procedural-memory

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

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.

A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No API key.

Dynamic agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS spaced repetition and memory consolidation. Zero-dependency TypeScript library, Model Context Protocol (MCP) server, Vercel AI SDK middleware. Paper: arXiv 2604.23878 · reproduction packages on Zenodo.

Persistent filesystem-based memory system for Claude Code. Pure MIF Level 3 compliant memory storage with YAML frontmatter, bi-temporal tracking, and proactive hooks. No dependencies - just markdown files and git.

Muscle memory for coding agents. Local Hebbian procedural memory that learns which files, tools and fixes go together — and recalls them before your agent searches.

A persistent Minecraft inhabitant that remembers, feels functionally, forms habits, pursues goals, and learns how to live

📚 Practical guide to context engineering for AI agents. Why context fails, how memory works, and techniques that actually help.

MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.

Staff-Level Engineering Meta-Skill for AI coding agents. Evidence-based verified loops, strict TDD, anti-guessing discipline, and clean code.

Memory for Claude Code that survives between sessions. Three kinds of memory (episodic, semantic, procedural) in one local markdown vault, surfaced in conversation through MCP.

Locally run multi-tier, multi-model, multi-modal, multi-mode Agentic AI Assistant Training/Inference Instance with CRAIID - Continuous Redundant AI Instance Dialogue - A proprietary personalized context/memory compression/storage/management subsystem designed to overcome ctx fatigue while maintaining accuracy, integrity & fidelity. And a lot more!

Build and manage persistent memory for AI agents by enhancing workspace indexing to ensure directive compliance and accurate behavior.

An agentic harness for accelerator kernel generation and optimization, with reusable skills extracted from expert implementations.

Open-source procedural memory for AI agents. Learns from what worked and what failed.

Agent's procedural memory for the web. Turn one successful browser workflow into reusable, zero-cost CLI commands.

LIA Labs / Learnkit - "Make your AI agents Learn Improve and Adapt".

Self-growing procedural knowledge layer for AI agents. Rust MCP server + CLI — recall relevant knowledge before tasks, record outcomes after, distill experience into reusable insights. Works with Claude Code, Codex, opencode.

A model-agnostic multi-layer vector storage system with explicit mappings and learned retrieval shortcuts.

Every session becomes practice film — Hermes-inspired, Letta-native Skill Ops for agents.