[opensourcedex]

agent-beacon is a free, open source documentation & knowledge base project written in Go and released under MIT. It has 905 GitHub stars, 64 forks and 13 open issues, and was last pushed 2 hours ago. On this registry it ranks #72 of 93 tracked projects in Documentation & Knowledge Base, with 5 head-to-head comparisons available.

What is agent-beacon?

Agent Beacon is an MIT-licensed, local-first memory layer for AI coding agents that captures full session history across Claude Code, Cursor, Codex, OpenCode and 20+ other harnesses, then turns useful workflows, corrections and debugging patterns into knowledge that future agents can reuse — built for developers and teams who want agent knowledge to compound across tools instead of disappearing when a session ends.

What it is

Agent Beacon is a Go program released under the MIT licence that sits above the AI coding agent harness layer rather than inside any single harness. It continuously captures agent session history in the background as you work in Claude Code, Cursor, Codex, OpenCode, Cline or any other supported harness, and holds sessions from all of them in one place. Around that history it builds a loop: run agents, capture session history, evaluate what worked, extract useful knowledge, review and approve it, then reuse it in future sessions.

The concrete problem it addresses is that most agent memory belongs to a single harness, so anything learned in one session is lost when that session ends. A migration that was finally run the right way, a debugging path that fixed an obscure issue, a testing convention agents repeatedly get wrong, a repository-specific workflow, or a correction given to several agents separately all have to be relearned from scratch. Agent Beacon replaces that per-harness, per-session memory with a cross-harness store, on the premise that a problem solved by one agent should not need to be learned again by another.

Key capabilities

  • Cross-harness session history that collects Claude Code, Cursor, Codex, OpenCode, Cline and 20+ other harnesses into a single view.
  • Exact session replay covering prompts, responses, tools, commands, edits, approvals, MCP activity and tokens in one trace.
  • A local terminal browser opened with beacon traces for traces, event timelines, token usage and retained content.
  • A local web view available through beacon endpoint dashboard.
  • Local-first portability built on a durable JSONL event stream at ~/.beacon/endpoint/logs/runtime.jsonl, with explicit destinations and no harness lock-in.
  • Shared agent memory that reviewed knowledge can be retrieved from through MCP or Agent Skills.
  • Explicit privacy and account controls, including beacon whoami to inspect the account used during setup and beacon endpoint disconnect to stop forwarding.

Who uses it and how

  • Individual developers who work across more than one harness and want a single searchable history instead of scattered session logs.
  • Teams that want repository conventions, testing habits and correction patterns captured once and made retrievable by every agent working in the codebase.
  • Fleet operators: the system, package, MDM and CI installation paths remain noninteractive and account-free, which suits managed rollouts.
  • Privacy-sensitive organisations that choose the Local option during interactive setup to keep everything on the machine.
  • People debugging agent behaviour, who can replay the full event timeline of a session rather than reconstructing it from memory.

Getting started

On macOS the endpoint is installed with brew trust asymptote-labs/tap, brew tap asymptote-labs/tap, brew install beacon, then beacon endpoint install; Linux uses the .deb or .rpm from the latest release and Windows uses the x64 MSI, which also supports a silent /qn install.

How it compares

The facts provided here name no directly comparable alternative tool, and no list of paid products that this project replaces is supplied. On the evidence available, Agent Beacon stands alone in this registry.

When to use it — and when not to

A self-hoster runs a local endpoint agent and is responsible for the retained event stream on that machine; no external database or mail service is mentioned as a requirement. Anyone who needs zero connection to a hosted account should note that interactive setup signs in through beacon.sh and preselects Beacon Managed, with Local offered as an explicit opt-out and the noninteractive paths left account-free. The documented material covers capture, replay and portability in most detail, while the evaluate, extract and review stages appear mainly as a loop diagram, so teams expecting a fully specified curation workflow should read the linked docs before committing.

project readme (upstream, from github) — read inline

GitHub release Homebrew GitHub Workflow Status MIT license Docs Discord

Website · Docs · Discord · Install · Commands

Beacon captures agent session history across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses, then turns useful workflows, corrections, and debugging patterns into reusable knowledge for future agents.

A problem solved by one agent shouldn't need to be learned from scratch by another.

Beacon Overview

Beacon is an open-source memory layer for AI coding agents that learns from your work across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses. It captures full session history, identifies useful workflows, corrections, and debugging patterns, and makes that knowledge reusable by future agents. Built for developers who want agent knowledge to compound across tools instead of disappearing when a session ends.

Key Capabilities:

  • Cross-harness history - sessions from Claude Code, Cursor, Codex, OpenCode, Cline, and 20+ harnesses in one place
  • Knowledge that compounds - workflows, corrections, debugging patterns, and repo conventions that survive beyond a single session
  • Shared agent memory - reviewed knowledge future agents can retrieve through MCP or Agent Skills
  • Exact session replay - prompts, responses, tools, commands, edits, approvals, MCP activity, and tokens in one trace
  • Local-first portability - durable JSONL, explicit destinations, and no harness lock-in

🚀 Quick Start

Beacon is open source and local-first. Interactive endpoint setup signs in through beacon.sh and preselects Beacon Managed, with an explicit Local opt-out. Signing in forwards nothing; confirming Managed installs Beacon and connects this machine in the same command, and the confirm screen says so before you accept. System, package, MDM, and CI installation paths remain noninteractive and account-free.

