Versatile Almost Local, Eventually Reasonable Assistant 🔫

Send voice notes to Telegram → get organized knowledge base, tasks in Todoist, and daily reports. Persistent memory with Ebbinghaus decay, vault health scoring, knowledge graph. Runs on Claude Code + OpenClaw. 5/mo.

A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.

HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.

OpenClaw Q&A 社区 — AI Agent 记忆系统、多Agent架构、进化系统、具身AI | 龙虾茶馆 🦞

A Multiplatform benchmark designed to provide holistic, detailed and close-to-hardware view of memory system performance with family of bandwidth--latency curves.

Standalone intelligent memory system with knowledge graphs, pattern learning, and 7-layer architecture. 100% local, zero external APIs.

Production-ready AI infrastructure: RAG with smart reindexing, persistent memory, browser automation, and MCP integration. Stop rebuilding tools for every AI project.

Make your OpenClaw AI agent faster, smarter, and actually useful. One prompt does the whole setup.

Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Features hybrid search (semantic + BM25), MCP server integration, SQLite persistence with knowledge graph, and proactive memory surfacing. Written in Rust.

MemP: Exploring Agent Procedural Memory

🧠 Claude Code 三层记忆系统 | 结构化存储 + 生命周期管理 + Git追踪 | 官方Auto Memory的管理层 | 一行命令安装 零依赖

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.

The Mess benchmark, redesigned. A C++ framework for generating bandwidth–latency curves to characterize memory systems.

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

A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten

Episodic memory for AI coding agents — captures tool calls, edits, and outputs across sessions. The episodic layer of a full agent memory stack (pairs with QMD + probe).

An auxiliary system for language models that integrates a vector-based retrieval/memory system that metabolizes inference history based on a symbiotic score.

A local desktop app for creating AI companions with unique personalities, emotional depth, and persistent memory.

Long-term memory for AI agents using plain markdown. No vector DB, no embeddings — just skill files the agent already knows how to read.

Structured memory system for AI assistants. Eliminates context loss with branch notes, tacit knowledge, and project context. Local MCP integration for Cursor IDE.

Local-first AI memory system and multi-agent control plane for persistent context, project routing, and long-term knowledge.

Every memory technique that works. All coexisting additively. 102 features, 2,037+ tests.

Single-repository bootstrap framework for Claude Code, Codex, and Gemini with memory, IM bridge, and catalog-guided MCP/skills onboarding.

A cognitive runtime architecture for LLM continuity, memory, identity, and safe pseudo-conscious agents.

Five-layer memory architecture for Claude AI. Local-first, Git-tracked.

🦞 Zero-cost layered memory system for 24/7 AI Agents. Inspired by memU, powered by pure Markdown.

Get started integration Llama Index into your swarms application now!

Universal Agent Harness - Transform Claude Code & Codex into intelligent, memory-aware development teams. 5-agent system, dual-layer memory, TDD workflow.

Persistent memory infrastructure for Claude Code. Multi-layer retrieval with bio-inspired memory dynamics.