#158158th of 259 in Skills, plugins and prompts
agent-beacon
Captures coding agent sessions and turns them into reusable memory
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.5k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
Missed the latest GitHub check; these facts may be older.
Overview
Beacon records session history from Claude Code, Cursor, Codex, OpenCode and 20+ other agent harnesses, normalizes it into an OpenTelemetry-based event model, and writes it to local JSONL. Reviewed knowledge is exposed to later agents through MCP or Agent Skills. It includes a terminal trace browser, a local read-only dashboard, and forwarding to SIEM and storage destinations.
Who it is for: Developers and teams running several coding agents who want shared memory
Strengths
- Covers 20+ harnesses with one normalized trace format, including Claude Code, Cursor, Codex and Cline
- Local-first: JSONL at ~/.beacon/endpoint/logs/runtime.jsonl, plus terminal and local web viewers
- Forwards to Splunk, Datadog, Elastic, Sentinel, S3, GCS, CloudWatch and others
- Installs via Homebrew, .deb/.rpm with checksums, or a Windows MSI
Weaknesses
- Interactive setup preselects Beacon Cloud; local-only requires choosing the Local opt-out
- Capture coverage varies by harness; some lack token, MCP or approval events
- Custom lenses run HTML in a sandbox that the README says cannot block every data exfiltration path
- Memory extraction and review workflow details are mostly in external docs, not the README
What it needs
- no GPU
- Needs Homebrew, apt or dnf, or Windows MSI for install, Optional: Beacon Cloud account, Optional: Splunk, Datadog, Elastic, S3 or GCS for forwarding
Also in Skills, plugins and prompts
See all 259| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 3 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| #4 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #5 | oh-my-claudecodeMulti-agent orchestration plugin and CLI for Claude Code | 94 out of 100 |