Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
| Date | Stars |
|---|---|
| 2026-07-24 | 279 |
| 2026-07-25 | 280 |
| 2026-07-28 | 280 |
| 2026-07-30 | 280 |
| 2026-07-31 | 283 |
| 2026-08-06 | 283 |
Today
— stars today
This week
+3 stars this week
This month
— stars this month
Momentum
18.8
growth rate 1.07%/day
<!-- mcp-name: io.github.oleksiijko/pmb-ai --> <div align="center"> <img src="https://raw.githubusercontent.com/oleksiijko/pmb/main/docs/assets/logo.png" width="100" alt="PMB logo"> # PMB ### Local-first memory for your AI coding agent. ### SQLite is the source of truth. No cloud, no API keys, no re-explaining. [](https://pmbai.dev) [](https://pypi.org/project/pmb-ai/) [](https://github.com/oleksiijko/pmb/actions/workflows/ci.yml) [](https://docs.pmbai.dev) [](https://pypi.org/project/pmb-ai/) [](LICENSE) [](https://modelcontextprotocol.io) [](https://github.com/mcp/oleksiijko/pmb-ai) <img src="https://raw.githubusercontent.com/oleksiijko/pmb/main/docs/assets/dashboard-map.png" width="760" alt="PMB dashboard - your project's memory as a live entity graph"> *Local-first memory, visualized. 3,800+ entities and 41,000+ connections, captured automatically as you work.* [**Website**](https://pmbai.dev) · [**Docs**](https://docs.pmbai.dev) · [Quickstart](#quickstart) · [Demo](#demo) · [Why PMB](#why-pmb) · [How it works](#how-it-works) · [FAQ](#faq) **Your AI agent forgets everything between sessions.** So you re-explain the same decisions, lessons and constraints over and over. PMB remembers them in one local workspace and feeds them back through MCP - no cloud, no API keys, no LLM call on the read path. And it tells you **when memory is actually helping**, instead of claiming "+X%". ⭐ **Star the repo if PMB saves you a re-explanation.** </div> --- PMB gives Claude Code, Cursor, Codex and the other MCP-aware agents a real memory: decisions you made last week, lessons you taught them, personal facts, project structure, PDFs. They survive every restart, every model upgrade, every agent switch - because they live in a **local workspace you own**, with SQLite as the durable source of truth and rebuildable search indexes beside it. No API keys. No subscription. No LLM call on the read path. Just local files. ## Quickstart ```bash pip install pmb-ai # 1. install pmb setup # 2. detect your agent + wire the MCP entry pmb warmup # 3. preload the model (first recall is instant) # 4. restart your agent, then just talk to it - memory is automatic pmb stats # 5. see what's stored pmb recall "auth decision" # 6. search memory from the terminal pmb doctor # 7. confirm everything is wired ``` That's it - your agent now remembers. No account, no keys, nothing leaves your machine. > **Command name:** the CLI is **`pmb`**. Via `pip` you also get the alias > **`pmb-ai`**; via `npm` (`npx pmb-ai setup`) the command is `pmb-ai` and it > installs the Python package first, then runs setup. Same tool - use whichever > your install gave you. > **Links:** [pmbai.dev](https://pmbai.dev) (site) · > [docs.pmbai.dev](https://docs.pmbai.dev) (docs) · > [Getting started](docs/guide/getting-started.md) · > [Deleting memories](docs/guide/deleting-memories.md). --- ## Demo *What it feels like - same prompt, with and without memory:* <div align="center"> <a href="https://github.com/oleksiijko/pmb/raw/main/docs/assets/pmb-setup.mp4"><img src="https://raw.githubusercontent.com/oleksiijko/pmb/main/docs/assets/pmb-setup-poster.png" width="820" alt="Watch the 2-minute PMB setup"></a> <sub>▶ Click to play the 2-minute setup</sub> <img src="https://raw.githubuser
Excerpt of 21,926 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:787bfab90215008f, topic:rag, topic:knowledge-graph, topic:memory
matched fp:787bfab90215008f, topic:vector-search, topic:semantic-search
matched fp:787bfab90215008f, topic:mcp, topic:model-context-protocol