feedback-memory runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 3 Oct 2026.
Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections
Nothing serious here today
Today is the operative word: we check feedback-memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Alternatives to feedback-memory
same job, measured the same wayLocal memory your AI tools share: decisions, notes and corrections that carry across sessions.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Auto-approve small agent actions under your rules; approval cards for the rest.
Persistent memory layer for AI coding agents — your agent remembers what you taught it.
Memory for any Ai: remembers across sessions, enforces your rules before actions, reviews the work.
Living technical memory for AI agents: recall approved project context, record what was learned.
Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.
Team memory for coding agents: rules you approve, served to every agent, and which ones it cited.
feedback-memory — questions
Answers built from our own checks of this server.