{"slug": "little-coder", "name": "little-coder", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 5, "warners": 0, "score": 2.53, "rising": -0.98, "first": "2026-04-22", "latest": "2026-07-04", "why": "I use little-coder (built on pi) and have good results for small Python and TypeScript applications.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 2, "neutral": 2, "compare": 1, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I use little-coder (built on pi) and have good results for small Python and TypeScript applications.", "kind": "", "icon": false, "domain": null, "github_repo": "github.com/itayinbarr/little-coder", "official_url": "https://github.com/itayinbarr/little-coder", "pricing": "", "aliases": ["little-coder"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 776733778, "item_id": 48545861, "url": "https://news.ycombinator.com/item?id=48545861", "by": "mark_l_watson", "date": "2026-06-15", "version": null, "stance": "recommend", "quote": "I use little-coder (built on pi) and have good results for small Python and TypeScript applications.", "excerpt": "I would like to say I run 100% local, but I use Opus + Gemini Pro cumulatively for 3 or 4 hours a week. I also like to use DeepSeek v4 flash with OpenCode for small quick tasks. I did just publish a free to read online book \"The Rise of Local Coding Agents\" [1] where I document my setup that I enjoy using. I use little-coder (built on pi) and have good results for small Python and TypeScript applications. I struggle ", "context": "", "use_case": "local coding agent", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 776154497, "item_id": 48509656, "url": "https://news.ycombinator.com/item?id=48509656", "by": "mark_l_watson", "date": "2026-06-12", "version": null, "stance": "recommend", "quote": "I use little-coder that wraps pi with reasonable defaults for running local models", "excerpt": "Nice writeup, thanks. I run something very similar except for directly using pi as the agentic harness I use little-coder that wraps pi with reasonable defaults for running local models. Even though my local setup is a bit slow, it is a thrill to do real work completely locally.", "context": "", "use_case": "local coding agent", "switched_from": "", "story": "How to Setup a Local Coding Agent on macOS"}, {"id": 771216178, "item_id": 48201011, "url": "https://news.ycombinator.com/item?id=48201011", "by": "zambelli", "date": "2026-05-19", "version": null, "stance": "recommend", "quote": "As for little coder, I love it!", "excerpt": "Mainly because I have plenty of use cases and not all of them need or want pi. Forge isn't an orchestration framework and is not coding specific, it lives one level lower - if I understand pi correctly. The proxy mode should integrate seamlessly, and the middleware guardrail mode could be lifted into pi. As for little coder, I love it! I wanted forge to be more generic than just agentic coding as there's many more ag", "context": "", "use_case": "", "switched_from": "", "story": null}, {"id": 771213312, "item_id": 48200832, "url": "https://news.ycombinator.com/item?id=48200832", "by": "tempoponet", "date": "2026-05-19", "version": null, "stance": "recommend", "quote": "lets me mix and match with my current setup or any plugins built for pi", "excerpt": "Why this entire tool chain instead of building within something like pi code? I've been exploring this area and a project like https://github.com/itayinbarr/little-coder (not my work) lets me mix and match with my current setup or any plugins built for pi.", "context": "", "use_case": "", "switched_from": "", "story": null}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["local coding agent", "local coding agent on 16g macbook air", "local model coding harness", "local agentic coding", "coding agent for small llms"], "compared": [{"slug": "pi", "name": "Pi", "co": 6, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48192383", "title": "item 48192383", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48722052", "title": "Ornith-1.0: self-improving open-source models for agentic coding", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48721903", "title": "Qwen 3.6 27B is the sweet spot for local development", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48707103", "title": "Google limits Meta's use of its Gemini AI models", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48542100", "title": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48507020", "title": "How to Setup a Local Coding Agent on macOS", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 2}, "2026-06": {"neutral": 1}, "2026-07": {"compare": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 780655952, "item_id": 48790997, "url": "https://news.ycombinator.com/item?id=48790997", "by": "lhl", "date": "2026-07-04", "version": null, "stance": "compare", "quote": "", "excerpt": "You got me curious, so I made a little harness comparison to my model test suite: Model Adapter Suite Score Passed Tasks --------------------------------- ------------ -------------- ------ ------ ----- local/ornith-1.0-35b little_coder aider_polyglot 36.0% 81/225 225 local/ornith-1.0-35b pi_devstack aider_polyglot 39.6% 89/225 225 local/ornith-1.0-35b pi_vanilla aider_polyglot 32.0% 72/225 225 Little Code does a lit", "context": "", "use_case": "", "switched_from": "", "story": "Ornith-1.0: self-improving open-source models for agentic coding"}, {"id": 779605876, "item_id": 48725367, "url": "https://news.ycombinator.com/item?id=48725367", "by": "mark_l_watson", "date": "2026-06-29", "version": null, "stance": "neutral", "quote": "gemma4:12b-it-qat-16k (\"-16k\" is my resizing