Latent-k
Maps codebase structure and file relationships, automatically injecting context into AI coding sessions to reduce token usage and improve response speed.
A developer tool that maps codebase structure and file relationships, automatically injecting context into AI coding sessions to reduce token usage and improve response speed. It targets software developers and engineering teams using AI coding assistants like Claude Code and Gemini CLI. The tool is delivered as a local CLI binary with hooks and MCP tools, processing data locally without sending it to the cloud.
Key features
- Tracks imports, exports, and file relationships
- Context-aware file reading with imports and dependents
- YAML audit testing for business rules
- Automatic context injection via hooks
- MCP tools for Claude Code
- Local processing, no data leaves machine
Social posts
- No social media activity detected
GTM channels
- Docs
ICP
- Software developers
- Engineering teams
- Startups