly from a screen recording, with autonomous visual debugging (it \"looks\" at its own output and iterates). - Open-source model weights on HuggingFace, plus a ", "context": "", "use_case": "", "switched_from": "", "story": "Kimi K2.5"}, {"id": 748442368, "item_id": 46777648, "url": "https://news.ycombinator.com/item?id=46777648", "by": "vinhnx", "date": "2026-01-27", "stance": "recommend", "quote": "it is capable agent with stable harness", "excerpt": "One thing caught my eyes is that besides K2.5 model, Moonshot AI also launched Kimi Code (https://www.kimi.com/code), evolved from Kimi CLI. It is a terminal coding agent, I've been used it last month with Kimi subscription, it is capable agent with stable harness. GitHub: https://github.com/MoonshotAI/kimi-cli", "context": "", "use_case": "Terminal coding agent", "switched_from": "", "story": "Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model"}]}