Memory middleware
-
2026-AI-Value-Memory-Mining
Value Mining personal knowledge system — OpenSpec SDD showcase + forkable vault template
-
agent-history
Local semantic search over your AI coding agent session transcripts, using Ollama embeddings and sqlite-vec
-
agentic-swmm-workflow
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex, Hermes, Claude code as well as OpenClaw compatibility
-
agentic-workspace
Repo-native operating layer for AI agents: memory, planning, proof, routing, and continuity across sessions.
-
AgentWorkspaceOS
Local-first, Markdown-first operating protocol for shared context, memory, tasks, skills, ownership, and handoffs across Codex, Claude Code, Cursor, and other AI agents.
-
ai-brain-starter
The operating system for Claude Code. Memory, accountability, journaling, knowledge graphs, pattern recognition — one install, every session compounds.
-
AI-CLI-Agent
A privacy-first, local AI desktop agent. Wraps Gemma 4 in a modular Python framework, enabling autonomous web searching and system-level tool execution directly from the Linux terminal. Zero API keys required.
-
AIDOCS
AIDOCS — AI Doctrine Orchestrator, Control & Security.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
AliceBot
Local-first AI agent memory and second-brain runtime with MCP, governed scheduler, live capture connectors, dogfood telemetry, OpenClaw, and Hermes integrations.
-
anythingllm-mcp
Manage and operate AnythingLLM workspaces, chats, documents, and vectors with a fast, Python-based MCP server.
-
asya-chat-ui
Build multi-organization LLM chat platforms with model routing, tool execution, usage analytics, and OpenAI-compatible APIs.
-
athenaeum
Open source knowledge management pipeline — passive recall, append-only intake, tiered compilation, configurable schemas
-
aurora-cloudbank-symbolic
Secure symbolic memory vault for Aurora runtime, seeds, and exports
-
awesome-ai-agents-zh
中文 AI Agents、MCP 和 AI 开发工具导航
-
backchain-plugins
Claude Code plugins by Backchain. Practical agent skills authored to the agentskills.io specification.
-
bki-rag-chatbot
CLI chatbot RAG untuk menjawab pertanyaan teknis dari BKI Rules for Hull (Part 1 Seagoing Ships, Volume II, January 2026 Edition).
-
BridgeBuild-AI-PM-Tool
An AI-powered Enterprise Agile OS that instantly translates raw client audio and notes into client pitch decks, PM epics, UI specs, and backend engineering architectures using Gemini 1.5.
-
cairntir
Memory-first reasoning layer for Claude Code. Kills cross-chat AI amnesia. MCP server, verbatim storage, prediction-bound drawers, belief-as-distribution retrieval.
-
cc-harness-skills
Package portable CC coding-agent skills for Claude Code, Codex, and OpenClaw with reusable prompts, helper scripts, and installable SKILL.md bundles
-
chatbot-saas
RAG-powered chatbot-as-a-service — embed an AI chatbot trained on your own docs into any website
-
Chroma
Open-source embedding database (vector store) for building AI apps with memory and retrieval.
-
chronovisor
Provenance-first agentic memory for local AI systems
-
claude-context-local
🗂️ Manage and utilize local context for Claude, enhancing applications with tailored insights and improving user experience seamlessly.
-
claude-copilot
Transform Claude Code into a full development team. 11 specialized agents (Architect, Engineer, QA, Security, UX, DevOps, and more), persistent memory across sessions, and 25,000+ on-demand skills. Works immediately for solo devs—customizable with your team's standards, methodologies, and proprietary knowledge.
-
claude-recall
Automate repeated Claude Code workflows by capturing and converting them into reusable skills for faster, consistent task execution.
-
claude-tab-tracking
Real-time task tracking and conversation memory for Claude Code sessions
-
context-bridge
Persistent memory and replanning for Claude Code. Checkpoints what Claude was doing and injects context at the start of the next session.
-
core-graph
Converged graph + vector knowledge platform on PostgreSQL (Apache AGE + pgvector) for security, threat intel, and AI memory
-
ctxmem
Git-native, shareable project memory for AI coding agents — fully local, no cloud.
-
d-nd-seed
Portable operating substrate for AI coding agents: runtime memory, hooks, guardrails, continuity, capability routing and governed self-improvement.
-
DARWIN
Local-first RAG engine — ingest, index, search. MCP server for AI agents. All offline.
