Beacon: open-source cross-harness memory for AI agents, hooks into 20+ harnesses
shakshukan · hn · 2026-10-21
A developer launched Beacon (Asymptote-Labs/agent-beacon) on HN, solving the pain of re-explaining tasks, workflows and common mistake patterns every time you switch coding agents like Claude Code, Codex or Cursor.
How it works:
- Hooks into 20+ agent harnesses, capturing session telemetry (prompts, tool calls, command executions) in one normalized format
- Distills telemetry into common patterns and repeatable workflows with a human-approval step
- Compounded knowledge is exposed to any future agent via skills / MCP
The authors stress data ownership: your agent data shouldn't be locked behind any frontier lab's closed memory infrastructure.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23