Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, or in the cloud.
# Add to your Claude Code skills
git clone https://github.com/Asymptote-Labs/agent-beaconagent-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, or in the cloud. It has 236 GitHub stars.
agent-beacon's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
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).
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.
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.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, or in the cloud.
Beacon started with local endpoint telemetry for security and IT teams that need visibility into AI agent activity on employee machines. It now captures supported runtime activity across local agents, CI agents, and cloud agents, then normalizes that activity into events your team can inspect, retain, and forward under your control.
Beacon is built to be easy to deploy for Security and IT teams through MDM deployment, CI workflows, and cloud-agent setup paths, and to emit agent harness telemetry logs to all the major enterprise-grade SIEMs.
Learn more in the Agent Beacon Documentation.
Beacon keeps endpoint collection, processing, and inspection local by default, while extending the same normalized event model to CI and cloud-agent telemetry paths under customer control.
Beacon captures supported agent harness activity across local endpoints, CI jobs, and cloud-agent surfaces, then writes normalized events that teams can inspect in place or forward into customer-managed security pipelines.
Agent Beacon supports the most popular enterprise agent harnesses across local, CI, and cloud surfaces.
| Agent harness | Collection path | Telemetry coverage |
|---|---|---|
| Antigravity CLI | Native hooks | Prompt, pre-tool, post-tool, stop, invocation, command, and file telemetry where Antigravity exposes hook payloads |
| Claude Code | Local OTLP export plus optional hooks | Prompt, command, tool, file, lifecycle, subagent, and permission telemetry where emitted through OTLP or hooks |
| Codex CLI | Local OTLP logs | Session, prompt, approval, and tool-result activity from Codex semantic logs |
| Cursor | Native hooks | Prompt, tool, shell command, MCP-like, approval, and file edit telemetry |
| Devin CLI | Native hooks | Session, prompt, pre-tool, post-tool, permission request, stop, session-end, approval, and file telemetry |
| Devin Desktop | Cascade/Windsurf hooks | Prompt, command, MCP tool, file read, and file write telemetry where Desktop exposes Cascade hook payloads |
| Factory Droid | OTLP HTTP plus optional hooks | Session, prompt, write/edit/create tool use, stop, session-end, and available OTLP telemetry |
| Gemini CLI | Opt-in local OTLP | Prompts, tool calls, MCP activity, file operations, and approval-related events emitted through OTLP |
| GitHub Copilot CLI | MDM-managed OTLP HTTP | Prompt, session, tool, and approval-like activity emitted through Copilot CLI spans |
| Grok Build | Native hooks | Session, prompt, pre-tool, post-tool, failed tool, stop, session-end, command, and file telemetry |
| OpenCode | Managed plugin hooks | Chat messages, session events, command execution, permission activity, diffs, and errors |
| VS Code | Copilot Chat OTel plus optional preview hooks | Copilot session, prompt, model, and tool activity through OTel; optional hooks for extra lifecycle and cross-agent detail |
| Agent harness | Collection path | Telemetry coverage |
|---|---|---|
| Claude Cowork | Admin-configured OTLP | Prompt, command, tool, and file telemetry when emitted through Claude Cowork OTLP |
| Hermes Agent | Shell hooks | Prompt, observed tool, command, file, approval request and response, session lifecycle, and subagent stop telemetry |
| OpenClaw Gateway | Gateway-configured OTLP/HTTP | OTLP logs, traces, and metrics from the Gateway diagnostics plugin |
| Harness | Collection path | Telemetry coverage |
|---|---|---|
| CI agent telemetry | Temporary local collector through beacon ci exec or beacon ci start / beacon ci finish |
Supported agent prompt, tool, command, file, and run context where emitted during the job |
| Cloud surface | Collection path | Telemetry coverage |
|---|---|---|
| Anthropic | OpenLLMetry instrumentation through @asymptote/sdk |
Supported Anthropic model call spans, errors, and OpenTelemetry attributes |
| Claude Agent SDK | Query wrapper through Observe.wrapClaudeAgentQuery() |
Query root spans with Beacon-compatible prompt attributes |
| Claude Code Cloud Agents | Cloud sandbox hooks with GCS upload | Session, prompt, tool, command, file, and lifecycle telemetry where Claude Code cloud hook payloads expose it |
| Cursor Cloud Agents | Cloud sandbox hooks with GCS upload | Tool, shell command, file, subagent, and compaction telemetry where Cursor cloud hook payloads expose it |
| Devin Cloud Agents | Org-wide API poll via beacon cloud devin pull, with GCS upload |
Session, prompt, agent message, status, pull request, and ACU usage telemetry the Devin sessions API exposes (message-level; the autonomous agent runs no in-sandbox hooks) |
| OpenAI | OpenLLMetry instrumentation through @asymptote/sdk |
Supported OpenAI model call spans, errors, and OpenTelemetry attributes |
| Vercel AI SDK | Tracer handoff through experimental_telemetry |
AI SDK model call and tool spans where telemetry is enabled |
Agent Beacon writes endpoint telemetry to local JSONL by default and supports customer-controlled forwarding into common security information and event management (SIEM), log aggregation, and object storage destinations.
| Destination | Support path |
|---|---|
| CrowdStrike Falcon LogScale HEC | Optional endpoint forwarding with LogScale ingest tokens during install or repair |
| Microsoft Sentinel | Azure Monitor Agent and Data Collection Rule content pack over local JSONL |
| [Rapid7 InsightIDR](htt |