Havuz

The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing tha

Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.

记忆核心（Memory Eternal）：自研的 DeepSeek Harness 记忆插件——对话结束自动沉淀知识卡到本地 Markdown Vault（自研去重 / 自研 CJK 检索 / 知识图谱 + 审核中心 / 回收中心），Agent 通过 memory_recall

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown

Lightweight, local-first memory for AI agents. Hybrid vector + BM25 search, LLM-powered fact extraction, zero infrastructure — just pip inst

Long-term memory for LLM apps that shows its work: dated facts, as-of answers, supersession, and receipts on every answer. Library, CLI, loc

Memory and state for AI agents: every correction kept with history, and agents that resume from their own records. Runs on your database.

Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.

Persistent memory for Claude Code. Your AI never starts from scratch again.

Baron Munchausen — local memory for coding agents that outlives the chat, with a verdict on every answer. Public alpha.

Open source memory infrastructure for AI and humans. Turn scattered knowledge into AI-ready context across Claude, Cursor, ChatGPT, and any

Personal Hermes agent with Emblem Vault crypto integration.

Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.

Longitudinal relational modeling for reflective agents: behavioral signals, evolving subject profiles, inspectable runtime governance.

Your AI finally remembers your codebase

Persistent memory system for Coding Agents (Claude, Opencode, Codex), infinite context, learning extraction, persona modeling and so much m

FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.

aiduMEI⚕爱嘟优忆思——aidu Memory Engine Insight · 智能体通用智慧引擎——Excellent memory system for all agents.

Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation. Cloud Run service + MCP tools.

Files you own. Memory your agents can trust. Also: your AI won't gaslight you about what's in your own notes anymore.

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Im

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflo

Lightweight, provider-agnostic long-term memory for conversational agents

Advanced Memory for LLM characters

A standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP server

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no c

Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team co

Persistent, governed memory for chat clients, IDEs, & agents. Share memory across clients without losing scope, provenance, or auditability.

[NeurIPS 2026] Official codebase for the paper "WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction"

Long-term memory for Claude Code. Indexes every session as SQLite+FTS5, exposes recall via MCP, and ships PreCompact/PostCompact hooks so no

Your personal AI team that gets things done. Shared memory. Any model. Local or cloud. Run. Rest. Dream. 🐨

源码级逆向工程（Hermes、OpenClaw、nanobot、NullClaw、OpenFang）记忆系统 —— 架构图、数据模型、检索管线、复刻指南。Source-Level Reverse Engineering of Memory Systems (OpenClaw, n

A local predictive experience layer where AI agents turn repeated work into inspectable model cards

The AI agent with a memory that lives on your machine and answers the phone.

Git-native shared memory for AI CLI agents

A local-first cognitive architecture for building a persistent digital companion with memory, reasoning, personality, and long-term learning

mori MCP server — a governed memory layer for AI coding agents.

A high-performance, local, offline-first AI memory system built in Rust

Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings

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

Persistent memory for Claude Code. Local SQLite + MCP + hooks.

SGME 拾光记忆引擎：AI 全面接管记忆、技能库、WIKI 知识库三大模块，跨会话、多智能体共享记忆，AI 会一直记得你的偏好。ShiGuang Memory Engine · AI takes full charge of three core modules — memor

Persistent memory for AI agent teams: private silos, shared hive, and curator workflow.

Memory layer for AI Agents and OpenClaw powered by Rust

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

Mental health support companion

A memory system for AI agents modeled on human memory: episodic, affective, reconstructive.

🧠 Community skill for Claude Code & Codex that helps your agent learn from its mistakes. /aprende reviews the conversation, surfaces durable

A desktop workspace for coding agents: browse local session history, chat with agents live, and orchestrate multi-agent threads.

OpenClaw plugin for persistent AI memory