Skip to content
repository radar
RAG & Memory
Understory of the Month Sep 2025 · +36

🧩cognee

ACTIVE BREAKOUT

topoteretes/cognee · homepage ↗

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

⭐ Very popular: 30k stars, gaining about 415 a week

View on GitHub ↗

repo profile

vintage 2023 3 years old
delivery product
language Python
license Apache-2.0

momentum

total stars 30k
stars added last week +415
weekly downloads 67k /wk · PyPI
used by 145 repos & packages
commits / week 140 steady · +22% vs prior mo
issues closed 83% ~27d to close, median
contributors 279 (+48 in 15d)
release cadence weekly
last activity today

durability

backing VC-backed Cognee (Pebblebed, 42CAP)
openness permissive
security score 5.3/10 OpenSSF Scorecard · 2026-08-11
bus factor 2 concentrated
top-author share 26% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 2k/mo (+33%/mo) · + 25k total since PR#10

why it's a big deal

  • It unifies vector search and graph databases into a single memory layer, so documents are both searchable by meaning and connected by relationships - not one or the other.
  • Graduated from GitHub’s Secure Open Source Program, which matters when you’re building the memory layer that production AI systems depend on.
  • Ships an MCP server out of the box, which means any MCP-compatible agent (Claude Code, OpenClaw, Cursor) can use cognee as its memory backend without custom integration work.

under the hood

  • Python framework with modular pipelines: add data, cognify it (extract entities, build graphs, generate embeddings), then search across the resulting knowledge structure.
  • Supports Neo4j, Kuzu, and NetworkX for graph storage and PostgreSQL, Qdrant, or Weaviate for vectors - swap backends without changing application code.
  • CLI, FastAPI server, and a Next.js frontend for browsing the knowledge graph visually, plus full Docker support for self-hosted deployment.

our take from PR#27, 2026-02-11

star history

PR#10 · 5k PR#27 · 12k30k now Aug 2023Aug 2026
  1. PR#10 5k 2025-06-11
  2. PR#27 12k 2026-02-11
  3. now 30k + 25k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Quietly building: more output than attention, for now.

+18 understory score output 100 · clout 82
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#27 2026-02-11 on the radar

    Memory infrastructure for AI agents

  • PR#10 2025-06-11 below the radar

    Visual memory for local AI assistants

similar projects

compare these →
  • 📑 PageIndex

    📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

    35k ACTIVE
  • 🧠 Memori

    leaner, 16k stars

    Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

    16k ACTIVE
  • 🥥 CocoIndex

    Rust · leaner, 11k stars

    Incremental engine for long horizon agents 🌟 Star if you like it!

    11k ACTIVE

comments

Sign in with GitHub to add your blip on cognee.

loading comments…