# garrytan/gbrain

> A personal and company memory layer for AI agents: stores facts with sources, supports corrections and sharing across agents, and adds semantic search, answer synthesis, and a knowledge graph. Runs as a local daemon with background enrichment and memory consolidation.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 30,617 total · +1 star measured 2026-10-07, 11:05–12:46 UTC, ≈ 8 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-04-05 · Last push: 2026-10-07
- GitHub: https://github.com/garrytan/gbrain · Page: https://gitnova.dev/en/r/garrytan/gbrain

## Useful for

- Attach GBrain to an existing agent (Claude Code, Codex) to persist memory across sessions
- Expose your knowledge base over MCP via Tailscale to query it from any device
- Ask about a person or company and get a synthesized answer with source citations

## Why it’s here

- Star-counter measurements on 2026-10-07 (UTC), 11:05–12:46: 30616 → 30617 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +8 stars, using observed gains and the previous day.
- GitHub Trending TypeScript today: #7, +40 stars.
- About 6 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 4,595
- Issues and pull requests: 6,243
- Watchers: 140
- Average over the last week: 28 per day
- Usual pace: 36 per day
- Stars in the last hour (measured): 5
- Latest release: v0.60.102.0 (2026-10-07)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-08 … 2026-10-07: 45, 36, 32, 34, 25, 36, 39, 44, 52, 48, 52, 42, 33, 35, 38, 38, 32, 27, 24, 39, 32, 26, 27, 28, 30, 20, 47, 27, 32, 1

## Spotted in now

- GitHub Trending TypeScript today: #7, +40 stars

## Similar by description

1. **mem0ai/mem0** — 3.1 · Steady · AI agents · Python · +67 stars measured 2026-10-07, 00:22–12:41 UTC, ≈ 118 by evening
   A long-term memory layer for AI agents and apps: stores user preferences, session state and facts so assistants keep context across conversations. Available as a Python/JS library, self-hosted server and cloud service.
   Full card: https://gitnova.dev/en/r/mem0ai/mem0.md
2. **deeplethe/utopia** — 2.6 · Steady · Language models · Rust · +14 stars measured 2026-10-07, 00:22–12:43 UTC, ≈ 30 by evening
   Utopia is an open-source enterprise knowledge platform: a bitemporal knowledge graph, RAG search and agent workflows on a single Rust binary plus PostgreSQL. It deploys offline, for companies that need a controlled knowledge foundation…
   Full card: https://gitnova.dev/en/r/deeplethe/utopia.md
3. **vectorize-io/hindsight** — 3.6 · Cooling · AI agents · Python · +240 stars measured 2026-10-07, 00:21–12:40 UTC, ≈ 434 by evening
   Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server (Docker, pip, Helm) or…
   Full card: https://gitnova.dev/en/r/vectorize-io/hindsight.md
4. **VictorTaelin/OptMem** — 2.8 · Peaking · AI agents · Python · +17 stars measured 2026-10-07, 00:21–12:43 UTC, ≈ 36 by evening
   Permanent memory tool for AI agents: a single Python script plus a 426-token prompt pasted into AGENTS.md or CLAUDE.md. The agent records notes with memo note and reads them at session start via memo wake.
   Full card: https://gitnova.dev/en/r/VictorTaelin/OptMem.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-07 12:58 UTC, updated every 30 minutes.