-
DeepLaw
DeepLaw 2.0：本地优先单用户 Agent Knowledge OS，融合自主长期记忆、Markdown-native 知识、可信 Ledger、有界上下文与可验证法律证据。
-
Dxrk
Dxrk Ecosystem Configurator — supercharge AI coding agents
-
EleSync
Your AI chats and memories Synced! Claude, ChatGPT, Gemini, Grok, Deepseek and Perplexity with a 1-click install. Create your local Vault or make a fully encrypted USB Hub. No Ads. No E-Mail. No Trackers. No registration. No BS. Your data is yours, we don't want it. Full features and 100% Free!
-
elite-reasoning-mcp
90+ tool Model Context Protocol server for AI coding agents: workflow flight recorder, quality-gated memory, release doctor, eval harnesses, and reasoning safety.
-
engram
AIエージェント用 人間型記憶基盤（MCPサーバー）— 完全日本語版。使うほど思い出しやすくなる長期記憶を Claude Code / Codex / Antigravity で共有
-
epicurus
Self-hosted, modular, local-first personal-assistant platform — an AI agent plus pluggable integration modules.
-
exomem
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
-
gnosis
Gnosis is a Greek noun meaning "knowledge" or "awareness"
-
greedy-token
Route dev tasks through tool (rg/jq - rust) → python → ollama (cheap llm) → RAG before escalating to Cursor (expencive llm)
-
Grimore-MD
Local-first cognitive daemon for automated vault management Markdown. Semantic indexing, auto-tagging, and connection discovery using LLMs and vector search.
-
intellectual-dna
🧠 Transform conversations into a searchable knowledge base, enabling deeper insights and evolved thinking on AI and decision-making.
-
junto-memory
Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.
-
kai
Kai is a local, Telegram-first personal engineering system: a persistent AI collaborator with repo-aware coding, memory, scheduling, PR review, and multi-backend resilience. Your machine, your data, your rules.
-
LangChain
Framework for building applications with large language models — chains, agents, tools, and retrieval.
-
lemory
🍋 Local-first memory middleware for your Markdown — turn your Obsidian vault into memory for any AI (MCP), with Korean-first hybrid retrieval, keyless on-device search, and an interactive knowledge graph.
-
Lians
Agent memory for regulated environments. Bitemporal model, tamper-evident audit chain, GDPR crypto-shred.
-
life-index
Life Index (CLI Core) — an agent-native, local-first personal life archive built on Markdown + YAML.
-
lilbee
The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.
-
lilith-cli
Lilith — Norse-themed terminal IDE and AI agent interface (Textual TUI, agent orchestration, vector memory)
-
LlamaIndex
Data framework for connecting custom data sources to large language models (RAG).
-
LLM-Apps
AI agents with support to multiple models
-
localm
Run local LLMs fully offline - chat, coding agent, image & music generation, knowledge/RAG, voice. Privacy-first, one CLI, no cloud required.
-
lumio
灵智（Lumio）— 银行级私有化智能客服参考实现 · RAG 机器人问答 + 实时 AI 坐席辅助 · 合规过滤/熔断降级/全链路监控 · FastAPI + Spring AI · 22 个信用卡 MCP 工具 · make demo 一键体验
-
markdown-memory
A cross-platform, file-based persistent memory and prompt bridge for Claude Code, claude.ai, and Antigravity IDE. Synchronizes project passports, handoffs, and session logs in an Obsidian Vault, connecting web planning with local CLI execution. Install via: npx markdown-memory
Memory Python -
markdown-vault-mcp
Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing
Memory Python -
Marrow
Multi-provider persistent memory and orchestration backend for AI coding agents via MCP
-
mcp-agent-framework
🤖 Orchestrate AI agents at scale using the MCP framework, enabling seamless context sharing, communication, and integration for enhanced collaboration.
-
mcp-code-mode
🤖 Enable AI code generation using the Code Execution MCP Server, integrating large language models with the Model Context Protocol for seamless tool use.
-
MCP-rag-with-Chromadb
🗂️ Build a versatile MCP server with RAG capabilities, supporting multiple document formats using LangChain and ChromaDB for efficient data retrieval.
-
memforge
Spec and reference tooling for typed dynamic memory on top of AGENTS.md-compatible coding agents.
-
memoria
🗂️ Organize messy social media exports into well-structured media libraries with accurate dates for easy access and management.
-
memory-seed
Portable local memory system and MCP search tooling for file-reading AI coding agents.
