#44th of 18 in Memory
gbrain
Long-term memory store for coding agents, with sources and corrections
- Stars
- 31.1k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
3,141 on 10 Apr 202631,140 on 23 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
GBrain keeps explicit facts and their sources in a local PGLite or Postgres brain and exposes them to agents such as Claude Code, Codex, Cursor and Hermes over stdio or HTTP MCP. It starts keyless with keyword search; semantic search, cited synthesis, a typed knowledge graph and an overnight enrichment cycle are optional. It is installed with Bun from GitHub, not npm.
Who it is for: Developers giving Claude Code, Codex or other agents persistent shared memory
Ranked among open-source alternatives to Mem (#4 of 10).
Strengths
- Keyless start: PGLite brain with keyword search, no server or Docker needed
- One brain shared across agents via stdio MCP or HTTP MCP with scoped OAuth tokens
- One-command setup for Claude Code and Codex, with dry-run and remove options
- Optional cited synthesis that notes gaps, plus a typed graph for relationship queries
Weaknesses
- Not on npm; the unrelated npm package named gbrain can shadow the real binary
- Always-on OpenClaw/Hermes setup needs a server with 8GB+ RAM plus paid API usage
- Local files and shared database credentials are not isolated by sources
- Remote put_page does not extract graph edges inline; HTTP needs explicit maintenance
What it needs
- RAM ≥ 8 GB
- no GPU
- Compose
- Needs Bun 1.4.0+, PGLite or Postgres, Tailscale (optional, for remote MCP)
- Models: Optional cloud embedding, reranking, extraction and synthesis providers (unspecified)
Quick answers
Is gbrain open source?
Yes. Its code is on GitHub under the MIT license.
Can you run gbrain with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does gbrain need a GPU?
No, it runs without one. Plan for at least 8 GB of RAM.
Head to head
Also in Memory
See all 18| Rank | Project | Score |
|---|---|---|
| 1 | hindsightAgent memory server with retain, recall and reflect operations | 94 out of 100 |
| 2 | MemPalaceLocal verbatim memory store for AI agents with semantic search and MCP | 90 out of 100 |
| 3 | Mem0Long-term memory layer that stores and retrieves user facts for LLM agents | 89 out of 100 |
| #5 | CogneeMemory engine that turns documents and code into a knowledge graph | 85 out of 100 |
| #6 | GraphitiPython framework for temporal knowledge graphs that track how facts change | 84 out of 100 |