Nayshins/ummon
The semantic layer for software engineering: Connect code to meaning, build on understanding
This project helps software developers and architects better understand complex codebases by building a "knowledge graph" of their code. It takes your existing source code in languages like Python, Java, or Rust and creates a map of functions, classes, and how they relate. This map helps you quickly find relevant code, understand system architecture, and even suggests files for specific tasks like fixing a bug.
No commits in the last 6 months.
Use this if you need to quickly understand a large, unfamiliar codebase, find specific code sections related to a business concept, or get AI-powered suggestions for files relevant to a development task.
Not ideal if you are working on a very small project with simple code, or if you primarily need tools for coding style enforcement or dependency management rather than semantic understanding.
Stars
37
Forks
5
Language
Rust
License
Apache-2.0
Category
Last pushed
Apr 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Nayshins/ummon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bgauryy/octocode-mcp
MCP server for semantic code research and context generation on real-time using LLM patterns |...
DeusData/codebase-memory-mcp
MCP server that indexes your codebase into a persistent knowledge graph. 64 languages, sub-ms...
Azure-Samples/snippy
🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search....
aimasteracc/tree-sitter-analyzer
A scalable, multi-language code analysis framework based on Tree-sitter, usable both as a CLI...
wrale/mcp-server-tree-sitter
MCP Server for Tree-sitter