-
memtomem
Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.
-
mente_digital
Assistente de voz 100% local (PT-BR): llama.cpp + RAG do vault Obsidian + anti-alucinação por controle de fluxo. Whisper, XTTS/Piper, barge-in, agentes falados. 824 testes sem GPU.
-
minder
Self-hosted, 100% local AI platform — LLM inference, RAG, and knowledge graphs in one Docker stack. No API keys.
-
minni
Local-first memory and governance layer for AI agents, with per-agent vaults, hybrid recall, review-first learning, handoffs, audit trails, and native AFM/bridge provider support.
-
mnemo
Persistent memory layer for Claude Code — Obsidian vault health, connection discovery, brain dump, session notes, email bridge. Five lightweight skills, CLI-first, any taxonomy.
-
mnemo-mcp
🧠 Manage persistent AI memory with hybrid search and embedded sync for open, free, and unlimited access.
-
Mnemos
Persistent local MCP/CLI memory system for AI agents. CPU-only, 98.94–99.15% R@5 on LongMemEval. Named after Mnemosyne (Greek: μνήμη, memory).
-
mnemos-mcp
🧠 Transform documentation chaos into a structured memory system with Mnemos, your self-hosted, multi-context knowledge server for developers.
Memory Python -
Mnemosyne-OS
🧠 认知型记忆操作系统 · AI 长期记忆宫殿 · TMT五层记忆树 · 三馆闭环 · 知识图谱 · Hermes原生集成 · 自托管
-
MoHan-PC-Desktop-Assistant
MoHan Desktop Assistant is a customizable Windows AI companion and permission-gated productivity aide. It offers text and voice chat, Realtime conversation, animated expressions, to-dos, long-term memory, reminders, workflows, secure desktop tools, portable profiles, Home Assistant support, and privacy-first local data controls for daily life/work.
-
MoHan-PC-Desktop-Assistant
MoHan Desktop Assistant is a customizable Windows AI companion and permission-gated productivity aide. It offers text and voice chat, Realtime conversation, animated expressions, to-dos, long-term memory, reminders, workflows, secure desktop tools, portable profiles, Home Assistant support, and privacy-first local data controls for daily life/work.
-
neuralmind
Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 40-70× cheaper code questions.)
-
Neuron
MCP server giving LLMs long-term associative memory: per-context concept graph with 384-dim vector search, Hebbian link reinforcement and spreading activation. Local-first (embedded libSQL) or shared on Turso Cloud with concurrency-safe writes.
-
neurostack
Index and search Markdown vaults as knowledge graphs to provide AI agents with persistent, structured long-term memory across sessions.
-
NeXgen-Engine
Configure your AI coding CLIs from one Git repo you can diff and revert: author AGENTS.md, MCP config, and Markdown memory once, render them to each tool's native format, check for drift, and sync across machines fail-closed. Linux stable, Windows beta.
-
novaberg
Local, private personal AI with persistent memory, emergent personality, intrinsic curiosity and emotional intelligence. Runs fully offline on your own hardware — Python, LangGraph, PostgreSQL, Ollama.
-
oh-no-my-claudecode
Memory-grounded autonomous coding loops for Claude Code and Codex, with verifier gates, replay, evals, and tamper-evident receipts.
-
olympus
Self-hosted, partitioned agent-memory fleet: bare-metal Debian setup + mem0/Qdrant/Ollama stack + Hermes/Claude Code/OpenCode/Pi integrations, run from one olympus CLI/TUI.
-
omind
OMI/Obsidian memory tooling (Open Knowledge Format) for AI agents: reproduce the integration on any machine, plus a local web app to view, edit, and add memory entries.
-
open-mind
Understand any unfamiliar codebase in an afternoon — a local, deterministic, source-traceable knowledge index (glossary · graphs · code search) that never invents what isn't there.
-
openkos
Local-first engine that turns your scattered text into a living, portable knowledge base in the Open Knowledge Format (OKF)
-
opentulpa
Run a personal AI agent on your server that remembers your data and builds custom tools via chat commands through Telegram or API.
-
opti-oignon
Local-first AI inference platform for LLMs — private chat, RAG, defense-in-depth security (Daily/Bulbe, encryption at rest, 2FA), on your own hardware. SvelteKit + FastAPI
-
origin-memorycore
LLM Agent 记忆治理层 —— 热层/冷层双层,自动溢流 + 自适应召回阈值 | Memory governance layer for LLM agents — hot/cold tiers, automatic overflow + adaptive recall threshold
-
owledge
Markdown-first persistent memory and project planning for AI agents, existing knowledgebases, and multi-agent workflows.
