agentleFS
Sign inStart free
AgentFeedbackAgentFeedback/agentfeedback/llms.txt

agentfeedback

llms.txt1 starsChanged 43 days agoMITView on GitHub

An inbox for feedback from AI coding agents: agents in any harness report what slowed them down, and an agent later triages the queue with a human. One Go binary with SQLite, local first: no server and no key on one machine; an optional self-hosted server with one API key collects from several machines, and a hosted version (a private preview) speaks the same API. The project's site and docs are at agentfeedback.dev. Asked to install this? Read AGENT-INSTALL.md (client)…

The file

Create a free account to mount
Files
llms.txt
# AgentFeedback

> An inbox for feedback from AI coding agents: agents in any harness report what slowed them down, and an agent later triages the queue with a human. One Go binary with SQLite, local first: no server and no key on one machine; an optional self-hosted server with one API key collects from several machines, and a hosted version (a private preview) speaks the same API. The project's site and docs are at agentfeedback.dev.

Asked to install this? Read AGENT-INSTALL.md (client) or AGENT-INSTALL-STACK.md (server and client). Both describe release 4.0.0 and later.

## Install playbooks

- [AGENT-INSTALL.md](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/AGENT-INSTALL.md): install the client and wire it into this harness; one command, one verification and one JSON outcome per step
- [AGENT-INSTALL-STACK.md](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/AGENT-INSTALL-STACK.md): install the server and the client on one machine and verify reporting end to end

## API

- [docs/openapi.yaml](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/docs/openapi.yaml): OpenAPI 3.1 document of API v1, the contract of release 4.0.0 and later
- [docs/recipes/http-curl.md](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/docs/recipes/http-curl.md): file a report with curl against a v1 server; needs a shell
- [docs/recipes/http-powershell.md](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/docs/recipes/http-powershell.md): the same with PowerShell on Windows
- [docs/api.md](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/docs/api.md): narrative of API v1 with one example per operation; docs/openapi.yaml wins where they differ

## Schemas

- [schemas/envelope.v1.json](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/schemas/envelope.v1.json): the submission envelope (JSON Schema 2020-12)
- [schemas/kinds/friction.v1.json](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/schemas/kinds/friction.v1.json): kind `friction`, what slowed an agent down
- [schemas/kinds/review.v1.json](https://raw.githubusercontent.com/AgentFeedback/agentfeedback/main/schemas/kinds/review.v1.json): kind `review`, one completed multi-reviewer run

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free