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

Forge: A Memory System for Claude Code Built with Claude Code
A developer built Forge, a TypeScript monorepo MCP server that automatically captures decisions, constraints, and rejections from Claude Code conversations. It uses a six-stage pipeline to classify, extract, and persist structured data in an event-sourced SQLite model.

ModelFitAI: Deploy AI Agents Without VPS Setup, Built with Claude Code
ModelFitAI is a platform that lets developers deploy AI agents directly on its infrastructure, eliminating VPS setup, Docker configuration, and SSH sessions. The entire platform was built using Claude Code by a solo founder.

Grape Root Tool Reduces Claude Code Token Usage by Caching Repository Context
A free experimental tool called Grape Root addresses redundant token consumption in Claude Code by maintaining lightweight state about previously explored repository files, preventing unnecessary re-reads of unchanged files during follow-up prompts.

Sgai: Goal-Driven Multi-Agent Software Development Tool
Sgai is an open-source Go tool that coordinates AI agents to execute software goals defined in GOAL.md files. It decomposes goals into DAG workflows, runs tests for completion gates, and operates locally with a web dashboard for monitoring.