EtienneChollet/ontomics

Overview

Ontomics extracts domain knowledge from codebases by analyzing concepts, naming conventions, and vocabulary, then makes them queryable via MCP. It reduces LLM token consumption by 20x and agentic search time by 10x by providing a structured ontology instead of raw code.

Best for

Best for
Developers working with large codebases who want to reduce LLM costs and speed up agentic search

Use cases

• Pre-process a codebase to build a queryable ontology for LLM-assisted development
• Reduce token costs when using LLMs to understand or refactor large codebases
• Speed up agentic code search by replacing raw code scans with ontology lookups

Notes

Ontomics extracts domain knowledge from codebases by analyzing concepts, naming conventions, and vocabulary, then makes them queryable via MCP. It reduces LLM token consumption by 20x and agentic search time by 10x by providing a structured ontology instead of raw code.

35 stars on GitHub. Last updated 2026-04-17. Licensed MIT.

Use cases

• Pre-process a codebase to build a queryable ontology for LLM-assisted development
• Reduce token costs when using LLMs to understand or refactor large codebases
• Speed up agentic code search by replacing raw code scans with ontology lookups

Pros

• Written in Rust for performance and safety
• Delivers measurable reductions in token usage and search time
• Exposes domain knowledge via MCP for easy integration with LLM tools

Cons

• Limited community adoption with only 35 GitHub stars
• Requires initial setup and understanding of MCP protocol
• Effectiveness depends on codebase structure and naming consistency

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.