The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
Go agent-ai-cliagent-harnessesagent-securitybrowser-extensionciclaude-codecloudcodexcursordetection-engineeringjevknowledge-basememorymobile-device-managementobservabilitysecuritysecurity-information-and-event-managementsecurity-toolstelemetrytraces
Merge remote-tracking branch 'origin/main' into claude/architecture-docs-update-o46auk
Claudeea5bb0408a05
diff --cc README.mdindex 64c2190c,e459717b..8dd79dd0--- a/README.md+++ b/README.md@@@ -51,26 -51,26 +51,31 @@@ Learn more in the [Agent Beacon documen## High-Level Architecture+ Beacon captures activity where each agent actually runs, then normalizes it into a+ single OpenTelemetry-based event model.+<p align="center">- <img src="images/beacon-architecture.png" alt="Beacon endpoint architecture" width="860">+ <img src="images/beacon-architecture.png" alt="Agent Beacon architecture: local agents, browser, agents in code, CI pipelines, and cloud agents feed a Beacon layer that collects, normalizes, stores, correlates, and detects, then forwards unified AI telemetry to customer-owned destinations" width="860"></p>-- **Agent runtime layer** — hooks, OpenTelemetry sources, CI wrappers, SDKs, and an- optional browser extension capture supported agent activity.-- **Beacon processing layer** — normalizes events, applies retention and redaction- settings, and writes durable telemetry.-- **Output layer** — inspect events in the local dashboard, retain JSONL, or forward- records into the [major enterprise-grade SIEMs](#output-destinations).+- **Sources** — [local agents](#local-agents) through hooks, plugins, and local+ OpenTelemetry; [browser chat](#browser-chat) through an optional extension;+ agents in code through the [TypeScript SDK](#cloud-agents);+ [CI pipelines](#ci-agents) through a temporary collector; and+ [cloud agents](#cloud-agents) through sandbox hooks.+- **Beacon** — collect, normalize, store, correlate, and detect. Every surface lands+ in one event model, one durable JSONL log, one session timeline, and one+ [local detection engine](#dashboard-and-local-detection).+- **Destinations** — inspect events in the local dashboard, retain JSONL, or forward+ the same stream into the [major enterprise-grade SIEMs](#output-destinations),+ log aggregators, and object storage.Collection, processing, and inspection stay local by default; the same normalized- event model extends to CI, cloud-agent, and SDK paths under customer control.- See the [architecture docs](https://docs.asymptotelabs.ai/architecture/architecture)- for the full breakdown by surface.-event model extends to CI and cloud-agent paths under customer control. See the++event model extends to CI, cloud-agent, and SDK paths under customer control. See the+ [open-source architecture reference](https://docs.asymptotelabs.ai/architecture/architecture)-for the full collection, normalization, storage, and forwarding pipeline, or the++for the full breakdown by surface, or the+ [system architecture overview](https://docs.asymptotelabs.ai/architecture/system-architecture)+ to compare it with the managed path.## Supported Surfaces