InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. wavespeed-cli

    Skills

    WaveSpeed CLI — run any image, video, audio or 3D model from your terminal or coding agent: live catalog search, per-model schema introspection, local-file upload, price quotes

    Indexed GitHub, WaveSpeedAI 26 ★MITUpdated yesterday

    git clone https://github.com/WaveSpeedAI/wavespeed-cli.git
  2. 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
  3. memex

    MCP servers

    Local-first second brain with semantic search. Markdown notes indexed by a local ML model.

    Stale Official MCP Registry, io.github.evan-moon Updated 4 months ago 1 note

    @evan-moon/memex@0.5.0
  4. memtomem

    MCP servers

    Long-term memory for AI coding agents, kept as Markdown you own. Hybrid BM25 + vector search over your notes and code via MCP — one local store shared across Claude Code, Codex, Cursor, OpenCode, and more. Hook-free by default.

    Indexed GitHub, memtomem 25 ★Apache-2.0Updated today

    git clone https://github.com/memtomem/memtomem.git
  5. Browser extension & Python WebSocket bridge to connect web-based AI interfaces with local Model Context Protocol (MCP) servers.

    Indexed GitHub, AstraxOf 16 ★Apache-2.0Updated yesterday

    git clone https://github.com/AstraxOf/web-mcp-bridge.git
  6. Model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost check. Free.

    Stale Official MCP Registry, io.github.DinevDecor Updated 2 days ago 1 note

    trust-engine-mcp@0.2.2
  7. mcp-video-analyzer

    MCP servers

    MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.

    Indexed GitHub, guimatheus92 123 ★MITUpdated 2 days ago

    git clone https://github.com/guimatheus92/mcp-video-analyzer.git
  8. kaeru

    MCP servers

    Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.

    Stale GitHub, LamantinAI 73 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/LamantinAI/kaeru.git
  9. llm_for_css

    Docs & tutorials

    Tutorial on using LLM APIs for computational social science research: OpenAI, Anthropic, open-source models via OpenRouter, and local LLMs with Ollama

    Stale GitHub, yang3kc 54 ★MITUpdated 46 days ago

    git clone https://github.com/yang3kc/llm_for_css.git
  10. cerul

    Agents & frameworks

    Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.

    Stale GitHub, cerul-ai 164 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/cerul-ai/cerul.git
  11. deno-mcp-template

    MCP servers

    A template repo for writing and publishing local, remote, DXT, and binary MCP servers using Deno.

    Stale GitHub, phughesmcr 34 ★MITUpdated 9 days ago

    git clone https://github.com/phughesmcr/deno-mcp-template.git
  12. DevWebUI

    MCP servers

    GUI + MCP control plane for your local dev servers. Humans click, agents automate the same daemon.

    Indexed GitHub, LunarWerxs 29 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/LunarWerxs/DevWebUI.git
  13. codebase-context

    MCP servers

    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.

    Stale GitHub, PatrickSys 68 ★Custom licence (see repository)Updated 12 days ago

    git clone https://github.com/PatrickSys/codebase-context.git
  14. windbg-mcp

    MCP servers

    MCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --listen

    Indexed GitHub, glslang 21 ★MITUpdated today

    git clone https://github.com/glslang/windbg-mcp.git
  15. lot-map

    Agents & frameworks

    A live map beside the chat that shows what Claude Code is doing: tool calls, model steps, hooks, skills and subagents light up as they happen. Local only, in five languages.

    Stale GitHub, alexeyw 428 ★MITUpdated 4 days ago

    git clone https://github.com/alexeyw/lot-map.git
  16. nl-veil

    Agents & frameworks

    Open-source AI coding desktop app with parallel agents and persistent project memory. Local models, Ollama or cloud AI. Windows, macOS and Linux.

    Indexed GitHub, gary23w 113 ★MITUpdated 2 days ago

    git clone https://github.com/gary23w/nl-veil.git
  17. Cortex

    Skills

    Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

    Indexed GitHub, cdeust 77 ★MITUpdated today

    git clone https://github.com/cdeust/Cortex.git
  18. Anvil

    MCP servers

    Provider-agnostic AI dev pipeline: clarify → plan → build → review → PR across your repos, mixing LLM providers per stage with your own keys. No vendor lock-in, no markup.

    Stale GitHub, esanmohammad 20 ★MITUpdated 4 days ago

    git clone https://github.com/esanmohammad/Anvil.git
  19. Bring Apple Health to the AI agents you already use. Open-source iPhone app on the App Store, automatic sync to your own computer, and MCP access to your health history—for everyday questions and custom agent workflows.

    Stale GitHub, roian6 30 ★Apache-2.0Updated 14 days ago

    git clone https://github.com/roian6/apple-health-ai-bridge.git
  20. FABULA-LLM-5

    Agents & frameworks

    A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.

    Stale GitHub, sergezuber 82 ★MITUpdated 55 days ago

    git clone https://github.com/sergezuber/FABULA-LLM-5.git
  21. xiryn

    Agents & frameworks

    Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent gets its own Linux desktop in Docker, any model with your keys, an encrypted vault, and control from Telegram.

    Stale GitHub, SouravBeraAkaSpeed 395 ★MITUpdated 14 days ago

    git clone https://github.com/SouravBeraAkaSpeed/xiryn.git
  22. kana

    Skills

    Lightweight, untracked, and self-evolving terminal AI companion. Zero telemetry, durable memory, bidirectional synergy, and native TUI.

    Stale GitHub, longyijdos 8 ★MITUpdated 25 days ago

    git clone https://github.com/longyijdos/kana.git
  23. usagetrim

    MCP servers

    Fast local CLI and MCP tool for compacting verbose test runners and build output.

    Stale GitHub, 00200200 43 ★MITUpdated 23 days ago

    git clone https://github.com/00200200/usagetrim.git
  24. janas

    AI repositories

    37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

    Indexed GitHub, prabanta-dev 717 ★GPL-3.0Updated today

    git clone https://github.com/prabanta-dev/janas.git

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.