Versatile Almost Local, Eventually Reasonable Assistant 🔫

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.

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

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

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

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

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

A TypeScript-based autonomous agent framework with modular systems for memory, planning, and tool integration. Features vector-based recall, multi-strategy planning, and extensible tools for AI agent development.

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

Get started integration Llama Index into your swarms application now!

Stateful personality + memory + emotion model for AI personas. Create digital companions that remember, feel, and evolve through conversations.

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

Claude Code Presentation - Showcasing Claude Code features

The STYNTHREAD Advanced Game Engine (SAGE) — born from defiance, built for consequence

🧠 基于文档的AI协作系统，让AI具备长期记忆能力，帮助开发者管理知识、任务和项目

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.

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

Hybrid memory and harmonic pattern engine with RAM buffer, SQLite storage, pattern compression, predictive engine, waveform visualization, authorship verification, encrypted cache - by Adam Lee Hatchett