ontogr /
agentic-graphrag
Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have and the decisions they make. Each decision links back to the passages and task events behind it, so agents can look up earlier decisions with their evidence…
Updated 57 min ago
+1 stars gained this week
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
It is aimed at teams building agents that need to recall past decisions with their sources. It runs on Python with a Neo4j graph database, and is used through an MCP server, an API, or a built-in agent.
Summary written by AI from the repository’s description and README.
What this repo contains
- Executables and archives
- 4 in the repo benchmarks/results/lite/20261001T190456Z-financial-lite-agrag-64a581/trace.jsonl.gz, benchmarks/results/lite/20261002T051945Z-memory-lite-agrag-8fc229/trace.jsonl.gz, benchmarks/results/lite/20261002T053553Z-legal-lite-agrag-d98fa8/trace.jsonl.gz, benchmarks/results/lite/20261002T055455Z-healthcare-lite-agrag-26def6/trace.jsonl.gz
- Skills
- 6 SKILL.md files
- Files for
- Claude Code, Codex
- Its README
- Asks you to install software (npm -g, pip, brew…)Asks for an API key or a token
No scripts, hook files or MCP settings.
Read from the repository's files and README: facts to check on GitHub, not a review.
ontogr / agentic-graphrag
View on GitHub(opens in new tab)