Havuz

Offline-first AI memory for coding — 29 MCP tools, temporal knowledge graph, and local vector search. No API keys, no cloud, no server.

F.R.I.D.A.Y — a secure self-improving personal AI agent. Local-first, with memory, tools, voice, MCP, automation, and verified self-extensio

Framework-agnostic, local-first memory lifecycle for AI agents: Rust CLI, SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve a

中文 GBrain 实操手册 for Amazon sellers: build an AI-native second brain with real commands, examples, governance, and Agent workflows.

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

Precision-aware retrieval benchmark for LLM memory systems.

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,

Open Source Coding Agent

Knows your world. Answers to you. — the open-source personal AI agent you own.

讓 Claude 在每一台電腦都記得你：Claude Code 記憶的跨裝置同步、整理與復原。記憶存在你自己的 GitHub 私人 repo（Windows 11）

Self-hosted shared memory for AI agents: vaults of people, facts and decisions your agents recall over MCP or REST, with semantic, keyword a

LITSAN (formerly Memhub): self-hosted AI memory for people and teams: project continuity, traceable evidence, private workspaces, and MCP in

Friday, AI coding agent’ların oturumlar arasında mimari kararları ve proje bağlamını koruması için self-hosted bir memory servisi sunuyor.

Neden yükseliyor · Agent’ların kalıcı proje bağlamına duyulan ilgiyle uyumlu, erken aşamada görünürlük kazanmış bir proje. 11 günde 60 yıldız ve son 28 günde 32 commit hareketliliğe işaret ediyor; ancak commit’lerin tamamı tek yazardan geldiği için bu veriler bağımsız katkı veya benimsenme kanıtı sayılmaz.

Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persist

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, C

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local proj

Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code c

Four local, file-based MCP servers for solo devs/vibecoders: persistent memory, session handoff/resume, file checkpoints, token-efficient pr

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradictio

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次，你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置

The memory and context-management layer for production AI agents. 95.6% on LongMemEval, 93.2% on LoCoMo, with an open harness. Python + JS S

Local-first, evidence-aware memory and project continuity for AI coding agents. Checkpoints, context packs and auditable receipts without te

A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.

Starter kit for a huge full-stack Web2 app or a whole app factory, on your own PC or a VPS. Sign-in, data, files, design, memory and a kno

CTX is the standard Cognitive Version Control System for AI. Structured working memory for AI agents. CTX preserves goals, tasks, evidence,

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop

Persistent Shared Memory Server for AI Agents via MCP

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embe

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

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection,

Sovereign, depth-adaptive AI memory. Open source. Local-first. Model-agnostic.

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

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve

bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clie

Give Claude Code a persistent memory — it remembers you, your projects, and your decisions as plain Markdown files you own. Fully local. Jus

Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreadi

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

🏛️ Memory OS for AI agents — every conversation becomes a catalog card (archive no · entities · evidence · trace back to the transcript). Fo

Makra is a memory layer between the web and your AI agents. It serves real-time structured data from the open web at the cost of a vector se