Grepathy – Claude made a decision nobody approved
hey HN - Claude pre-created users in Clerk with null emails/names as "guest users" on a contract job. Wasn't in any plan. The CTO asked why, and I didn't know! I didn't make that decision! The reasoning was in a transcript on my laptop. Claude Code deletes those after 30 days by default. Two of my projects lost their whole history that way. Grepathy distills transcripts locally into markdown committed with the code. Decisions only, never your messages, no server. List every decision nobody approved: grep -rn "agent-initiated" .ai/why/ Ran a blind eval before shipping,…
In plain words
Grepathy is a tool that captures AI agent decision-making by storing transcripts locally as markdown files committed alongside code. It records only decisions and reasoning, never user messages, and stores everything locally without server involvement. Designed for developers using AI agents in their workflows, it helps track why agents made changes to code, preventing lost context when transcript histories are deleted. Users can search for agent-initiated decisions across their codebase using grep commands.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
hey HN - Claude pre-created users in Clerk with null emails/names as "guest users" on a contract job. Wasn't in any plan. The CTO asked why, and I didn't know! I didn't make that decision! The reasoning was in a transcript on my laptop. Claude Code deletes those after 30 days by default. Two of my projects lost their whole history that way. Grepathy distills transcripts locally into markdown committed with the code. Decisions only, never your messages, no server. List every decision nobody approved: grep -rn "agent-initiated" .ai/why/ Ran a blind eval before shipping, published it including the misses (REPORT.md). Agents with Grepathy answered the "why" questions right. Baseline agents made up confident wrong answers.
Does the same job
all alternatives →
- GFGit for AI AgentsMay 2026 · github.com · ▲129
hi guys. been working on something i think is fundamentally missing in today's workflow with ai agents. vcs. i find myself struggling with questions that agents can't answer like "why did you do it?", "when did u delete this folder? why?", etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session. just like git did for code, i think we are the same core capabilities with ai agents so... i developed an open source solution for that (currently supporting claude code) would love to…
- AFAbralo – Free, easy way to run several Claude Code agents in one windowJul 2026 · abralo.com · ▲37
Hi guys, I've been using Claude Code for almost everything lately. Have given one an email account so it can research business leads, draft emails, fact-check them and clear them with me before sending (works really well by the way). I also tend to have a few Claude Code agents running at any one time for coding. I used to create a split terminal to manage them from there, but found working in the terminal all day pretty depressing and, more importantly, found it hard to follow Claude Code's process and see which agents needed my immediate attention. I tried Anthropic's VS Code Claude Code…
- ICI cut my Claude API bill by 66% with Git-based context2025 · shadowgit.com · ▲5
Hey HN, I built ShadowGit a while back to automatically commit code every minute to a hidden git repo (.shadowgit.git). Original goal was to easily rollback when AI tools break things. But I discovered something interesting: this minute-by-minute history is perfect context for AI assistants. So I built an MCP server that lets Claude/Cursor query this history using native git commands. The results surprised me: Before: Claude would read my entire codebase repeatedly, burning 15,000+ tokens to debug issues. After: Claude runs `git log --grep="drag"` finds when drag-and-drop worked,…
- IAI am running 3 coding agents non-stop over the last 3 days. Here is howJun 2026 · ▲10
1. Headless mode Headless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run. 2. Ask human The traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu... 3. Tasks queue Beads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
