{"slug": "autolith", "name": "Autolith", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 3, "warners": 0, "score": 2.227, "rising": 3.0, "first": "2026-08-12", "latest": "2026-10-02", "why": "", "why_is_quote": false, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2], "listed": true, "loved": [], "caveat": "", "short_quote": "", "icon": true, "domain": null, "github_repo": "github.com/lambda-symbolics/autolith", "official_url": "https://github.com/lambda-symbolics/autolith", "pricing": "", "aliases": ["Autolith"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 798953168, "item_id": 49934573, "url": "https://news.ycombinator.com/item?id=49934573", "by": "evanjrowley", "date": "2026-10-02", "stance": "recommend", "quote": "Very powerful stuff.", "excerpt": ">emacs of harnesses! Would you be interested in a self-modifying harness written in Common Lisp? If so, then please check out Autolith: https://github.com/lambda-symbolics/autolith/ In my time using it with GLM 5.2, I've observed it modify itself to disassemble binaries in search of answers - without me needing to ask it to do so. Very powerful stuff. Here's what it looked like: \u25c7 reasoning summary \u2502 The 200MB binary", "context": "", "use_case": "self-modifying agent harness", "switched_from": "", "story": "DeepSeek Harness Desktop for macOS and Windows"}, {"id": 798822353, "item_id": 49926397, "url": "https://news.ycombinator.com/item?id=49926397", "by": "sroerick", "date": "2026-10-01", "stance": "recommend", "quote": "I also like Autolith.", "excerpt": "Pi is really good. I use it for a majority of my work. I also like Autolith. The freedom of having a lisp machine is, to me, much more enjoyable than trying to maintain Typescript. But I'm not a typescript guy. I do largely stick with Pi because it's very bulletproofed", "context": "", "use_case": "", "switched_from": "", "story": "Pi 1.0"}, {"id": 788488241, "item_id": 49280515, "url": "https://news.ycombinator.com/item?id=49280515", "by": "dismalaf", "date": "2026-08-12", "stance": "recommend", "quote": "here's an interesting tool to use CL with LLMs", "excerpt": "Was going to write something about the article but then poked around the blog and it led to Github including this gem: https://github.com/jrm-code-project/llambda which is much more interesting. I do agree with a lot of the article though, Lisp plays nicely with LLMs. Definitely had better luck with Lisp and LLMs than C++ or Rust. Also, kind of random, but here's an interesting tool to use CL with LLMs: https://www.l", "context": "", "use_case": "Common Lisp with LLMs", "switched_from": "", "story": "Why vibe code in Common Lisp?"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["self-modifying agent harness", "lisp-based agent environment", "common lisp with llms"], "compared": [], "makers": [{"id": 790395168, "item_id": 49399698, "url": "https://news.ycombinator.com/item?id=49399698", "by": "magnusi", "date": "2026-08-22", "stance": "neutral", "quote": "Hi, I'm the author of Autolith!", "excerpt": "Hi, I'm the author of Autolith! Never heard about Jolt, and I love Chez Scheme, it was my first Lisp! Would you like to come to our Zulip at https://zulip.lambda-symbolics.com? We can exchange ideas for our harnesses", "context": "author of Autolith", "use_case": "programming agent", "switched_from": "", "story": "Autolith: A programming agent with a live runtime"}, {"id": 790365120, "item_id": 49397820, "url": "https://news.ycombinator.com/item?id=49397820", "by": "magnusi", "date": "2026-08-22", "stance": "recommend", "quote": "if you'd like to try Autolith, I am happy to help with issues/questions", "excerpt": "Hi! I was thinking about Smalltalk as well before I made Autolith. I ended up going with Common Lisp because I know Lisp much better (last time I used smalltalk was like, whew, 2014 or so) and because it has better platform support and ecosystem (at least in my experience). I think Elixir could be great, I knew a guy who was trying to do an agent in Elixir, but sadly didn't get far. Keep me posted if you get anywhere", "context": "", "use_case": "programming agent with live runtime", "switched_from": "", "story": "Autolith: A programming agent with a live runtime"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49926069", "title": "Pi 1.0", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49376197", "title": "Autolith: A programming agent with a live runtime", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49929489", "title": "DeepSeek Harness Desktop for macOS and Windows", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49269429", "title": "Why vibe code in Common Lisp?", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"recommend": 2}}, "quotes": [{"id": 798953168, "item_id": 49934573, "url": "https://news.ycombinator.com/item?id=49934573", "by": "evanjrowley", "date": "2026-10-02", "stance": "recommend", "quote": "Very powerful stuff.", "excerpt": ">emacs of harnesses! Would you be interested in a self-modifying harness written in Common Lisp? If so, then please check out Autolith: https://github.com/lambda-symbolics/autolith/ In my time using it with GLM 5.2, I've observed it modify itself to disassemble binaries in search of answers - without me needing to ask it to do so. Very powerful stuff. Here's what it looked like: \u25c7 reasoning summary \u2502 The 200MB binary", "context": "", "use_case": "self-modifying agent harness", "switched_from": "", "story": "DeepSeek Harness Desktop for macOS and Windows"}, {"id": 798884928, "item_id": 49930308, "url": "https://news.ycombinator.com/item?id=49930308", "by": "sroerick", "date": "2026-10-02", "stance": "neutral", "quote": "I think Autolith ships with one also.", "excerpt": "I use the open weight models and they kind of suck lol. I have a lot of paren helpers. I think Autolith ships with one also. The boys in the Autolith zulip say that Openai and Anthropic models are all totally fine with parens. Come say hi in the chat", "context": "", "use_case": "Lisp-based agent environment", "switched_from": "", "story": "Pi 1.0"}, {"id": 798822353, "item_id": 49926397, "url": "https://news.ycombinator.com/item?id=49926397", "by": "sroerick", "date": "2026-10-01", "stance": "recommend", "quote": "I also like Autolith.", "excerpt": "Pi is really good. I use it for a majority of my work. I also like Autolith. The freedom of having a lisp machine is, to me, much more enjoyable than trying to maintain Typescript. But I'm not a typescript guy. I do largely stick with Pi because it's very bulletproofed", "context": "", "use_case": "", "switched_from": "", "story": "Pi 1.0"}, {"id": 788488241, "item_id": 49280515, "url": "https://news.ycombinator.com/item?id=49280515", "by": "dismalaf", "date": "2026-08-12", "stance": "recommend", "quote": "here's an interesting tool to use CL with LLMs", "excerpt": "Was going to write something about the article but then poked around the blog and it led to Github including this gem: https://github.com/jrm-code-project/llambda which is much more interesting. I do agree with a lot of the article though, Lisp plays nicely with LLMs. Definitely had better luck with Lisp and LLMs than C++ or Rust. Also, kind of random, but here's an interesting tool to use CL with LLMs: https://www.l", "context": "", "use_case": "Common Lisp with LLMs", "switched_from": "", "story": "Why vibe code in Common Lisp?"}]}