Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
wavespeed-cli
SkillsWaveSpeed 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
git clone https://github.com/WaveSpeedAI/wavespeed-cli.git -
Fuuga minion
MCP serversOffline local-LLM helper: delegate simple errands to a local model, with sandboxed file tools.
Fuuga.Server.cpu@1.0.41 -
memex
MCP serversLocal-first second brain with semantic search. Markdown notes indexed by a local ML model.
@evan-moon/memex@0.5.0 -
memtomem
MCP serversLong-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.
git clone https://github.com/memtomem/memtomem.git -
web-mcp-bridge
SkillsBrowser extension & Python WebSocket bridge to connect web-based AI interfaces with local Model Context Protocol (MCP) servers.
git clone https://github.com/AstraxOf/web-mcp-bridge.git -
Model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost check. Free.
trust-engine-mcp@0.2.2 -
mcp-video-analyzer
MCP serversMCP 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.
git clone https://github.com/guimatheus92/mcp-video-analyzer.git -
kaeru
MCP serversCognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
git clone https://github.com/LamantinAI/kaeru.git -
llm_for_css
Docs & tutorialsTutorial on using LLM APIs for computational social science research: OpenAI, Anthropic, open-source models via OpenRouter, and local LLMs with Ollama
git clone https://github.com/yang3kc/llm_for_css.git -
cerul
Agents & frameworksOpen-source video processing core and CLI. Search and annotate local videos with your own model endpoints.
git clone https://github.com/cerul-ai/cerul.git -
deno-mcp-template
MCP serversA template repo for writing and publishing local, remote, DXT, and binary MCP servers using Deno.
git clone https://github.com/phughesmcr/deno-mcp-template.git -
DevWebUI
MCP serversGUI + MCP control plane for your local dev servers. Humans click, agents automate the same daemon.
git clone https://github.com/LunarWerxs/DevWebUI.git -
codebase-context
MCP serversCodebase 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.
git clone https://github.com/PatrickSys/codebase-context.git -
windbg-mcp
MCP serversMCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --listen
git clone https://github.com/glslang/windbg-mcp.git -
lot-map
Agents & frameworksA 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.
git clone https://github.com/alexeyw/lot-map.git -
nl-veil
Agents & frameworksOpen-source AI coding desktop app with parallel agents and persistent project memory. Local models, Ollama or cloud AI. Windows, macOS and Linux.
git clone https://github.com/gary23w/nl-veil.git -
Cortex
SkillsCross-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.
git clone https://github.com/cdeust/Cortex.git -
Anvil
MCP serversProvider-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.
git clone https://github.com/esanmohammad/Anvil.git -
apple-health-ai-bridge
MCP serversBring 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.
git clone https://github.com/roian6/apple-health-ai-bridge.git -
FABULA-LLM-5
Agents & frameworksA 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.
git clone https://github.com/sergezuber/FABULA-LLM-5.git -
xiryn
Agents & frameworksXiryn — 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.
git clone https://github.com/SouravBeraAkaSpeed/xiryn.git -
kana
SkillsLightweight, untracked, and self-evolving terminal AI companion. Zero telemetry, durable memory, bidirectional synergy, and native TUI.
git clone https://github.com/longyijdos/kana.git -
usagetrim
MCP serversFast local CLI and MCP tool for compacting verbose test runners and build output.
git clone https://github.com/00200200/usagetrim.git -
janas
AI repositories37 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.
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.