1. Install Beacon

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

beacon endpoint install
Linux

Download the .deb or .rpm from the latest release.

sudo apt install ./beacon_<version>_linux_amd64.deb

or:

sudo dnf install ./beacon_<version>_linux_amd64.rpm
Windows

Download the x64 MSI from the latest release.

msiexec /i BeaconEndpointAgent-<version>-x64.msi

For silent installation:

msiexec /i BeaconEndpointAgent-<version>-x64.msi /qn

2. Use your agents normally

Open Claude Code, Cursor, Codex, or any other supported harness.

Beacon continuously captures your session history in the background

3. Explore your history

beacon traces

This opens a local terminal browser for traces, event timelines, token usage, and retained content. Nothing is sent anywhere. To use the local web view instead:

beacon endpoint dashboard

Or inspect the raw event stream:

~/.beacon/endpoint/logs/runtime.jsonl

[!NOTE] Signing in does not enable forwarding. Confirming the preselected Beacon Managed option does: the wizard says so on the confirm screen, names what your chosen privacy mode sends, and connects the endpoint after the install succeeds. Choose Local to keep everything on this machine, and disconnect any time with beacon endpoint disconnect.

Inspect the account used during interactive setup:

beacon whoami

🧠 Turn Session History Into Memory

Every agent session contains potentially useful knowledge about your codebase.

Beacon creates a loop around that history:

Run agents
    ↓
Capture session history
    ↓
Evaluate what worked
    ↓
Extract useful knowledge
    ↓
Review + approve
    ↓
Reuse across future agents

That could be:

  • the right way to run a migration
  • a debugging path that finally fixed an obscure issue
  • a testing convention agents repeatedly get wrong
  • a repository-specific workflow
  • the right sequence of internal tools
  • a correction you've given multiple agents

Instead of disappearing into old sessions, that knowledge becomes reusable.

🔀 Cross-Harness by Design

Most agent memory belongs to a single harness.

Beacon sits across the harness layer.

Claude Code ─┐
Cursor ──────┤
Codex ───────┼──→ Beacon ──→ shared project knowledge
OpenCode ────┤
Cline ───────┘

Because Beacon captures and normalizes session history across tools, knowledge learned through Claude Code doesn't have to stay in Claude Code.

Your Cursor sessions can improve Codex.
Your Codex sessions can improve OpenCode.
Your history keeps compounding even as you switch tools.

Your agent session history belongs to you, not the harness.

🔎 One Trace Format for Every Agent

Beacon captures agent execution where it happens and normalizes it into a common OpenTelemetry-based event model.

That includes:

  • sessions
  • prompts and responses
  • tool calls
  • commands
  • file activity
  • approvals
  • MCP interactions
  • token usage

Instead of separate proprietary histories for every coding tool, you get one dataset you can inspect, search, learn from, and build on.

🖥️ Local Dashboard

Beacon ships with a local, read-only dashboard:

beacon endpoint dashboard

Use it to explore session history across harnesses and understand what your agents actually did.

The underlying JSONL remains directly accessible, so you're never dependent on the UI.

Supported Agents

Beacon supports local agents, browser agents, cloud agents, CI workflows, and agent SDKs.

Local Agent Coverage

Runtime Collection Session Prompt Tool Command File Approval MCP Tokens
Antigravity CLI Hooks ✅ ✅ ✅ ✅ ✅ – – –
Claude Code OTLP + hooks + poll ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Claude Cowork OTLP ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
Cline Plugin + poll ✅ ✅ ✅ ✅ ✅ – ✅ ✅
Codex CLI OTLP + hooks + poll ✅ ✅ ✅ ✅ – ✅ – ✅
Codex Desktop OTLP ✅ ✅ ✅ ✅ – ✅ – ✅
Cursor Hooks + poll ✅ ✅ ✅ ✅ ✅ ✅ ✅ –
DeepSeek Harness Hooks + poll ✅ ✅ ✅ ✅ ✅ – ✅ ✅
Devin CLI Hooks ✅ ✅ ✅ ✅ ✅ ✅ ✅ –
Devin Desktop Hooks – ✅ ✅ ✅ ✅ – ✅ –
Factory Droid OTLP + hooks + poll ✅ ✅ ✅ – ✅ ✅ – –
fx (Vercel Labs) Poll ✅ ✅ ✅ ✅ ✅ – ✅ ✅
Gemini CLI OTLP – ✅ ✅ – ✅ ✅ ✅ –
GitHub Copilot CLI OTLP + poll ✅ ✅ ✅ ✅ ✅ ✅ – ✅
goose Adapter only; manual hooks/OTLP ✅ ✅ ✅ ✅ ✅ – ✅ ✅
Grok Build Hooks + poll ✅ ✅ ✅ ✅ ✅ ✅ – –
Hermes Agent Hooks + poll ✅ ✅ ✅ ✅ ✅ ✅ ✅ –
Kimi Code Hooks ✅ ✅ ✅ ✅ ✅ ✅ ✅ –
Kiro Hooks ✅ ✅ ✅ ✅ ✅ – ✅ –
Muse Code Hooks ✅ ✅ ✅ ✅ ✅ ✅ – –
Oh My Pi Extension ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
OpenClaw Gateway Plugin + OTLP + poll ✅ ✅ ✅ ✅ ✅ – ✅ ~
OpenCode Plugin + poll ✅ ✅ ✅ ✅ ✅ ✅ ✅ ✅
OpenHands Hooks ✅ ✅ ✅ ✅ ✅ – ✅ –
Pi Extension + poll ✅ ✅ ✅ ✅ ✅ – ✅ ✅
Prime Agent Extension + poll ✅ ✅ ✅ ✅ ✅ – – ✅
Qwen Code Hooks ✅ ✅ ✅ ✅ ✅ ✅ – –
Senpi Extension ✅ ✅ ✅ ✅ ✅ – – ✅
VS Code OTLP + hooks ✅ ✅ ✅ ~ ~ – ~ –

