| name | knowledge_graph |
| display_name | Knowledge Graph Specialist |
| description | Code knowledge graphs and Graph RAG — entity extraction, relationship mapping, and natural-language queries over source repositories |
| version | 0.1.0 |
| source_repo | abhigyanpatwari/GitNexus |
| license | MIT |
| tier | core |
| capabilities | ["knowledge_graph","code_analysis","entity_linking","graph_rag"] |
| allowed_tools | ["build_graph","query_graph","find_relationships"] |
| output_formats | ["python_api","cli","mcp_server","agent_skill","rest_api"] |
Knowledge Graph Specialist
Overview
knowledge_graph wraps patterns from
abhigyanpatwari/GitNexus for code
entity extraction and graph construction, and
topoteretes/cognee for Graph RAG retrieval.
Given a source artifact — repository URL, file path, or raw code — the specialist
builds a directed knowledge graph of entities and relationships, then answers
natural-language questions through graph traversal. Results are returned as ranked
entity lists, relevance scores, and explicit relationship paths, ready for downstream
reasoning or citation.
The specialist is stateless. Each :meth:execute call builds a fresh graph and
returns a self-contained result dict. Graph IDs can be passed across calls to query
a previously built graph without rebuilding.
Capabilities
- knowledge_graph: Build a structured entity/relationship graph from code or
documents, scoped by traversal depth and entity type.
- code_analysis: Extract modules, classes, functions, variables, and imports from
source repositories, surfacing dependency and call-graph structure.
- entity_linking: Resolve named entities across files and modules into a unified
graph, deduplicating references by stable entity ID.
- graph_rag: Answer natural-language queries via graph traversal and relevance
ranking — Graph Retrieval-Augmented Generation over structured code knowledge.
Tools
| Tool | Description | Side Effects |
|---|
build_graph | Build a knowledge graph from a source artifact | None (v1 local; future: network/disk) |
query_graph | Query the graph with natural language; returns ranked entities and paths | None |
find_relationships | Find all paths between two named entities; returns types and strength | None |
Parameters
Request-level (intent.parameters)
| Key | Type | Default | Description |
|---|
source | str | |
