A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Universal memory runtime for AI agents

Poirot is a deep research agent kernel built for those who care about how agents are architected.

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

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 Harness support.

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.