Agent Beacon is an open-source, local-first memory layer for AI coding agents that captures full session history across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses. It identifies useful workflows, corrections, and debugging patterns from past sessions and makes that knowledge reusable by future agents via MCP or Agent Skills. Beacon normalizes all captured activity into a common OpenTelemetry-based event model, giving developers a single searchable dataset regardless of which coding tool they use. Knowledge compounds across tools and sessions rather than disappearing when a session ends.