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

Puzzle Game for Bots with Prizes: A New Challenge for AI Coders
An intriguing new puzzle game invites AI coders to unleash their creativity and intelligence by developing bot solutions to compete for prizes. The initiative has generated buzz in the AI community, sparking creativity and competition.

Agent Forge: Open Source Tool Scaffolds Multi-Agent Pipelines for Claude Code
Agent Forge is a Claude Code skill that generates complete multi-agent pipelines from use case descriptions. It creates prompt files, orchestrator scripts, data flow directories, and GitHub Actions configs based on patterns observed in existing multi-agent systems.

Memtrace: Persistent, Time-Aware Codebase Memory for Claude Code Agents
Memtrace provides always-fresh snapshots and bi-temporal replay for Claude Code agents, using Tree-sitter AST parsing and hybrid retrieval (BM25 + Jina-code embeddings) with zero LLM inference cost during indexing.

Prism MCP v5.1 adds 10x memory compression and agent learning from corrections
Prism MCP v5.1 introduces 10x memory compression via TurboQuant ported to TypeScript, enabling millions of memories on a laptop without vector databases. The update adds agent learning from user corrections and a visual knowledge graph interface.