LibreAI / AI Agents / agent-beacon
// agents · Asymptote-Labs/agent-beacon

agent-beacon

agent-beacon is an open-source ai agents project by Asymptote-Labs (Asymptote-Labs/agent-beacon on GitHub). It has 1,761 GitHub stars and 156 forks, is released under the MIT license, and was last updated on GitHub on 3 October 2026.

Self-improving memory layer that works across AI agent harnesses.

💎 Hidden gem★ 1.8k stars⑂ 156 forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

GitHub stars
1,761
Forks
156
License
MIT
Last updated on GitHub
3 October 2026
Category
AI Agents
Listing
Hidden gem — a shorter page for a lesser-known project
Official site
Official site
// how it works

How it works

  1. Clone the repository

    Download the source and enter the folder.

  2. Build the beacon

    Compile the Go service.

  3. Connect your harness

    Point Claude Code, Codex, or Cursor at it.

  4. Let memory accumulate

    Agents store and recall learnings across sessions.

// features

Why people love it

Cross-harness memory

One memory layer for Claude Code, Codex, Cursor, and more.

Self-improving

Memory quality grows as agents use it.

Agent security

Detection engineering for agent tooling.

Browser extension

Capture context from the browser too.

CI integration

Memory-aware checks in your pipelines.

Go service

Fast backend for memory operations.

Advertisement
// run it

Run it yourself

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/Asymptote-Labs/agent-beacon.git
    cd agent-beacon
  2. Step 2 — Build the service

    Compile the Go binary.

    go build ./...
  3. Step 3 — Start the beacon

    Launch the memory service.

    ./agent-beacon
// use cases

What you can build

  • Share learnings between Claude Code and Codex sessions.
  • Give agents persistent memory across restarts.
  • Detect anomalous agent behavior in CI.
  • Build a team-wide agent knowledge layer.
Advertisement
// faq

Questions, answered

Who maintains agent-beacon?

It is an open-source project at Asymptote-Labs/agent-beacon with 156 forks.

Is it free for commercial use?

Yes. It is MIT licensed.

Which harnesses are supported?

Claude Code, Codex, Cursor, and other agent harnesses via its integrations.

What does self-improving mean here?

The memory layer refines what it stores as it observes more agent activity.

Is there a cloud component?

The project lists cloud support alongside self-hosting — check the README.

// keep exploring

Similar tools

AI Agents

MemoryOS

A memory operating system for long-term, personalized AI agents.

★ 1.6k starsApache-2.0
View guide →
RAG & Knowledge

wenlan

Agent-fed knowledge base that distills learnings into cited wiki pages.

★ 79 starsApache-2.0
View guide →
Dev Tools

agent-manager

A tmux TUI for managing AI coding agents — status, prompts, worktrees, diffs.

★ 564 starsApache-2.0
View guide →
AI Agents

EverOS

One portable, local-first memory layer for every AI agent - Markdown-native, user-owned and self-evolving.

★ 13.4k starsApache-2.0
View guide →
AI Agents

PhyAgentOS-core

Recursive self-improving physical agent OS — verified, evidence-based execution for robots and simulators

★ 2.8k starsMIT
View guide →
AI Agents

agent-qa

A self-improving QA agent that writes tests in plain English.

★ 902 starsNOASSERTION
View guide →
// alternatives

Alternatives in AI Agents

The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if agent-beacon is not the right fit.

  • openclaw★ 391.6k

    A personal AI that really does things — on any OS, with your data staying yours.

  • superpowers★ 294.9k

    An agentic skills framework & software development methodology that works.

  • ECC★ 275.2k

    Agent harness optimization system with skills, memory and security for Claude Code, Codex and more

  • hermes-agent★ 252.0k

    The agent that grows with you — a Python framework for adaptive AI agents.

  • deepseek-harness★ 245.5k

    DeepSeek's plugin-based agent harness where everything is a plugin.

// more in agents

More in AI Agents

Nearby AI Agents projects in the catalogue, closest in stars to agent-beacon — keep exploring the shelf either side of it.

  • AgentDock★ 1.8k

    Retired agent framework: its prompts and guides live on in successor repos.

  • mex★ 1.8k

    Team memory for engineers and their AI agents.

  • agent-desktop★ 1.8k

    Reliable computer use for any agent: drive real apps through accessibility trees, not pixel guessing.

  • iwe★ 1.7k

    A markdown knowledge graph with LSP for editors and MCP for agents.

  • dmux★ 1.8k

    Dev agent multiplexer designed for git worktrees and coding agents.

  • context-engineering-kit★ 1.7k

    Run context-engineering-kit locally: hand-crafted claude code skills focused on improvi...

Get agent-beacon

Free and open — grab the source, star the repo, and start creating.