memory

Maximem Synap is the memory layer that makes AI agents remember. 92% LongMemEval, 93.2% on LOCOMO. Works natively with LangChain, LlamaIndex, CrewAI, Google ADK, AutoGen, OpenAI Agents, Semantic Kernel, Haystack, and Pydantic AI.

A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

Advanced AI email assistant using Groq for responsive replies, Llama for contextual information retrieval, and RAG with LangChain for enhanced accuracy.

Adaptive Reasoning Engine for Efficient and Context-Aware Intelligence

Persistent memory for AI agents - Learn, remember, improve. Alternative to Mem0 with scoped learning, anti-patterns, multi-agent sharing, and MCP integration.

A SillyTavern extension providing a multi-tier memory and narrative context system for AI roleplay. Tracks character facts, relationship history, per-character knowledge and secrets, entity state, scene history, story arcs, and rolling summaries - extracted automatically so your AI stays coherent no matter how long the story runs.

Kronos Agent OS (KAOS): self-hosted runtime for durable AI agents with memory, skills, MCP tools, automations, dashboard, and optional swarm coordination.

➡️ Moved to Hivekeep: github.com/MarlBurroW/hivekeep — self-hosted autonomous AI agents. Your AI team. At home.

A Free, Open Source MCP server for dynamic custom persona management with public a GitHub collection of personas, skills, templates, and other elements for AI models.

🐍 Personal AI agent in pure Python — OpenClaw reimagined. Memory, RAG, skills marketplace, cron, voice. Telegram/Discord/WhatsApp/Web. Works with DeepSeek, Claude, Gemini, Kimi, GLM, Ollama.

TMLR | This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms.

Reference architecture for LLM-based applications on Google Cloud Platform with Redis Enterprise as a high-performance data layer.

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

A web-based memory usage and performance calculator for Huggingface GGUF models

Official Core Services for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, Windsurf. Temporal decay, contradiction detection, knowledge graph, autonomous consolidation. Backed by the YantrikDB Rust engine. Install: pip install yantrikdb-mcp.

A python toolbox for analyzing and plotting free recall data