{"repo":"Kyros-494/kyros-ai","free":true,"listed":false,"github":"https://github.com/Kyros-494/kyros-ai","clone":"git clone https://github.com/Kyros-494/kyros-ai.git","description":"Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.","language":"Python","stars":96,"topics":["agents","ai","artificial-intelligence","docker","episodic-memory","fastapi","langchain","llamaindex","llm","memory"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"Kyros Persistent Memory System for AI Agents Give your AI agents secure, self-correcting, persistent memory with cryptographic integrity and natural forgetting curves. Features • Quick Start • Documentation • Examples • Contributing • License --- Overview Kyros is an open-source memory operating system designed specifically for AI agents. It provides three biologically-inspired memory types (episodic, semantic, and procedural) with built-in features like cryptographic integrity proofs, Ebbinghaus decay curves, and belief propagation. The Problem Modern AI agents are stateless — they forget everything between sessions. Developers manually implement memory using: - Vector databases for semantic search - Key-value stores for facts - Custom logic for memory management - Ad-hoc solutions for data integrity This approach is fragile, insecure, and doesn't scale . The Solution Kyros provides a complete memory system in a single SDK: --- Features Three Memory Types Based on cognitive science research, Kyros implements three distinct memory systems: - Episodic Memory : Events and experiences (conversations, actions, observations) - Semantic Memory : Facts and knowledge (user preferences, domain knowledge) - Procedural Memory : Skills and workflows (how to perform tasks) Cryptographic Integrity Every memory is protected with SHA-256 hashing and Merkle tree proofs: - Detect tampering and poisoning attacks - Verify memory authenticity - Audit trail for all changes - Immutable memory histo","default_branch":null,"files":null,"tree":[],"storefront":"/r/Kyros-494","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Kyros-494/kyros-ai/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}