local-first
267 servers · 18,967★ total
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.
Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 285 commands, 244 MCP tools, change-safety gates, audit evidence, zero API keys.
Open-source, local-first parametric CAD in the browser for people and permissioned typed agents, powered by OpenCascade WASM.
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Harness-oriented agent system framework for production-grade LLM agent applications
Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.
Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.
DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
Mine your Claude Code and Codex logs into a local you.md agent profile.
On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.
Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.
Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.
Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.
Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
Local MCP server that exposes eBay Sell APIs to AI assistants with OAuth, tool gating, and stdio/HTTP transports.
One TypeScript interface for 24+ LLM providers — swap providers without rewriting. MCP-native (connect any MCP server), voice (TTS/STT/realtime), RAG, memory, file processors. Production-origin: powers Tara, Yama, and Clairvoyance at Juspay.
Codex/ChatGPT plugin app and OAuth MCP connector for approved local workspaces.
Modular Context | Karpathy LLM Knowledge Base + Gmail & G-Cal — multi-account MCP server for Claude Code, encrypted local-first
Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.
Track work, verify results, carry memory, and sync tools across coding agents. Local files, no daemon.
MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control and query.
Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.
From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.
Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 122 canonical MCP tools, hybrid recall, bi-temporal history, AES-256-GCM. Local-first, air-gap ready, MIT.
Local-first workspace for Claude Code, Codex CLI, and Gemini CLI with sessions, analytics, workflows, and tools
Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes
Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.
Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.
Local-first skill routing for agent builders — index SKILL.md bundles, get ranked skill plans with confidence and evidence, and serve them to any agent over MCP.
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.
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.
Live context engine for AI agents: resolve verified workspace state before the context window opens. Pairs with Perseus Vault for persistent encrypted memory. Local-first, MIT. pip install perseus-ctx
Your AI remembers now. Geniuz stores everything in a local database locally on Mac, Windows, Linux, Raspberry Pi. No cloud. No account. No API keys. Nothing leaves your machine. It's open source; you can read every line of code.
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
Drive your real, logged-in Chrome from any AI agent (Claude Code, Cursor, VS Code) — works where headless dies. Reads emailed login codes from your Gmail, solves CAPTCHAs, 34 tools. MIT, local-only.
local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools
Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.
The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.
The Private Agent OS — search files, run AI agents, connect to 10,000+ tools via the complete protocol stack (MCP, AG-UI, A2UI, A2A). Zero cloud. Zero telemetry. On-device inference.
Catch up on Slack without reading it. Unreads, threads, search. Browser-session or hosted OAuth. 21 tools.
Local-first autonomous coding agent that plans, executes, validates, and finishes software tasks end-to-end.
Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-weighted RRF. Apache-2.0.
Local-first beat library built for producers — catalog, BPM/key analysis, license tiers & PDFs, tagged-MP3 + loopkit export, and assisted multi-platform publishing. Chat with your catalog via a built-in AI Agent (Claude · ChatGPT · DeepSeek), or wire it to any MCP client. Desktop + web.
Turn tab overload into a local-first workspace with intent-first AI organization and Agent collaboration through MCP.
一键配置各类 AI Agent 工具的 MCP、Skills 和规则；支持 Claude Code、Codex、Cursor、Gemini CLI、Qwen Code 等。 One-click local setup for MCP servers, skills, and rules across AI coding agents.
The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first, MCP-native, open source.
Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.
Your AI forgets everything between sessions. SAME fixes that. Local-first, no API keys, single binary.
Public registry for local-first wellness MCP connectors: wearables, recovery, training, nutrition and the Delx Wellness Hermes profile.
m1nd is a local-first context runtime for coding agents: an evidence-bound, continuously verified model of your code, memory, and change.
A local-first, LLM-agnostic memory layer for AI assistants
Modular, agentic framework and MCP platform you self-host. Build and run your own AI agents, connect Claude Code, Claude Desktop, or Cursor as a native MCP connector, self-host your apps, and share over encrypted P2P — on hardware you own, with local or cloud models. Open source.
Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.
