InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. lilbee

    MCP servers

    A 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.

    Stale GitHub, tobocop2 70 ★MITUpdated 4 days ago

    git clone https://github.com/tobocop2/lilbee.git
  2. Browsegrab

    MCP servers

    Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

    Stale Official MCP Registry, io.github.ArkNill Updated 8 months ago 1 note

    browsegrab@0.1.1
  3. laya

    Agents & frameworks

    Laya 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.

    Stale GitHub, aayushch 765 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/aayushch/laya.git
  4. HARTOS

    Agents & frameworks

    An 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.

    Indexed GitHub, hertz-ai 52 ★Apache-2.0Updated today

    git clone https://github.com/hertz-ai/HARTOS.git
  5. agenticos

    MCP servers

    Open-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.

    Indexed GitHub, vstorm-co 336 ★Apache-2.0Updated today

    git clone https://github.com/vstorm-co/agenticos.git
  6. droid-mcp

    MCP servers

    Let 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.

    Stale GitHub, stixez 42 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/stixez/droid-mcp.git
  7. LumaBrowser

    MCP servers

    Local 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.

    Indexed GitHub, amurgola 144 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/amurgola/LumaBrowser.git
  8. Tellurion

    Agents & frameworks

    Mission 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.

    Indexed GitHub, steventsvik 142 ★AGPL-3.0Updated 4 days ago

    git clone https://github.com/steventsvik/Tellurion.git
  9. metrillm

    MCP servers

    Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

    Stale Official MCP Registry, io.github.MetriLLM Updated 8 months ago 1 note

    metrillm-mcp@0.2.6
  10. VRAMGlass

    MCP servers

    Live GPU prices, VRAM requirements and local LLM hardware planning from VRAMGlass.

    Stale Official MCP Registry, com.vramglass Updated 25 days ago 1 note

  11. inferbench

    MCP servers

    Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

    Stale Official MCP Registry, io.github.RudrenduPaul Updated 3 months ago 1 note

    inferbench-cli@0.1.7
  12. EdgeBox

    Agents & frameworks

    A 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.

    Stale GitHub, BIGPPWONG 212 ★GPL-3.0Updated 6 months ago

    git clone https://github.com/BIGPPWONG/EdgeBox.git
  13. OGAD

    AI repositories

    Your 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.

    Indexed GitHub, off-grid-ai 147 ★AGPL-3.0Updated yesterday

    git clone https://github.com/off-grid-ai/OGAD.git
  14. token-compressor

    MCP servers

    Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

    Stale Official MCP Registry, io.github.base76-research-lab Updated 8 months ago 1 note

    token-compressor-mcp@0.1.1
  15. Cowork

    MCP servers

    Self-hosted MCP task inbox shared by Claude Code, Codex, Gemini CLI and local LLMs.

    Indexed Official MCP Registry, io.github.slashman413 Updated yesterday 2 notes

    ghcr.io/slashman413/cowork:1.0.2
  16. Orma Memory

    MCP servers

    Episode-first, zero-latency long-term memory for local LLMs and AI coding assistants.

    Stale Official MCP Registry, io.github.wizardwithcodehazard Updated 15 days ago 1 note

    orma-ai@0.1.13
  17. Fuuga minion

    MCP servers

    Offline local-LLM helper: delegate simple errands to a local model, with sandboxed file tools.

    Stale Official MCP Registry, io.github.Thorium Updated 33 days ago 1 note

    Fuuga.Server.cpu@1.0.41
  18. qsp-client

    MCP servers

    QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

    Stale Official MCP Registry, io.github.qso-graph Updated 8 days ago 1 note

    qsp-client@0.5.2
  19. qsp-mcp

    MCP servers

    QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

    Stale Official MCP Registry, io.github.qso-graph Updated 49 days ago 2 notes

    qsp-mcp@0.1.1
  20. Search and match German public procurement tenders (OCDS) from your local LLM.

    Stale Official MCP Registry, io.github.qune-tech Updated 7 months ago 2 notes

    @qune-tech/ocds-mcp@0.4.0
  21. TokenMark

    MCP servers

    Measured local-LLM speeds and model picks for Strix Halo, DGX Spark, Mac and GPU cards.

    Stale Official MCP Registry, io.github.sypherin Updated 24 days ago 1 note

    @altronis/tokenmark-mcp@0.4.1
  22. inferock-bench

    Datasets & benchmarks

    Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

    Stale GitHub, inferock 107 ★Custom licence (see repository)Updated 3 months ago

    git clone https://github.com/inferock/inferock-bench.git
  23. m3-memory

    MCP servers

    Local-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

    Stale GitHub, skynetcmd 30 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/skynetcmd/m3-memory.git
  24. M1K3

    MCP servers

    Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.

    Indexed Official MCP Registry, app.m1k3 Updated today 1 note

    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.