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

QCAI Mobile App Adds OpenClaw Gateway Control with Native Tailscale VPN
QCAI for iOS and Android now integrates with OpenClaw Control Center, allowing direct gateway management from mobile devices via secure Tailscale VPN tunnels without open ports.

FOMOE Enables 397B Qwen3.5 Model Inference on $2,100 Desktop Hardware
FOMOE (Fast Opportunistic Mixture of Experts) allows running Qwen3.5's 397 billion parameter flagship model at 5-9 tokens/second on consumer hardware using two $500 GPUs, 32GB RAM, and an NVMe drive with Q4_K_M quantization.

PocketBot Beta: Privacy-First iOS AI Agent with Hybrid Local/Cloud Engine
PocketBot is an iOS AI agent that runs in the background, hooks into App Intents, and uses a hybrid engine: local execution for system triggers and PII sanitization, with cloud processing for complex tasks like email summarization or flight booking.

AI Agent Autonomously Creates Video Using Remotion Without Predefined Tools
A developer tested an AI agent that autonomously created a short video reel by installing Remotion, writing composition code, debugging issues, and delivering a rendered file without human intervention.