11st of 13 in Memory
gbrain
Long-term memory store for coding agents, with sources and corrections
- Stars
- 30.9k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
104 on 8 Apr 202630,881 on 14 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
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)
Head to head
Also in Memory
See all 13| Rank | Project | Score |
|---|---|---|
| 2 | hindsightAgent memory server with retain, recall and reflect operations | 78 out of 100 |
| 3 | MemPalaceLocal long-term memory store for agents with verbatim storage and semantic search | 77 out of 100 |
| #4 | CogneeMemory engine that turns documents and code into a knowledge graph | 76 out of 100 |
| #5 | OpenVikingContext database that stores agent memory, resources and skills as a virtual filesystem | 74 out of 100 |
| #6 | Mem0Memory layer for agents with a self-hosted server, SDKs and CLI | 72 out of 100 |