https://github.com/abians/code-recall
Ultra-fast MCP server for semantic memory and code analysis
https://github.com/abians/code-recall
ai coding-agents mcp memory semantic-search
Last synced: 8 days ago
JSON representation
Ultra-fast MCP server for semantic memory and code analysis
- Host: GitHub
- URL: https://github.com/abians/code-recall
- Owner: AbianS
- License: mit
- Created: 2026-01-13T21:44:20.000Z (23 days ago)
- Default Branch: main
- Last Pushed: 2026-01-13T23:29:36.000Z (23 days ago)
- Last Synced: 2026-01-13T23:58:53.222Z (23 days ago)
- Topics: ai, coding-agents, mcp, memory, semantic-search
- Language: TypeScript
- Homepage: https://www.npmjs.com/package/code-recall
- Size: 91.8 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
**Semantic memory for AI coding agents**
Give your AI assistant persistent memory that learns from your project's history.
[](https://opensource.org/licenses/MIT)
[](https://bun.sh)
[](https://modelcontextprotocol.io)
---
## Packages
This monorepo contains two independent packages:
### [`code-recall`](./apps/server) - MCP Server
[](https://www.npmjs.com/package/code-recall)
The core MCP server that gives AI agents persistent, semantic memory. It stores observations, decisions, and learnings in a local SQLite database with vector search, full-text search, and a rules engine.
```bash
bun install -g code-recall
```
```bash
claude mcp add code-recall -- bunx code-recall
```
### [`code-recall-tui`](./apps/tui) - Terminal UI
[](https://www.npmjs.com/package/code-recall-tui)
A terminal UI for browsing and exploring your code-recall database. View memories, rules, code entities, and search through everything your AI agent has learned.
```bash
bun install -g code-recall-tui
```
```bash
code-recall-tui
```
---
## Quick Start
1. **Install the MCP server** and add it to your AI coding agent
2. **Start coding** -- the agent will automatically store decisions, patterns, warnings, and learnings
3. **Browse your data** with the TUI to see what your agent has learned
All data stays local on your machine. No cloud, no telemetry, fully private.
---
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
## License
MIT License - see [LICENSE](LICENSE) for details.