The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
Agent Beacon is a local-first memory layer that records AI coding-agent sessions and turns useful workflows, corrections, and debugging patterns into knowledge that other agents can reuse. Developers use it across Claude Code, Cursor, Codex, OpenCode, and other agent harnesses so lessons and repository conventions persist between sessions. The catalogue entries provide instructions and a skill for working with Beacon's shared agent memory.
Latest release v1.3.41 · 15 Oct 2026
3 files for Claude Code, Codex and OpenCode: self-verify-beacon-in-sandbox, agent-beacon AGENTS.md, agent-beacon CLAUDE.md — 20,571 tokens loaded in every session.
AGENTS.md A 580 tok CLAUDE.md D 19,991 tok .claude/skills/self-verify-beacon-in-sandbox/SKILL.md A 114 tok These files are Asymptote-Labs/agent-beacon's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.