Beacon: Open-Source Endpoint Telemetry for Local AI Agents

Beacon is Asymptote Lab's open-source endpoint agent that gives security and IT teams visibility into local AI agent activity. It hooks into agent harnesses like Claude Code, Codex CLI, OpenCode, Factory Droid, Claude Cowork, and Cursor, captures supported activity, and normalizes it into endpoint events stored as local JSONL or forwarded to SIEM pipelines.
Supported Agents and Outputs
The agent supports the following coding agent runtimes:
- Claude Code – via local OpenTelemetry configuration
- Codex CLI – via local OpenTelemetry configuration
- OpenCode – via Beacon hook adapter
- Factory Droid – via local OpenTelemetry configuration and optional hook adapter
- Claude Cowork – via admin-configured OpenTelemetry setup
- Cursor – via Beacon hook adapter
Outputs include local JSONL (default), Wazuh (localfile configuration with content pack), Elastic (Filebeat or Elastic Agent over JSONL), Splunk HEC (optional forwarding during install/repair), and customer-managed SIEM pipelines.
Architecture and Deployment
Collection, processing, and inspection remain local to the endpoint; forwarding is customer-controlled. Beacon filters out generic runtime metrics (Node.js event loop, V8 heap, CPU, memory) by default so agent prompts, tools, approvals, and file activity stay easy to inspect. To include runtime metrics, use beacon endpoint install --include-runtime-metrics or beacon endpoint repair --include-runtime-metrics.
For MDM deployment, Beacon supports Jamf Pro (macOS package, policy scripts, Extension Attributes) and Fleet (macOS package with user-context helpers).
Quickstart
Install via Homebrew:
brew tap asymptote-labs/tap
brew install beacon
For full setup paths, see the Quickstart docs. Security and IT teams should refer to the managed deployment guidance for rollout, validation, retention, and SIEM forwarding.
📖 Read the full source: HN AI Agents
👀 See Also

Arena AI Model ELO History Tracks LLM Performance Decay Over Time
A live dashboard visualizes ELO ratings of flagship models from major AI labs, revealing gradual performance degradation and sudden jumps at new releases. The tool dynamically plots one curve per lab, tracking the highest-rated model.

Zot: A Lightweight Terminal Coding Agent Now Supports Claude Opus 4.8
Zot is a minimal terminal coding agent distributed as a single static Go binary with no runtime or Docker dependencies. It now supports Claude Opus 4.8 along with dozens of other models.

SymDex: Open-Source MCP Code Indexer Reduces AI Agent Token Usage
SymDex is an open-source MCP code indexer that pre-indexes codebases to help AI coding agents find functions and classes without reading entire files, reducing token usage by approximately 97% per lookup according to the developer's benchmarks.

Ghostbar: A ~5MB native macOS Swift AI client that hides from screen sharing
Ghostbar is a native Swift macOS menu bar AI client (~5MB) that uses window.sharingType = .none to become invisible to screen recorders. Works with Ollama, vLLM, llama.cpp, and any OpenAI-compatible backend.