Don't write a bug report — record it. Local MCP: screen recording → transcript, frames, OCR, wall-clock evidence for coding agents.
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.
Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase. Zero config, zero cloud, full context.
AI-first, zero-dependency JavaScript database. Vector search, agent memory, MCP server, and encryption built in. Node.js, Bun, Deno, browsers, and edge runtimes.
Give ChatGPT a real terminal on your Mac. Open-source MCP bridge for shell, files, PTY sessions, jobs, and Codex history.
Local code search for AI coding agents: a CLI and MCP server with hybrid keyword + semantic search and SQL relevance-ranked aggregation over an index in plain files. No accounts, no keys, no server.
Локальный семантический граф и MCP-сервер для Markdown и Obsidian
Agentic coding harness with persistent memory and a REPL body. Built on Ori Mnemos. Open source must win.
Turn Hermes into a local-first wellness agent with guided setup, onboarding, wellness skills and MCP connector presets.
Local agent infrastructure in one stdlib-only Go binary
Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.
MoFlo — an opinionated, local-first AI agent orchestration toolkit for Claude Code: semantic memory, learned routing, gates, and spells. No API keys, no cloud, works out of the box.
🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.
Governed state engine for AI agents: typed, executable knowledge artifacts with a code-like lifecycle
Structured local memory storage and retrieval for LLM agents
Local-first file intelligence: desktop app, CLI, and safe MCP server for AI agents.
Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
Local-first agent memory MCP - cross-agent brain with token-saving file diff cache. By Synapse Arrows.
Graph + local semantic context for Obsidian, with guarded remote MCP access and edits from Codex, ChatGPT, Claude, and any MCP client.
Local message bus for Claude Code, Codex, and other MCP agents — one SQLite file, 20 tools, no daemon, no cloud.
Native macOS MCP server — secure local access to Mail, Calendar, Contacts, Notes, Reminders, Photos & Apple Intelligence for AI assistants
MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-gated shell command execution, scoped to a single workspace root. Local-first, no cloud dependency, full audit logging. Built in TypeScript.
Local-first MCP memory server. Indexes Claude Code/Cowork/Telegram chats; any MCP-compatible AI agent (Cursor, Cline, Continue) can search them.
Private, local-first AI assistant for Windows with permissioned tools, durable memory, and evidence-driven small-model improvements.
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.
Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.
Local-first AI image workspace for people and agents. Generate, edit, organize, and reuse images through the desktop app, JSON CLI, or MCP.
Organize and track job applications and tailor LaTeX resumes from the CLI or an MCP client.
Local-first MCP server for Obsidian vaults — no plugins, no API keys, with schema-validated Bases (.base) support.
Verified, fully-local code context for AI agents. MCP-native. No cloud, no editor lock-in.
Local-first knowledge graph for browser tabs. Louvain clustering, PageRank, MCP server for AI assistants, Chrome extension, CLI. 100% private.
Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph. No cloud, no API keys. npx @studiomeyer/local-memory-mcp
Local-first clipboard history for macOS — offline semantic search, OCR, content protection, and a built-in MCP server for AI tools. 本地优先的 macOS 剪贴板管理器
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
One memory layer for every AI agent. Local-first, markdown source of truth, and CLI/HTTP/MCP native. Your agent forgot who you are. Again. Dory fixes that.
Local-first memory for AI agents: one SQLite file, zero deps. Recency-aware exact recall, conflict detection, time-travel journal, MCP server.
Your data, explored locally — and your AI agents kept on a leash. A federated data explorer with governed agentic access.
A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambiguity, and a guardrail that refuses to amplify rumination, hyperfocus, or sycophancy. MCP-native. No telemetry. AGPL-3.0-or-later. Self-ID sufficient — no diagnosis gating.
The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents on your machine.
Local‑first MCP server for multi‑repository semantic code search with Qdrant and llama. Turns your entire workspace into private context for AI coding assistants like Claude Code, Codex, Cursor, Copilot, Antigravity and Windsurf.
Local-first MCP coordination hub. One local daemon serves multiple AI assistants across IDEs — shared meetings, tasks, messages, and project registry. Works with Claude, Cursor, VS Code, Zed.