Browser Chat

Site Collection Prompt Response Tool Tokens
Claude.ai Extension → local OTLP ✅ ✅ ✅ ~
ChatGPT Extension → local OTLP ✅ ✅ ✅ –

Cloud Agents

Runtime Collection Session Prompt Tool Command File Tokens
Claude Code Cloud Agents Sandbox hooks → GCS or S3 ✅ ✅ ✅ ✅ ✅ –
Cursor Cloud Agents Sandbox hooks → GCS or S3 – ✅ ✅ ✅ ✅ –
Devin Cloud Agents API poll → GCS ✅ ✅ – – – ✅
CI jobs beacon ci exec → temporary local collector ✅ ✅ ✅ ✅ ✅ ✅

SDK Instrumentation

SDK Surface Collection Captures
Anthropic OpenLLMetry through @asymptote/sdk Model call spans, errors, and OTel attributes
OpenAI OpenLLMetry through @asymptote/sdk Model call spans, errors, and OTel attributes
Claude Agent SDK Observe.wrapClaudeAgentQuery() Query root spans with Beacon-compatible prompt attributes
Vercel AI SDK experimental_telemetry tracer handoff Model call and tool spans where telemetry is enabled

Output Destinations

Beacon writes endpoint telemetry to local JSONL by default.

You can also forward the same normalized session history into infrastructure you already use:

Splunk · Datadog · Elastic · Microsoft Sentinel · CrowdStrike Falcon LogScale · Sumo Logic · Wazuh · AWS S3 · GCS · CloudWatch

Destination Category Support Path
Local JSONL Local Default endpoint log and local dashboard source
Beacon Managed Hosted forwarding Signed-in device enrollment with Standard or Metadata-only privacy
CrowdStrike Falcon LogScale HEC SIEM Endpoint forwarding with LogScale ingest tokens
Microsoft Sentinel SIEM Azure Monitor Agent and Data Collection Rule content pack
Rapid7 InsightIDR SIEM Custom Logs webhook content pack
Splunk HEC SIEM Endpoint forwarding during install or repair
Sumo Logic SIEM HTTP Logs & Metrics Source content pack
Wazuh SIEM Localfile configuration and Beacon content pack
AWS CloudWatch Logs Log aggregation Vector content pack
Datadog Log aggregation Datadog Agent custom log collection
Elastic Log aggregation Filebeat or Elastic Agent
Customer-managed pipelines Log aggregation Forward directly from local Beacon JSONL
AWS S3 Object storage Vector, CI upload, or cloud-agent snapshots
Google Cloud Storage Object storage Vector, CI upload, or cloud-agent snapshots

Architecture

Beacon captures activity where agents actually run and normalizes it into one shared event model.

Local agents ───────┐
Browser chat ───────┤
CI ─────────────────┼──→ Beacon ──→ unified session history
Cloud agents ───────┤                    │
Agent SDKs ─────────┘                    ├──→ local JSONL
                                         ├──→ reviewed memory
                                         ├──→ MCP / Agent Skills
                                         └──→ your own infrastructure

See the documentation for the full architecture breakdown.

Documentation

Read the docs for:

  • installation
  • supported runtimes
  • event schema
  • session history
  • memory
  • MCP
  • Agent Skills
  • forwarding
  • advanced configuration

Read the docs →

Contributing

Contributions are welcome.

Open an issue, submit a pull request, or join the Discord.

License

MIT

Star History

Star History Chart

Frequently asked questions

Is agent-beacon free to use?

agent-beacon is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does agent-beacon do?

The cross-harness self-improving memory layer for AI agents.

What is agent-beacon written in?

agent-beacon is primarily written in Go. Its source is publicly available at https://github.com/Asymptote-Labs/agent-beacon, and it has 905 GitHub stars.