Back to directory

Kyros

An open-source memory system for AI agents that gives them persistent episodic, semantic and procedural memory, with cryptographic integrity proofs and automatic decay and conflict resolution over time.

Kyros

Kyros stores three memory types modeled on cognitive science research: episodic memory for events and experiences, semantic memory for facts and preferences, and procedural memory for skills and workflows. Every memory is protected with SHA-256 hashing and Merkle tree proofs, giving tamper detection, authenticity verification and an audit trail across its history.

Memories fade over time following Ebbinghaus decay curves with category-specific half-lives, for example a much shorter half-life for market data than for user identity facts, which keeps the store from growing without bound. When new facts conflict with stored ones, a belief-propagation mechanism updates confidence scores across the semantic graph automatically. It is exposed as a model-agnostic REST API with Python and TypeScript SDKs, and is deployed with Docker alongside FastAPI, PostgreSQL and Redis.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.