Local room where AI coding agents collaborate on one codebase via MCP — collisions prevented, human in command.
Local-first MCP server for Garmin Body Battery, HRV, sleep & training data — Claude/Cursor ready
Local hardware intelligence for AI coding agents. Zero cloud. Zero telemetry.
MCP server for Hey.com: read, send, search, and organise email from Claude or any MCP client. Runs locally, stores no credentials, respects rate limits.
Markdown-first multi-model AI orchestration in one tmux session. A single coordinator (Chrono) routes scoped markdown task packets across 4 frontier model lanes (GPT-5.6 Sol / Claude Opus 5 + Fable 5 / Gemini 3.5 / Kimi K3) and 73 role-based specialists — with cross-family review gates, git-snapshot safety rails, and no server. Dogfooded.
Local-first crystalline intelligence for AI agents: the knowledge that endures across sessions, taught as Markdown Domains and captured as Engrams. One Rust binary with MCP server, CLI and hybrid search.
A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.
Smart note consolidation for Obsidian using Claude AI. Automatically identifies and merges scattered fragments into structured knowledge via MCP. Like Tetris for your thoughts - pieces fall into place.
One home for every idea — local-first macOS desktop app for tracking work-in-flight with linked repo worktrees, context files, external resources, and AI agent sessions, all per-idea.
Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.
Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git commits and diffs, and project docs into a local SQLite database, and serves back a token-budgeted slice on demand. No cloud, no account.
Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.
Local-first nutrition MCP for Claude/Cursor: USDA food search, barcode + photo, meal logging
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.
Local-first MCP memory server for AI coding agents with compact retrieval and project/global scopes.
Local-first knowledge base with semantic search for AI coding assistants. Fewer tokens, faster context.
Experimental local-first memory CLI for MCP agents: read-only Gmail, calendars, iMessage, and files → cited local context
Desktop AI agent for Windows — an architecture that expands what any model can do. Image/video OCR, offline speech transcription, an agent-driven browser, real .xlsx/.pptx/.docx output, MCP, and a delegated team of agents. Runs on your machine, with any provider.
Vellis — open-source context graph engine for AI agents: typed, local-first memory with explicit schema, validated change, deterministic query, migration, snapshots, replay, and audit. MCP-native. Apache-2.0.
Local-first codebase knowledge-graph MCP server for AI agents (Claude Code, Cursor, Codex). Symbol graph over MCP so agents stop wasting tokens re-scanning files. Watch-first · 21 languages · faster, leaner & more accurate than the incumbent.
Decision memory for AI coding agents. A local-first Go binary and MCP server: records decisions with evidence, scope, provenance and expiry, packs the relevant ones into each agent session within a token budget, and links commits back to the decisions that were in scope when they landed.
A autonomous, local-first personal intelligence layer. Features an Active World Model, Qdrant Graph Memory, Circadian Rhythms, and MCP integration to act as the hidden brain for your digital life and IDEs.
Open-source (AGPL v3) personal finance app with a first-party MCP server. Track your money here, analyze it anywhere — query your finances from Claude, Cursor, or any MCP client. Self-host with Docker or use the free cloud.
Local-first memory, observation, and autonomy layer for Claude. A background daemon that learns from your sessions.
Local-first MCP server for WHOOP recovery, HRV & sleep — Claude, Cursor, ChatGPT ready
Use ChatGPT as the brain and your local computer as the hands — a safe, permissioned local MCP gateway with default-deny security, local approvals, and full audit logging.
Local-first semantic knowledge graph with magnetic-pull retrieval
A living second brain that connects everything you think with — your AI agents, your notes, and beyond.
AI-Tadpole-OS a local-first "development platform" a Lily Pad to jump from for running autonomous AI agent teams on your own hardware. Coordinate parallel workflows, maintain full data privacy, and oversee every decision — no cloud required.
