Agents that self-improve with experience
7 daysStars3.8k24h gain+6Score2.7
Find trending repositories by name or description.
Agents that self-improve with experience
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)