The Cross‑Harness Memory Layer for Coding Agents
Beacon turns agent sessions across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses into a compounding knowledge layer, where every successful run
makes every future agent smarter.
brew tap asymptote-labs/tap && brew trust asymptote-labs/tap && brew install beacon && beacon endpoint install
Compounding agent memory
Turn every agent run into shared knowledge
Beacon captures what happens across your AI agents and turns successful workflows, corrections, and debugging patterns into reusable knowledge that compounds across harnesses.
Agent observability
Understand how your agents actually work
Beacon gives you a complete view of agent activity across harnesses, repositories, models, and workflows so you can see what agents are doing, where they succeed, and where they get stuck.
Workflow debugging
Find exactly where agent workflows break
Beacon traces every command, tool call, retry, and failure across a session so you can quickly pinpoint what went wrong and improve the workflow behind it.