context size) and little-coder", "excerpt": "I can come close to agreeing because queen-3.6-27b is my second favorite for local coding. I am using gemma4:26b-a4b-it-qat-48k (the \"-48k\" is from my modifying a model run with Ollama to always use a 48K context size). On a 32G Mac I use gemma4:26b-a4b-it-qat-48k and OpenCode and on my 16G MacBook Air I use gemma4:12b-it-qat-16k (\"-16k\" is my resizing context size) and little-coder. I break up projects into small li", "context": "", "use_case": "local coding agent on 16G MacBook Air", "switched_from": "", "story": "Qwen 3.6 27B is the sweet spot for local development"}, {"id": 779323989, "item_id": 48707749, "url": "https://news.ycombinator.com/item?id=48707749", "by": "mark_l_watson", "date": "2026-06-28", "version": null, "stance": "neutral", "quote": "when I am not using local models with little-coder/pi", "excerpt": "Misleading title on HN but an interesting article, a reminder of why the hyper scalers are investing heavily in infrastructure. That said, I expect much of the AI bubble to pop. Google Gemini with Antigravity is a good product, as is a Claude Code subscription but I have switched to using DeepSeek v4 Pro with the Claude Code harness and DeepSeek v4 Flash with the OpenCode harness (when I am not using local models wit", "context": "", "use_case": "local model coding harness", "switched_from": "", "story": "Google limits Meta's use of its Gemini AI models"}, {"id": 776733778, "item_id": 48545861, "url": "https://news.ycombinator.com/item?id=48545861", "by": "mark_l_watson", "date": "2026-06-15", "version": null, "stance": "recommend", "quote": "I use little-coder (built on pi) and have good results for small Python and TypeScript applications.", "excerpt": "I would like to say I run 100% local, but I use Opus + Gemini Pro cumulatively for 3 or 4 hours a week. I also like to use DeepSeek v4 flash with OpenCode for small quick tasks. I did just publish a free to read online book \"The Rise of Local Coding Agents\" [1] where I document my setup that I enjoy using. I use little-coder (built on pi) and have good results for small Python and TypeScript applications. I struggle ", "context": "", "use_case": "local coding agent", "switched_from": "", "story": "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"}, {"id": 776154497, "item_id": 48509656, "url": "https://news.ycombinator.com/item?id=48509656", "by": "mark_l_watson", "date": "2026-06-12", "version": null, "stance": "recommend", "quote": "I use little-coder that wraps pi with reasonable defaults for running local models", "excerpt": "Nice writeup, thanks. I run something very similar except for directly using pi as the agentic harness I use little-coder that wraps pi with reasonable defaults for running local models. Even though my local setup is a bit slow, it is a thrill to do real work completely locally.", "context": "", "use_case": "local coding agent", "switched_from": "", "story": "How to Setup a Local Coding Agent on macOS"}, {"id": 775372912, "item_id": 48460807, "url": "https://news.ycombinator.com/item?id=48460807", "by": "mark_l_watson", "date": "2026-06-09", "version": null, "stance": "neutral", "quote": "starting with 'little-coder --model ollama/gemma4:12b-it-qat'", "excerpt": "Thanks apfel looks useful! I have been experimenting with Apple's foundation models for almost a year and they are useful for embedded applications. I have been taking a deeper dive into local agentic coding tools (starting with 'little-coder --model ollama/gemma4:12b-it-qat') and I put together a tiny free book with some setup advice that might save people a few minutes of setup time: https://leanpub.com/read/local-", "context": "", "use_case": "Local agentic coding", "switched_from": "", "story": "Apple Core AI Framework"}, {"id": 771216178, "item_id": 48201011, "url": "https://news.ycombinator.com/item?id=48201011", "by": "zambelli", "date": "2026-05-19", "version": null, "stance": "recommend", "quote": "As for little coder, I love it!", "excerpt": "Mainly because I have plenty of use cases and not all of them need or want pi. Forge isn't an orchestration framework and is not coding specific, it lives one level lower - if I understand pi correctly. The proxy mode should integrate seamlessly, and the middleware guardrail mode could be lifted into pi. As for little coder, I love it! I wanted forge to be more generic than just agentic coding as there's many more ag", "context": "", "use_case": "", "switched_from": "", "story": null}, {"id": 771213312, "item_id": 48200832, "url": "https://news.ycombinator.com/item?id=48200832", "by": "tempoponet", "date": "2026-05-19", "version": null, "stance": "recommend", "quote": "lets me mix and match with my current setup or any plugins built for pi", "excerpt": "Why this entire tool chain instead of building within something like pi code? I've been exploring this area and a project like https://github.com/itayinbarr/little-coder (not my work) lets me mix and match with my current setup or any plugins built for pi.", "context": "", "use_case": "", "switched_from": "", "story": null}, {"id": 765866480, "item_id": 47866655, "url": "https://news.ycombinator.com/item?id=47866655", "by": "homarp", "date": "2026-04-22", "version": null, "stance": "neutral", "quote": "a coding agent optimized to smaller LLMs", "excerpt": "Coding Agent Adaptation Lets a 9B LLM Outperform 10x Larger Models on Aider Polyglot Benchmark and as an output, a coding agent optimized to smaller LLMs: https://github.com/itayinbarr/little-coder", "context": "", "use_case": "coding agent for small LLMs", "switched_from": "", "story": "Honey, I Shrunk the Coding Agent"}]}