Why Beacon
Agent history is fragmented across tools. Prompts, tool calls, commands, file edits, and model interactions are often trapped inside individual harnesses and session formats. Beacon normalizes that activity into one consistent record across agents. That shared history makes it easier to:- debug failed workflows
- understand how agents are being used
- analyze runtime behavior
- compare activity across harnesses
- surface recurring workflows and corrections
- turn past agent runs into reusable knowledge
From traces to shared knowledge
Every agent session contains useful context: debugging paths, repository conventions, repeated corrections, commands, and tool sequences. Beacon captures that history so it can be reused across future runs and across different harnesses. Every run adds to the knowledge base.Beacon
Beacon is built on theagent-beacon repository.
Quickstart
Choose the right setup path for a managed rollout or local developer evaluation.
Open Source Architecture
Learn how Beacon collects, normalizes, stores, correlates, and detects telemetry across every supported surface.
Local testing
Validate endpoint health, events, dashboard access, MCP access, and logs.
Agent harness integrations
See supported agent harnesses, deployment modes, destinations, and boundaries.
Endpoint event schema
Review Beacon JSONL fields, normalization behavior, and example events.
Security & IT Rollout Guide
Plan endpoint inventory, MDM rollout, retention policy, validation, and log forwarding.
Related
Beacon
Install the open-source CLI and configure Agent Beacon telemetry.
Beacon Managed
Review managed visibility, investigations, and rollout support.
Hosting Options
Compare the open-source local path with managed and enterprise deployment options.
Pricing
See plan positioning for open-source, managed enterprise, and private deployment.