CoreCoder
Self-hosted ai agents: minimal ai coding agent (~1,000 lines of python) inspir.
GBrain is an open-source ai agents project by garrytan (garrytan/gbrain on GitHub). It has 31,948 GitHub stars and 4,759 forks, is released under the MIT license, and was last updated on GitHub on 9 November 2026.
Garry Tan's agent memory — a self-hosted brain your agents share, with sourced facts, corrections and synthesis, MIT
GBrain needs Bun 1.4.4 or newer; skip this if you already have it.
Install from GitHub — never from npm, where the gbrain package is an unrelated project.
Run the setup for your harness (Claude Code or Codex shown); it writes a brain-first block into the agent’s instruction file, wires MCP and smoke-tests the connection.
Explicit facts carry their sources, and you can correct or withdraw them — memory you control, not a black box.
Answers written as cited prose, with an explicit note on what the brain does not know yet.
People, companies and deals linked as a graph; relationship retrieval measurably improves recall.
The same memory serves OpenClaw, Claude Code, Codex, Grok Bot, Muse, ChatGPT and Cursor.
A daemon ingests meetings, emails, tweets and calls, enriches people and companies, and consolidates memory overnight.
Begin with keyless memory and keyword retrieval; cloud embedding and synthesis providers are opt-in.
Check Bun 1.4.4 or newer is installed; install it from the Bun website first if it is missing.
bun --versionClone the stable branch, then install and link the CLI with Bun.
git clone --branch stable https://github.com/garrytan/gbrain.git && cd gbrain && bun install && bun linkWire the brain into Claude Code (or use gbrain setup codex for Codex).
gbrain setup claude-codeFor comparison, the same shelf also holds CoreCoder — Self-hosted ai agents and pentagi — Autonomous AI agents for penetration testing. The complete list is the AI Agents shelf. Before running a model locally, check how much VRAM you need for local LLMs — model size has to match your hardware.
Yes — MIT licensed and free to self-host. gbrain.io is optional paid hosting; your own model and API usage are separate costs.
Claude Code, Codex, OpenClaw, Hermes, Grok Bot, Muse, ChatGPT and Cursor, via MCP and per-harness setup guides.
Bun 1.4.4 or newer, plus your own compute and model API configuration for always-on enrichment.
It runs on your hardware, your database and your keys. Configured cloud embedding, reranking and synthesis providers can receive text — read the memory-boundaries guide before sharing a brain.
That package is unrelated and can shadow the real binary. Install only from the GitHub repo via the Bun route above.
Self-hosted ai agents: minimal ai coding agent (~1,000 lines of python) inspir.
Autonomous AI agents for penetration testing — self-hosted, multi-agent, with a full web UI
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat…
Your self-hostable AI second brain for answers, agents, and automations.
Self hosted, live digital human agent system.
Agent-native memory infrastructure - structured, persistent memory for production agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if GBrain is not the right fit.
A personal AI that really does things — on any OS, with your data staying yours.
Matt Pocock's engineering skills for coding agents — grill the spec first, then build it right, MIT
An agentic skills framework & software development methodology that works.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
The agent that grows with you — a Python framework for adaptive AI agents.
Nearby AI Agents projects in the catalogue, closest in stars to GBrain — keep exploring the shelf either side of it.
Build and run agents you can see, understand and trust — framework plus a visual agent service
Open-source AI memory that gives agents persistent long-term recall.
GitHub's official MCP server — let AI tools work with repos, issues and pull requests
Real-time knowledge graphs that give agents a memory with structure.
A Claude Code-style coding agent that runs anywhere and works with almost any model provider
The memory API that gives AI apps instant, lasting context.
Free and open — grab the source, star the repo, and start creating.