G
31.3k
Stars
+2611
Stars/month
117
Commits (90d)
7
Releases (6m)
Star Growth
+7.8k (33.3%)estimated from velocity
Overview
Graphiti is a framework for building and querying temporal context graphs that track how facts change over time for AI agents. It integrates user interactions and enterprise data into a queryable graph, supporting incremental updates and historical queries without full recomputation.
Deep Analysis
Key Differentiator
Builds temporal graphs that track what's true now and what was true before, unlike static knowledge graphs.
⚡ Capabilities
- • Build temporal knowledge graphs
- • Track fact validity windows
- • Hybrid retrieval (semantic + keyword + graph)
- • Incremental data updates
- • Historical queries
✓ Best For
- ✓ Agents needing evolving, real-world context
- ✓ Applications requiring structured context over flat chunks
- ✓ Tracking provenance and relationships over time
✗ Not Ideal For
- ✗ Simple static RAG systems
- ✗ Applications needing only current-state retrieval
⚠ Known Limitations
- ⚠ Evidence does not specify integrations or deployment options
Alternatives
M
Memary
The Open Source Memory Layer For Autonomous Agents
C
Cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
M
MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harne
O
OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Compare Graphiti
Maintain Graphiti?
Show your live rank in your README, or put Graphiti in front of every visitor to AgentoolRank.