agent-beacon

Name: agent-beacon
Author: Asymptote-Labs

Verified

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.

445stars

36forks

Installation

# Add to your Claude Code skills
git clone https://github.com/Asymptote-Labs/agent-beacon

Getting Started

Guides for using ai agents skills like agent-beacon.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 6/16/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-06-16T09:26:59.249Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

Compare with similar skills

See how agent-beacon compares with popular alternatives.

agent-beacon vs hermes agent

See comparison

agent-beacon vs ecc

See comparison

agent-beacon vs everything claude code

See comparison

README.md

Frequently Asked Questions

What is agent-beacon?

agent-beacon is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Asymptote-Labs. Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud. It has 445 GitHub stars.

Is agent-beacon safe to use?

Yes. agent-beacon passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install agent-beacon?

Clone the repository with "git clone https://github.com/Asymptote-Labs/agent-beacon" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is agent-beacon written in?

agent-beacon is primarily written in Go. It is open-source under Asymptote-Labs on GitHub, so you can review or fork the full source.

Are there alternatives to agent-beacon?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent-beacon against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

257,961

narrator-ai-cli-skill ai-native-hiring-guide

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

Beacon Overview

Beacon is the system of record for all your agent activity, wherever your agents run.

Agent activity is fragmented across harnesses and environments, leaving no consistent way to see, reconstruct, or reason about what agents actually did.

Beacon solves this problem by capturing the full agent execution trace across every harness and environment, and normalizes that activity into a single, unified schema.

Key Capabilities:

Capability	What it means
Broad runtime coverage	24 local agent runtimes, plus browser chat, CI, cloud agents, and SDKs
One unified schema	Every session, prompt, tool, command, edit, approval, and token in one event model
Local-first by default	Data stays on the machine: durable JSONL and a read-only dashboard, no account
Offline threat detection	`beacon scan` runs open Threat Rules over your logs, with no network
Forwards where you already work	Stream the same log to your SIEM, observability, or object storage
Deploys in one command or fleet-wide	One command on a laptop, MDM across a fleet

Read the documentation to learn more.

Getting Started

Prerequisites:

macOS, Linux, or Windows. Homebrew installs the CLI; every release also ships a native package that installs the service itself
At least one supported agent runtime on the machine
No account, no API key, and no network dependency. Forwarding to Asymptote Managed additionally needs Vector 0.50+, which the macOS package bundles

Installation

# Install Beacon
brew tap asymptote-labs/tap
brew install beacon

# Install the endpoint agent and point local runtimes at it
beacon endpoint install

# Watch what your agents are doing
beacon endpoint dashboard

Note Events land in ~/.beacon/endpoint/logs/runtime.jsonl and the dashboard is local and read-only.

Ways to Run Beacon:

Open Source: free, local-only, your machine and your logs. Quickstart
Asymptote Enterprise: fleet rollout through MDM, managed ingest with per-device approval and revocation, and one dashboard across your organization. Book a demo →

Asymptote Enterprise

Asymptote's enterprise platform builds on the open-source foundation and adds real-time policy enforcement. It solves the engineering and infrastructure challenges of analyzing fleet-wide agent activity in real time for detection, remediation, and containment at petabyte scale.

Enterprise Capabilities:

Capability	What it means
Real-time policy enforcement	Allow or deny agent actions as they happen, with identity mapping and approval workflows
Real-time detection and response	Detections run on the live event stream, surfacing risky agent behavior as it happens with the session timeline to act on it
Fleet-wide inventory	Every agent, harness, and device in the organization in one view, rolled out through MDM
Managed ingest and retention	Hosted search and long-term retention across every endpoint, without running the pipeline yourself
SSO and access control	Single sign-on, role-based access control, and priority support and onboarding

Book a demo →

High-Level Architecture

Beacon captures activity where each agent actually runs, then normalizes it into a single OpenTelemetry-based event model.

See the open-source architecture reference for the full breakdown by surface.

Supported Surfaces

Agent Runtimes

Local Agents

Runtime	Collection	Session	Prompt	Tool	Command	File	Approval	MCP	Tokens
Antigravity CLI	Hooks	✅	✅	✅	✅	✅	–	–	–
Claude Code	OTLP + hooks	✅	✅	✅	✅	✅	✅	✅	✅
Claude Cowork	OTLP	✅	✅	✅	✅	✅	✅	✅	✅
Cline	Plugin	✅	✅	✅	✅	✅	–	✅	✅
Codex CLI	OTLP + hook	✅	✅	✅	✅	–	✅	–	✅
Cursor	Hooks	✅	✅	✅	✅	✅	✅	✅	–
Devin CLI	Hooks	✅	✅	✅	✅	✅	✅	✅	–
Devin Desktop	Hooks	–	✅	✅	✅	✅	–	✅	–
Factory Droid	OTLP + hooks	✅	✅	✅	–	✅	–	–	–
fx (Vercel Labs)	Poll	✅	✅	✅	✅	✅	–	✅	✅
Gemini CLI	OTLP	–	✅	✅	–	✅	✅	✅	–
GitHub Copilot CLI	OTLP	✅	✅	✅	–	–	✅	–	–
goose	Plugin + OTLP	✅	✅	✅	✅	✅	–	✅	✅
Grok Build	Hooks	✅	✅	✅	✅	✅	–	–	–
Hermes Agent	Hooks	✅	✅	✅	✅	✅	✅	–	–
Kiro	Hooks	✅	✅	✅	✅	✅	–	✅	–
Muse Code	Hooks	✅	✅	✅	✅	✅	✅	–	–
Oh My Pi	Extension	✅	✅	✅	✅	✅	✅	✅	✅
OpenClaw Gateway	OTLP	~	~	~	~	~	~	~	~
OpenCode	Plugin	✅	✅	✅	✅	✅	✅	✅	✅
OpenHands	Hooks	✅	✅	✅	✅	✅	–	✅	–
Pi	Extension	✅	✅	✅	✅	✅	–	–	✅
Prime Agent	Not yet collected	–	–	–	–	–	–	–	–
Qwen Code	Hooks	✅	✅	✅	✅	✅	✅	–	–
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