{"slug": "git-ai", "name": "Git AI", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 5, "warners": 0, "score": 2.482, "rising": -0.98, "first": "2026-02-10", "latest": "2026-08-25", "why": "I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 3, "compare": 1, "warn": 0}, "spark": [0, 0, 0, 0, 2, 0, 2, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.", "kind": "", "icon": true, "domain": "usegitai.com", "github_repo": null, "official_url": "https://usegitai.com/", "pricing": "", "aliases": ["Git AI", "git-ai", "GitAI"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 782754176, "item_id": 48922136, "url": "https://news.ycombinator.com/item?id=48922136", "by": "esafak", "date": "2026-07-15", "stance": "recommend", "quote": "I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.", "excerpt": "I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.", "context": "", "use_case": "preserving and searching AI transcripts", "switched_from": "", "story": "Show HN: Grepathy \u2013 Claude made a decision nobody approved"}, {"id": 768086544, "item_id": 48005409, "url": "https://news.ycombinator.com/item?id=48005409", "by": "nextaccountic", "date": "2026-05-03", "stance": "recommend", "quote": "There are tools like git-ai [0] that capture LLM sessions and associate each file edit to a specific agent action", "excerpt": "> even if they often forget > But I can at least ask the agent a question and it will be able to answer it A problem here is that, in some sense, the agent that wrote the code is not the same agent that is answering questions about it. if the original agent didn't leave their reasoning, you are probably out of luck. There are tools like git-ai [0] that capture LLM sessions and associate each file edit to a specific a", "context": "", "use_case": "capture LLM session history per edit", "switched_from": "", "story": "Agentic Coding Is a Trap"}, {"id": 767670384, "item_id": 47979399, "url": "https://news.ycombinator.com/item?id=47979399", "by": "esafak", "date": "2026-05-01", "stance": "recommend", "quote": "you can commit your chat sessions in git notes", "excerpt": "Besides documentation, you can commit your chat sessions in git notes e.g. with https://usegitai.com/", "context": "", "use_case": "Committing chat sessions to git notes", "switched_from": "", "story": "The end of \"Just ask Sarah\""}, {"id": 761238496, "item_id": 47577406, "url": "https://news.ycombinator.com/item?id=47577406", "by": "esafak", "date": "2026-03-30", "stance": "recommend", "quote": "If you want more metadata going forward", "excerpt": "If you want more metadata going forward: https://usegitai.com/", "context": "", "use_case": "recording AI metadata in git", "switched_from": "", "story": "\"Over 1.5M GitHub PRs have had ads injected into them by Copilot\""}, {"id": 755475104, "item_id": 47217194, "url": "https://news.ycombinator.com/item?id=47217194", "by": "addcn", "date": "2026-03-02", "stance": "recommend", "quote": "I think that model will win out", "excerpt": "This reduces down to the problem of summarization - a quite difficult one. At commit time it\u2019s difficult to know what questions readers will have. You can get close but never all the way there. Pre AI when engineers couldn\u2019t find the answer in commit messages or documentation they would ask the author \u201cwhy\u201d and that human would \u201ccompute\u201d the summary on demand. I think that\u2019s what I expect to do with these agent sessi", "context": "", "use_case": "", "switched_from": "", "story": "If AI writes code, should the session be part of the commit?"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["sharing ai agent sessions", "preserving and searching ai transcripts", "code tracking", "capture llm session history per edit", "committing chat sessions to git notes", "recording ai metadata in git"], "compared": [{"slug": "ctx", "name": "ctx", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49428395", "title": "Capture why AI wrote each commit, stored in Git-notes", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49378768", "title": "Show HN: Huzzah \u2013 a novel approach to coding with AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48920537", "title": "Show HN: Grepathy \u2013 Claude made a decision nobody approved", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48878682", "title": "Show HN: Mindwalk \u2013 Replay coding-agent sessions on a 3D map of your codebase", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48057104", "title": "Show HN: Selvedge \u2013 an MCP server that captures why AI agents change code", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48002442", "title": "Agentic Coding Is a Trap", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"neutral": 1}, "2026-03": {"recommend": 2}, "2026-04": {}, "2026-05": {"recommend": 2}, "2026-06": {}, "2026-07": {"neutral": 1}, "2026-08": {"neutral": 1, "compare": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 790862912, "item_id": 49428932, "url": "https://news.ycombinator.com/item?id=49428932", "by": "tamrix", "date": "2026-08-25", "stance": "compare", "quote": "Similar to https://usegitai.com/?", "excerpt": "Similar to https://usegitai.com/?", "context": "", "use_case": "", "switched_from": "", "story": "Capture why AI wrote each commit, stored in Git-notes"}, {"id": 