Open sourcePython · ≈33k stars · Apache-2.0
cognee
Memory as a knowledge pipeline for AI agents.
cognee turns documents, conversations and APIs into knowledge graphs and vector stores that agents can query — an open-source 'memory engine' positioned between RAG and long-term memory.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsBuilds a knowledge-graph memory from docs, code, tickets and conversations, with custom data models and ontologies.[1]
- DocsCan import memory from Mem0, Letta, Zep or Graphiti via the COGX format, which lowers switching cost.[1]
- DocsRuns fully local with Ollama (including embeddings), plus Docker Compose and distributed deployment templates.[1]
- MetadataApache-2.0, active (v1.6.x), about 33k stars, with recent Google Drive/Gmail connectors.[1]
Cons
- User reportsHandling facts that change over time was still being built when the founder was asked about it on HN.[1][2]
- DocsBenchmark claims (about 90% on industry benchmarks) come from the vendor's own paper.[1]
- MetadataIts most-commented issues are hackathon connector bounties, which bury bug signal among about 760 open issues.[1][2]
- Best for
- Agents and teams that want a graph-structured 'company brain' memory they can run locally and migrate into.
- Watch out for
- Graph-quality tuning; test on your own data before trusting the benchmarks.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
Activity
- Last push
- · yesterday
- Latest release
- v1.6.10
· 3d ago - Last 90 days
- 18 releases
v1.6.10v1.6.10 Reliability & Observability Improvements
· 3d agov1.6.10 Reliability & Observability Improvements Release Date: 2026-11-18 Changes: v1.6.9 → v1.6.10 Pull Requests: #6744 --- Summary This release focuses on making Cognee more reliable and easier to debug: Postgres connection pools are tightened to reduce runaway connections…
v1.6.9v1.6.9 — New Connectors & Integrations
· 3d agov1.6.9 — New Connectors & Integrations Release Date: 2026-11-18 Changes: v1.6.8 → v1.6.9 Pull Requests: #6639, #6644, #6739, #6742 --- Summary This release focuses on expanding integrations and stabilizing ingestion and embedding behavior. We added multiple new connectors…
v1.6.8v1.6.8 Integrations & Connectors
· 9d agov1.6.8 Integrations & Connectors Release Date: 2026-11-12 Changes: v1.6.7 → v1.6.8 Pull Requests: #5189, #6410, #6417, #6593, #6612, #6634, #6642 --- Summary This release focuses on expanding and hardening integrations (new Slack support and many connector improvements) and…
- · 2w ago
v1.6.7 Release Date: 2026-11-06 Changes: v1.6.6rc1 → v1.6.7 Pull Requests: #6266, #6337, #6338, #6339, #6340, #6342, #6392, #6404, #6493, #6512, #6540, #6546, #6550, #6564 --- Summary This release tightens ingestion safety and improves how search and retrieval behave and…
v1.6.6v1.6.6 — Conflict resolution & stability
· 3w agov1.6.6 — Conflict resolution & stability Release Date: 2026-10-29 Changes: v1.6.6rc1 → v1.6.6 Pull Requests: #6266, #6337, #6339, #6340 --- Summary This release focuses on making conflict handling more reliable and easier to manage, plus a handful of stability, vector, and…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
In research (2)
- Jetriever: Shifting Agent Memory Retrieval from Similarity to UtilityVerdict: Incremental
Nov 16, 2026 · Listed in the reproduced MAB baseline table (20.6 overall, Table 7) as a structure-augmented memory system.
Oct 23, 2026 · Cognee's graph memory is a baseline in Table 1 (23.7 average).
Neighbours on the workbench
JavaScript · ≈308k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
TypeScript · ≈265k stars · MIT
NousResearch/hermes-agent
The agent that grows with you.
Maintained by Nous Research
v0.23.3releasedTypeScript · ≈205k stars · AGPL-3.0
firecrawl/firecrawl
Turn websites into clean markdown for LLMs and agents.
Maintained by Firecrawl (formerly Mendable)
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- TopoteretesOrganisation
Similar entries · 4
- GraphitiProject
- Mem0Project
- OpenVikingProject
- ragflowProject