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
MCP server for AI memory -- hybrid search (BM25 + semantic + knowledge graph), temporal decay, local-first
🧠 Persistent memory for AI agents. SQLite for agent state. Zero cloud dependencies. Local embeddings. MCP-native integration with Claude Desktop/Code, Cursor, Windsurf & more.
AletheiaDB: The cognitive memory engine for AI agents with fact supersession.
BACH v3.12.4-earth: local-first text-based OS for LLM agents with SQLite memory, 113+ handlers, 550+ tools, MCP servers, scheduler and multi-agent orchestration
the memory layer of your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.
Local-first, audited memory MCP for Claude Code, OpenAI Codex, Gemini CLI, Cursor, Cline, Continue and OpenCode. Your agent gets a navigable cognitive map instead of a bloated context file. Zero cloud. SQLite local storage. Every mutation audited.
Local-first persistent memory for Claude Code, Cursor, ChatGPT & every MCP client — one Markdown vault, shared across every AI tool.
The open-source autonomy kernel MELRA — Modular Execution Layer for Reliable Autonomy. An agent-independent effect runtime for governed, durable, and verifiable autonomous execution. MELRA begins where the tool call leaves the model loop.
Local, private memory for AI agents — one vault on your Mac, shared by Claude Code, Cursor, Codex and more over MCP
DebugBundle product source and runtime code.
One local-first MCP server for agent working state — clipboard history & snippets, TTL cache, file-organizer overlay, and a knowledge graph — plus a live desktop activity lens. 40 tools, SQLite everywhere, no daemons. Apache-2.0.
Active state management for multi-agent coding — one versioned project brain (brain.klypix) over MCP
Self-hosted AI roleplay client with memory that survives long campaigns — tiered canon/heuristic/reflex writes, retrieval-time privacy ACL for group chats, and native MCP tool support. Imports v2/v3 character cards. Runs on Ollama, OpenAI, Anthropic, OpenRouter, or any OpenAI-compatible endpoint.
Turn code tasks, diffs, and stack traces into local, relationship-aware context packs for coding agents.
Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 65 MCP tools. Local, no cloud.
Local-first second brain for your handwritten reMarkable notebooks, searched through Claude Desktop.
🎙️🧠 Local-first macOS meeting + document notebook — on-device Whisper transcription, source-linked notes, @brain and history Q&A, a read-only local MCP server, E2EE sharing, and plain Markdown exports. Run AI locally or explicitly opt into redacted cloud AI · AGPL-3.0
Open-source, local-first, AI-native personal finance platform built on DuckDB
Local-first MCP memory server for operational project state: decisions, blockers, plans, patterns, and next moves.
LiAgent OS is a local-first AI agent OS for building a private personal assistant with governed autonomy across local models and hybrid cloud services. It brings conversation, tool use, multi-agent orchestration, task scheduling, heartbeat execution, human approval, and auditability into one long-lived loop.
Local-first semantic search for your ChatGPT, Claude, and AI conversation history. Python CLI + MCP server for Claude Desktop. Uses sentence-transformers + ChromaDB. No API keys, nothing leaves your machine. Part of the Resonant ecosystem.
Turn any markdown vault or codebase into a cited, AI-queryable knowledge graph. Local-first CLI, web viewer, and MCP server.
Confidential local RAG for your coding agents.
High-performance local SQLite FTS5-based tool output cache and MCP multiplexer for AI agents.
Model Context Protocol (MCP) server for local vector storage & semantic search (ChromaDB, OCR, async ingestion).
Secure execution for AI agents, on any machine. Connect any MCP client to the development environment on any machine you can run a command on (even your own laptop) - no open ports, no tunnels, and your source code never leaves the machine.
High-performance, low-latency MCP server for local code context. Features AST-aware symbol graphs, semantic reranking, and PageRank-scored search for AI agents (Claude, Cursor, and more).
Local-first personal Markdown knowledge base with semantic search, AI Q&A, MCP, desktop/web clients, and a self-hostable zero-data-at-rest relay.
Use less context in Claude, Codex, and Cursor. Local AI memory and verifiable work briefs for long-running tasks.