790069281, "item_id": 49379330, "url": "https://news.ycombinator.com/item?id=49379330", "by": "esafak", "date": "2026-08-20", "stance": "neutral", "quote": "See https://entire.io/ or https://usegitai.com/", "excerpt": "Sharing sessions means providing full visibility into what you did with the agent to the team. See https://entire.io/ or https://usegitai.com/ You can already retrieve the session associated with a given line of code.", "context": "", "use_case": "Sharing AI agent sessions", "switched_from": "", "story": "Show HN: Huzzah \u2013 a novel approach to coding with AI"}, {"id": 782754176, "item_id": 48922136, "url": "https://news.ycombinator.com/item?id=48922136", "by": "esafak", "date": "2026-07-15", "stance": "recommend", "quote": "I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.", "excerpt": "I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.", "context": "", "use_case": "preserving and searching AI transcripts", "switched_from": "", "story": "Show HN: Grepathy \u2013 Claude made a decision nobody approved"}, {"id": 782105121, "item_id": 48881570, "url": "https://news.ycombinator.com/item?id=48881570", "by": "esafak", "date": "2026-07-12", "stance": "neutral", "quote": "for which I'm testing https://usegitai.com/", "excerpt": "I think the chord diagram in the video is not informative. Generally speaking I suggest starting with the problem you are trying to shed light on, and device the visualization accordingly. For example, if you are shipping a mobile app and want to keep your package small, the treemap in the video would help you understand how the space is allocated. * https://en.wikipedia.org/wiki/Chord_diagram_(information_visualizat", "context": "", "use_case": "code tracking", "switched_from": "", "story": "Show HN: Mindwalk \u2013 Replay coding-agent sessions on a 3D map of your codebase"}, {"id": 768914032, "item_id": 48057127, "url": "https://news.ycombinator.com/item?id=48057127", "by": "esafak", "date": "2026-05-07", "stance": "compare", "quote": "GitAI does this without an MCP using git notes, which means it gets checked in: https://usegitai.com/", "excerpt": "GitAI does this without an MCP using git notes, which means it gets checked in: https://usegitai.com/", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Selvedge \u2013 an MCP server that captures why AI agents change code"}, {"id": 768086544, "item_id": 48005409, "url": "https://news.ycombinator.com/item?id=48005409", "by": "nextaccountic", "date": "2026-05-03", "stance": "recommend", "quote": "There are tools like git-ai [0] that capture LLM sessions and associate each file edit to a specific agent action", "excerpt": "> even if they often forget > But I can at least ask the agent a question and it will be able to answer it A problem here is that, in some sense, the agent that wrote the code is not the same agent that is answering questions about it. if the original agent didn't leave their reasoning, you are probably out of luck. There are tools like git-ai [0] that capture LLM sessions and associate each file edit to a specific a", "context": "", "use_case": "capture LLM session history per edit", "switched_from": "", "story": "Agentic Coding Is a Trap"}, {"id": 767670384, "item_id": 47979399, "url": "https://news.ycombinator.com/item?id=47979399", "by": "esafak", "date": "2026-05-01", "stance": "recommend", "quote": "you can commit your chat sessions in git notes", "excerpt": "Besides documentation, you can commit your chat sessions in git notes e.g. with https://usegitai.com/", "context": "", "use_case": "Committing chat sessions to git notes", "switched_from": "", "story": "The end of \"Just ask Sarah\""}, {"id": 761238496, "item_id": 47577406, "url": "https://news.ycombinator.com/item?id=47577406", "by": "esafak", "date": "2026-03-30", "stance": "recommend", "quote": "If you want more metadata going forward", "excerpt": "If you want more metadata going forward: https://usegitai.com/", "context": "", "use_case": "recording AI metadata in git", "switched_from": "", "story": "\"Over 1.5M GitHub PRs have had ads injected into them by Copilot\""}, {"id": 755475104, "item_id": 47217194, "url": "https://news.ycombinator.com/item?id=47217194", "by": "addcn", "date": "2026-03-02", "stance": "recommend", "quote": "I think that model will win out", "excerpt": "This reduces down to the problem of summarization - a quite difficult one. At commit time it\u2019s difficult to know what questions readers will have. You can get close but never all the way there. Pre AI when engineers couldn\u2019t find the answer in commit messages or documentation they would ask the author \u201cwhy\u201d and that human would \u201ccompute\u201d the summary on demand. I think that\u2019s what I expect to do with these agent sessi", "context": "", "use_case": "", "switched_from": "", "story": "If AI writes code, should the session be part of the commit?"}, {"id": 751403488, "item_id": 46962718, "url": "https://news.ycombinator.com/item?id=46962718", "by": "krashidov", "date": "2026-02-10", "stance": "neutral", "quote": "There is also Git AI:", "excerpt": "There is also Git AI: https://github.com/git-ai-project/git-ai https://usegitai.com/", "context": "", "use_case": "", "switched_from": "", "story": "Ex-GitHub CEO Launches a New Developer Platform for AI Agents"}]}