Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pi-dynamic-workflows
Agents & frameworksClaude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.
git clone https://github.com/QuintinShaw/pi-dynamic-workflows.git -
whenship
SkillsWhen will it ship, honestly? A tiny planner for small teams: live what-if Gantt, deadline risk and realistic dates. Works in the browser and inside Claude.
git clone https://github.com/HamedShams/whenship.git -
llm-guard
PromptsThe Security Toolkit for LLM Interactions
git clone https://github.com/protectai/llm-guard.git -
aisearch-openai-rag-audio
AI repositoriesA simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
git clone https://github.com/Azure-Samples/aisearch-openai-rag-audio.git -
rai
AI repositoriesRAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.
git clone https://github.com/RobotecAI/rai.git -
blockfrost Cardano
Public APIsInteraction with the Cardano mainnet and several testnets
-
INFURA Ethereum
Public APIsInteraction with the Ethereum mainnet and several testnets
-
Gemini 3.5 Transcribe
ModelsSpeech-to-text with speaker labels and timestamps, for call and meeting notes.
-
UnlimitedTTS
MCP serversQuote-first, non-custodial x402 text-to-speech with spend policy, MP3 artifacts, and receipts.
@unlimitedtts/mcp@0.1.0 -
ElevenLabs
MCP serversManage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
-
toolpiper
MCP serversOn-device MCP tools for macOS: local AI, speech, vision, browser automation, system control.
-
Voicely
MCP serversOffline speech-to-text on macOS: transcribe audio/video files, read dictations and calls.
https://github.com/StulkovLD/Voicely/releases/download/v1.4.2/voicely-1.4.2.mcpb -
ffvoice
MCP serversOffline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
ffvoice@0.8.3 -
live-translate-mcp
MCP serversMCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
live-translate-mcp@0.1.5 -
Talkies
MCP serversSelf-hosted speech server whose MCP endpoint exposes ASR transcription and file staging tools.
docker.io/psyb0t/talkies:v0.17.1 -
SpeechWeave
MCP serversTranscribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.
@speechweave/mcp@1.10.0 -
VoiceLabs
MCP serversAI voice generation: text-to-speech and voice cloning from any MCP client.
-
sweden-parliament-mcp-server
MCP serversSearch Swedish parliamentary documents, speeches, votes, members, and statutes.
@cyanheads/sweden-parliament-mcp-server@0.2.0 -
VocalLab
MCP serversText to speech in 200+ languages, voice cloning, voice design and SRT captions.
-
mcp-kubernetes
MCP serversA Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes
git clone https://github.com/Azure/mcp-kubernetes.git -
regenerator2000
MCP serversAn interactive disassembler for the CPU 6502, focused on Commodore 8-bit computers. Features a TUI with modern features like x-ref, undo/redo, flow arrows, keyboard-driven, MCP server for auto analysis, VICE debugger and more!
git clone https://github.com/ricardoquesada/regenerator2000.git -
Kooma — Bambara AI
MCP serversBambara AI over MCP: text-to-speech, transcription and translation (Bamanankan + more).
-
Wubble
MCP serversCreate, inspect, and manage Wubble music, speech, voice, and sound-effect requests through MCP.
-
Narrivela
MCP serversGenerate English and Chinese speech, split long text, track batch jobs, and download audio.
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.