AI Memory System

Lightweight Long-Term Memory for LLM Agents.

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

An index of my Claude Code related repos including a wide variety of starter templates for using Claude Code for common and more imaginative purposes!

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.

Shared starter template configuration and CLAUDE.md memory bank system for Claude Code

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

M.I.L.E.S, a GPT-4-Turbo voice assistant, self-adapts its prompts and AI model, can play any Spotify song, adjusts system and Spotify volume, performs calculations, browses the web and internet, searches global weather, delivers date and time, autonomously chooses and retains long-term memories. Available for macOS and Windows.

Open-source platform for multi-agent AI orchestration, real-world asset tokenization, workflow automation. Includes OAuth 2.1 MCP agent management, a 44-field RWA schema, Stripe, designed to integrate with AetherNet QUAS & KVS sovereign, post quantum, architecture agnostic omni-substrate, semantic memory, & institutional settlement system.

The best-benchmarked open-source memory system for AI coding assistants

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

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to your work and drives a real browser; and a Developer that names each weakness before writing, checks the project's security, runs the project's tests before saying done, and remembers what this project decided.

Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents

Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.

Autonomous orchestration framework for Claude Code with MemPalace-inspired memory (4-layer stack, 818-token wake-up), parallel-first Agent Teams (6 teammates), Aristotle First Principles methodology, and 4-stage quality gates. 925+ tests, 22 active hooks, automatic learning pipeline.

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Context Engineering: Build Consistent, Accurate, Predictable AI Systems

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.