-
PaddleDoc
Document OCR and Markdown extraction pipeline built on PaddleOCR, designed to feed RAG systems.
-
PDF-QA-RAG-System
📄 Transform your PDF documents into actionable insights with this RAG-based Question-Answering App for efficient and accurate responses.
-
Project-AMBER
Persistent memory & identity layer for AI agents with MCP server for Claude, Copilot, Gemini & Ollama
-
purrsh3ll
AI-powered terminal environment for penetration testers
-
qcobrain
Provenance-governed AI memory for agents: a self-evolving second brain in your IDE. Every write cites a source or it's refused. Markdown + grep.
-
Ragworks
Ragworks — a self-hosted, low-code workbench for building transparent, traceable RAG pipelines. Wire up ingestion and retrieval visually, then see exactly what every run did.
-
RightMemory
Tree + graph memory for AI coding agents, backed by Git-syncable Markdown.
-
rtfm
The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.
-
saipen
Portable, vendor-neutral continuation protocol for AI coding agents -- resume any project with any agent (Claude, Gemini, Codex, Aider...) with zero rebriefing. Plain markdown, zero dependencies.
-
second-brain
Persistent memory for Claude Code — the full plugin: hooks, skill, MCP server, workflows. A Markdown vault you own, no server and no account. Hooks-only version: continuum.
-
second-brain
A ready-to-use second brain for entrepreneurs, operated by Claude. Runs in Claude Code and Claude Cowork. Plain markdown, typed frontmatter, guided setup interview.
Memory Python -
session-recall
Shared memory for Claude Code and Codex. Your agent recalls decisions from weeks ago — including what the other engine worked out. Local semantic search over both histories, as MCP tools.
-
skills-tree
🌳 A comprehensive collection of all skills available for AI agents and computer-use models — perception, reasoning, memory, code, tool-use, multimodal, orchestration, and more.
-
SQLBot
🤖 Enhance data queries with SQLBot, an intelligent system that combines advanced models and RAG for seamless integration and secure access control.
-
subfloor
Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the data layer, we rent the harness.
-
Syntavra
Adaptive context and runtime optimization for coding agents—reducing token waste, externalizing tool output, preserving exact session history, and enforcing secure tool routing.
-
tailor
TAILOR — self-hosted AI memory framework. 100% local, LLM-agnostic, MCP-native
-
Talos
Selfhosted AI-Platform for using Local LLMs with a Multi-User Terminal and advanced RAG Pipeline for the LLM.
-
TangkuAgentOS
An open-source AI Operating System for intelligent agents, workflows, memory, plugins, automation, and autonomous AI ecosystems.
-
therapist
Local-first open-source AI agent for adult self-reflection — encrypted memory, terminal + Telegram, Italian/English. Experimental, not therapy.
-
theweave
Memory for AI agents you can cat, grep, and git. Markdown-native, MCP-compatible, you own the files.
-
trelix
🌲 Fast, reliable code intelligence — Tree-sitter AST parsing, contextual hybrid search, adaptive query planning, call-graph expansion & LLM synthesis. 20+ languages. Zero infra.
-
TST
TST is a local structured-memory framework for small language models. Its Rust kernel provides short-term memory, persistent long-term memory and a code Tree; the Python package adds action-aware routing, canonical memory planning, retrieval, safe repository indexing and an installed CLI.
-
tsubasa
Your engineering captain: a repo-resident AI persona with a knowledge graph stored in git. Agents cite incidents, ADRs and PRs instead of guessing — 47% fewer wrong answers, 40% cheaper on a public benchmark. Claude Code plugin + CLI.
-
v8-agent-os
The epoch-making Agent Runtime OS. Features Zero-Trust firewalls, Omni-Memory Graph, dynamic MCP/Skills pre-filtering, and something ecosystem hijack.
-
VecMem
Manage LLM agent memory with a resource-aware dual-tier system that uses HNSW indexing to balance short-term context and long-term knowledge retention.
-
vectr
Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.
-
Veracium
Provenance-aware memory for AI agents.
-
verimem
Verified memory for AI agents: gated writes, provenance on every read, bi-temporal history, abstention instead of hallucination. AGPL/commercial.
-
wavemind
Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.
-
Yggdrasil
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.