agentmako
Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.
agentmako is a local-first codebase intelligence engine for AI coding tools. It provides a typed MCP toolset for understanding a project before editing, indexing repos, building SQLite-backed facts, tracking diagnostics and review notes, and returning structured context packets. It aims to help agents answer questions like 'What files matter? What routes, symbols, tables, diagnostics, and prior findings are relevant?'
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- MMorgan ChenMay 1, 2026
Good for teams that want better agent performance without cloud data exposure
- FFinley JacksonMar 29, 2026
Used for large codebase navigation with coding agents, the structured context improves accuracy
- LLogan AndersonMar 24, 2026
Structured context packets for coding agents address the unstructured context problem
- KKai LewisMar 22, 2026
The local-first architecture means sensitive codebases stay on-premises