Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
lilbee
MCP serversA local model engine with a search engine and web crawler built in. Run your coding agents on your own GPUs, and get cited answers from your files, code, and the sites you crawl. One executable.
git clone https://github.com/tobocop2/lilbee.git -
Browsegrab
MCP serversToken-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
browsegrab@0.1.1 -
laya
Agents & frameworksLaya is an open-source, local-first AI notification command center that aggregates Slack, Gmail, GitHub, Jira, Notion, Outlook, Calendar (and more) notifications using local LLMs via Ollama and LM Studio. Supports cloud models via BYOK.
git clone https://github.com/aayushch/laya.git -
HARTOS
Agents & frameworksAn AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.
git clone https://github.com/hertz-ai/HARTOS.git -
agenticos
MCP serversOpen-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
git clone https://github.com/vstorm-co/agenticos.git -
droid-mcp
MCP serversLet an AI use your Android phone: an app and an SDK with 160+ MCP tools (calendar, SMS, files, camera, notifications, screen control) for Claude Code, Codex, Cursor or on-device models, with approvals on the phone.
git clone https://github.com/stixez/droid-mcp.git -
LumaBrowser
MCP serversLocal AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
git clone https://github.com/amurgola/LumaBrowser.git -
Tellurion
Agents & frameworksMission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an editor that follows their edits, undo for any turn, approvals from your phone and local models. 20+ built-in tools, all on the site below. Built on Ghostty.
git clone https://github.com/steventsvik/Tellurion.git -
metrillm
MCP serversBenchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
metrillm-mcp@0.2.6 -
VRAMGlass
MCP serversLive GPU prices, VRAM requirements and local LLM hardware planning from VRAMGlass.
-
inferbench
MCP serversBenchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
inferbench-cli@0.1.7 -
EdgeBox
Agents & frameworksA fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.
git clone https://github.com/BIGPPWONG/EdgeBox.git -
OGAD
AI repositoriesYour private, on-device personal AI assistant for macOS, Windows and Linux. Chat, create, search files, and connect tools with local models. Includes an OpenAI-compatible API. Opt-in Pro sees, remembers, reflects, and acts with your approval, for one payment. No cloud or account.
git clone https://github.com/off-grid-ai/OGAD.git -
token-compressor
MCP serversCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
token-compressor-mcp@0.1.1 -
Cowork
MCP serversSelf-hosted MCP task inbox shared by Claude Code, Codex, Gemini CLI and local LLMs.
ghcr.io/slashman413/cowork:1.0.2 -
Orma Memory
MCP serversEpisode-first, zero-latency long-term memory for local LLMs and AI coding assistants.
orma-ai@0.1.13 -
Fuuga minion
MCP serversOffline local-LLM helper: delegate simple errands to a local model, with sandboxed file tools.
Fuuga.Server.cpu@1.0.41 -
qsp-client
MCP serversQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
qsp-client@0.5.2 -
qsp-mcp
MCP serversQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
qsp-mcp@0.1.1 -
OCDS German Procurement Search
MCP serversSearch and match German public procurement tenders (OCDS) from your local LLM.
@qune-tech/ocds-mcp@0.4.0 -
TokenMark
MCP serversMeasured local-LLM speeds and model picks for Strix Halo, DGX Spark, Mac and GPU cards.
@altronis/tokenmark-mcp@0.4.1 -
inferock-bench
Datasets & benchmarksLocal LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.
git clone https://github.com/inferock/inferock-bench.git -
m3-memory
MCP serversLocal-first memory backend for AI agents · 99.2% LongMemEval-S retrieval @ k=8 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable
git clone https://github.com/skynetcmd/m3-memory.git -
M1K3
MCP serversPrivate memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.
https://github.com/Round-Tower/M1K3/releases/download/mcpb-v0.1.0/m1k3.mcpb@0.1.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.