Native C++17 AI agent runtime — local-first, embeddable, MCP-native. Tool-calling, memory, and an async agent loop that runs where Python can't: ROS2, game threads, drones, HFT.
Unofficial local-first Polar AccessLink Dynamic API v4 MCP server for AI agents
Local AI memory system for Node.js — verbatim storage, semantic search, knowledge graph, MCP server. Port of the Python MemPalace.
Local-first engine that grounds an AI agent's answers in your own Markdown and captures what it learns back into the KB — Node · TypeScript · MCP.
The canonical Sovereign AI Agent OS & runtime harness. Built for Model Context Protocol (MCP), Agent-to-Agent (A2A) swarms, and zero-token tax execution.
MCP server for agent memory over HexxlaDB—ring retrieval, embeddings + lexical search, seams, facets, YAML persistence policy, localhost HTTP transport.
Self-hosted AI gateway: OpenAI/Anthropic-compatible APIs, virtual keys with token budgets, exact+semantic response cache, reverse MCP governance (REST→MCP), Prometheus/Langfuse observability — fake-provider-first, zero credentials to try.
本地优先的文档数据管理工具：把大规模语料整理成带稳定地址的条件树，精确定位片段且可回溯出处；关键词 + bge-m3 语义检索，经 MCP 开放给外部 AI agent。
Local AI job application assistant for the German-speaking job market (DACH) — job search, application tracking, CV analysis. MCP server for Claude Desktop, self-hosted, no cloud. Deutsch: dein Bewerbungs-Helfer, läuft komplett lokal.
Rust homelab control plane and Labby MCP gateway for agents, plugins, registries, stash workspaces, setup, logs, fleet operations, CLI/API/web UI.
Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.
Search your data exports from Google, Telegram, Spotify, and Instagram in one place. Everything runs on your own computer. Hybrid search and MCP, built in .NET 10.
Your AI workforce. Multi-agent orchestrator across Telegram, Slack, WhatsApp, Discord, and many more. The first solo AI agency to rule them all 🦎
Local-first permission gateway for AI agents: connector-based SSH, Postgres, and Redis access with scoped tokens, human approval, audit logs, and encrypted local credentials.
Pi Arcweld, an auditable local workspace for Pi: pinned upstream source, curated extensions, bounded MCP tooling, and a reproducible external runtime (pi-arcweld)
A fully local, zero-config Mem0 memory server for MCP clients on macOS — no LLM, no API key, no cloud. The client is the brain; on-device embeddings + Chroma, auto-managed launchd lifecycle.
Offline MCP server for AI coding agents with semantic code search, symbol intelligence, dependency graphs, and safe file operations.
面向个人漫画创作者的开源漫画工作台，支持故事与资产管理、页面与画格编排、预览与导出，并通过 MCP + Skill 接入外部 AI Agent。
A local-first permission firewall and approval layer for AI agent tool calls.
Willow 2.0 — local-first memory, MCP tools, and fleet coordination for AI agents. Postgres KB, Ollama default, Grove LAN remote.
MCP-сайдкар с обязательным ревью для Markdown-баз и входящих материалов
Compression Runtime for Universal eXecution — a 60–95% token reducer for AI coding agents (Claude Code, Cursor, Cline, …). Single Rust binary, SQLite, 11 layers, local-first.
Drop-in MCP proxy for debugging AI agents. Real-time timeline, replay, diff. Local-first, no telemetry, one binary.
Public distribution surface for jarvis — local-first code intelligence MCP server (SCIP navigation + Zoekt search). Installer, Claude Code / Codex / Cursor plugins, and prebuilt binaries.
Stay sharp while your AI does the work — local MCP coach that teaches one concept per task.
Personal-use MCP server that gives Microsoft 365 Copilot real hands on your own laptop: files, Python, Office, SQL, Web. 100+ tools, autonomous relay, easily extensible, no extra licences.
🧠 Local-first AI memory OS — a shared knowledge graph for Claude, Cursor, Cline and any MCP client. Not just storage: it spots your blind spots and challenges your thinking. 25 MCP tools, fully offline.
