What problem it solves

Agent workflows, corrections, debugging patterns, and repository conventions often disappear when a session ends or remain trapped inside one coding tool. Beacon addresses this by capturing session history across harnesses and turning useful findings into reusable memory for future agents.

Key features

• Cross-harness session history — Capture session history from Claude Code, Cursor, Codex, OpenCode, Cline, and other supported harnesses in a unified place.

  Source: README

• Reusable agent memory — Identify workflows, corrections, debugging patterns, and repository conventions, review them, and make them available to future agents.

  Source: README

• Complete session replay — Record prompts, responses, tools, commands, edits, approvals, MCP activity, and token usage in a common trace format.

  Source: README

• Local-first inspection and portability — Store telemetry as durable local JSONL, explore it through a read-only dashboard, and explicitly choose whether to forward it.

  Source: README, cli

Quick start

Copied verbatim from the project's README.

brew update
brew trust asymptote-labs/tap
brew tap asymptote-labs/tap
brew install beacon

beacon endpoint install

beacon traces

Who it may suit

This may suit developers who use multiple AI coding harnesses and want project knowledge to persist across tools and sessions. It may also suit teams that want reviewed agent memory available through MCP or Agent Skills.

Topics to discuss

• Which cross-harness workflows should be captured and distilled first?

• How should shared memory be reviewed before future agents can retrieve it?

• What local-only telemetry workflows and integrations would be most useful?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/Asymptote-Labs/agent-beacon#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.