🧠 내 AI에게 '나'를 기억시키는 로컬 second-brain — 결정의 선택·이유·전제를 .md 노트로 남기고, MCP로 어떤 AI 앱(Claude Code·Desktop·Cursor)에서든 꺼내 쓰는 개인 기억 계층. 전부 로컬(Ollama 임베딩)·오픈소스.
Full CBCT + 2D radiograph viewer from a board-certified oral and maxillofacial radiologist: 8 reading modes, local-first, open source. Also the first viewer AI agents can drive natively (MCP).
No-code, local-first studio for building and running production ready AI agents. Inference runs on your machine — llama.cpp, MLX, or vLLM — or any OpenAI-compatible API you register
Render agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.
The agent-first social media planner: an AI agent drafts and schedules posts across Instagram, Facebook, LinkedIn, YouTube, X, Telegram, Discord, Mastodon, Nostr, WordPress, Ghost, and more, behind a human approval gate you control. Free, open source (MIT), local-first, MCP-native.
A tamper-evident, local-first audit trail for AI-agent work — an MCP server with typed tools behind workflow gates and a signed, hash-chained log anyone can verify without a secret.
Local filesystem MCP server with 44 tools: safe delete, process management, interactive sessions, async search, OCR, ZIP, Markdown/PDF export, and cloud-lock-safe operations.
Project-local MCP memory server for AI coding agents. Knowledge graph stored in .mcp/ inside each repo — isolated per project, Git-friendly JSON, dual-buffer (durable graph + active context).
Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.
Local graph memory for AI coding agents, giving MCP-compatible tools precise codebase context before they edit.
Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
Local-first RAG engine with cited answers from your own docs. GraphRAG, sealed sharing, MCP-native, VS Code Copilot integration. Nothing leaves your machine.
Open-source context layer for LLM agents — a single Rust binary served over MCP that feeds Claude, ChatGPT, Codex or any MCP client the facts, decisions & history they need. Local-first, on-device embeddings, hybrid BM25 + vector + graph retrieval. Apache-2.0.
Turn your ChatGPT conversations into safe, auditable local execution. PatchWarden lets you discuss ideas and plans with ChatGPT, then hand the approved plan to local AI agents for guarded, traceable implementation—with scoped permissions, independent verification, and a complete execution record.Turn your ChatGPT conversations into safe, auditable
A local, agent-queryable mail intelligence layer — progressive mailbox index + MCP server that gives AI agents recall over your email without handing them the keys.
Local MCP server that captures the why behind your code — domain knowledge for Claude, Cursor, Copilot, and any MCP agent.
Local MCP server that exposes your Apple Health data (synced to your Mac by the HealthMirror iOS app) to AI tools like Claude — runs locally, no network access.
Local-first terminal AI coding agent with resumable sessions, memory, Skills, MCP, and DeepSeek/OpenAI Codex support.
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
Local-first MCP memory & context-handoff server — capture context in one AI tool, resume it in another. Graceful decay, no cloud.
An AI organism - the human-AI interface layer. A safety reflex that refuses known lethal actions even when the model is fooled, and a memory that only keeps what actually worked. For code, research, writing, or a fleet of agents. 100% local.
Persistent, local-first memory for Claude Code, Codex, Cursor, Gemini CLI, OpenClaw and any MCP agent — cited Markdown, bitemporal history, no hosted account.
Persistent, local-first memory for AI coding agents. Give Claude Code and Cursor memory across sessions over MCP — and see and edit exactly what your AI remembers. Open source, no API key, no cloud.
MCP control surface for Orcho's durable AI software delivery lifecycle
One config, one credential set, one MCP endpoint — shared by Claude Code, Cursor, Codex and 9 more. Local-first, zero telemetry.
Local-first memory for AI agents. Stays on your machine, stays yours.
Local CLI and daemon for supervising collaboration between Claude Code, Codex, Grok, Gemini, and other AI coding agents over MCP. Supports work directory sandboxing preventing unexpected writes by reviewing agents.
Self-hosted, local-first AI assistant server: swappable LLM providers, review-gated memory, an encrypted vault, and wake-word voice. No accounts, no telemetry.
Local-first secrets manager for macOS. Encrypted vault, menu bar app, CLI, and an MCP server that loads secrets into your coding agent's shell instead of the chat. No cloud, no account, no subscription.
Local-first MCP server for shared memory, reservations, handoffs, and review evidence across AI coding agents.
Portable hybrid (BM25 + dense + RRF) retrieval engine and a label-free evaluation harness — extracted from a personal AI-assistant memory index and decoupled to run on any source tree.
Governed memory for long-lived coding agents. Trust, provenance, conflict detection. Local-first.
Local-first, fully offline AI assistant for an NGO's case data. A local Ollama model answers only through MCP tools, with full provenance in the UI. Nothing leaves the machine.
Unofficial Eight Sleep MCP server — give your AI agent your smart-mattress sleep trends, temperature program and alarms, with an explicit mutation gate for write actions. Part of Delx Wellness.
Research intake that reaches the hard places: web, video, papers, scanned PDFs, browser, OCR, and audio into structured research packets. DOM extraction and change tracking built in; provenance rides along on every item.
Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever - even when the API is down.
Notes die in folders. Stellavault keeps your knowledge alive — 3D knowledge graph, AI semantic search, memory decay tracking, P2P federation, 17+ MCP tools. npm i -g stellavault
Persistent identity and memory across AI tools - mcp-native, local-first, framework-agnostic, production-ready.
Free local MCP hub for connecting AI clients to multiple WordPress MCP servers.
A governed control plane for AI agents — approval before action, budget before spend, receipts after every run. Local + cloud.
Developer-focused MCP server with 22 tools for code analysis, Python editing, JSON repair, imports, encoding, Markdown/PDF export, diffs, and regex testing
Local-first temporal knowledge graph memory for AI agents. Runs with Ollama — no API keys required. Single Go binary + SQLite. Hybrid search, MCP server, REST API, interactive TUI.
Native, local-first MCP bridge for safe, editable procedural materials in Material Maker 1.7 and Godot 4.7.
Own your AI memory, don't rent it. A native Claude Code skill AND a standalone, zero-dependency MCP server over one local SQLite file. git clone and go — full-text knowledge graph, plain-markdown, you own the data.
Local-first multilingual memory for Codex, Claude Code & MCP — auditable Qdrant recall, project isolation, and a single-instance desktop tray.
A memory for your AI coding assistant. It keeps what you tell it and hands the right note back at the moment it matters. Runs entirely on your own machine.
Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.
Unofficial MCP server for Google Ads — campaign management, keyword/bid optimization, budget control, daily reports. Local-first, OAuth-based, mutations gated by env var.
Persistent engineering memory for coding agents over MCP.
Apple Health MCP server: query 190 HealthKit metrics from Claude, ChatGPT, Cursor, OpenClaw, Hermes & any AI agent — zero-dependency, local-first.
The local-first brain for coding agents: project memory + workflow intelligence + lossless ~50% context savings. MCP server + LLM proxy, zero cloud.
Free, local, open-source MCP server that audits your ClickUp, Slack & Teams for what fell through the cracks — stale tasks, dropped promises, decisions lost in DMs. No account, no telemetry. Works in Claude, Cursor, Codex, Cline, Zed.
Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.
Local-first AI desktop workbench with chat, documents, agents, skills, pipelines, channels, and MCP servers.
Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).
Persistent layered memory MCP server for AI agents — SQLite + FTS5 + vector hybrid search (RRF), multilingual, zero-cloud
Codex Vision is a macOS-only Codex plugin that lets a local Codex session request live camera frames through an explicit MCP tool. It packages a native AVFoundation capture app, compliant plugin metadata, install scripts, and docs so Codex can clone, build, install, and use laptop-camera vision without cloud camera services or browser hacks. Local.
Unofficial local-first Withings MCP server for AI health, sleep and activity agents.
Give any AI assistant real architectural understanding of a codebase — local, private, zero-config MCP serve
Local-first MCP server that gives sandboxed Codex a narrow, auditable Git workflow surface.