MCP servers and skills: search, filter by where they run, and compare.
Transcript timestamp-aligned speech filler word remover & cutlist generator (Descript / Cleanvoice)
MCPLink only★ 8
Transcript timestamp-aligned speech filler word remover & cutlist generator (Descript / Cleanvoice)
MCPLink only★ 8
A modular, multiprocessing voice assistant built with Python. This project integrates the Model Context Protocol (MCP) to allow the LLM to execute tools and interact with external systems. It features
SkillMIT★ 4Few starsNo key
VP2026 voice-privacy research toolkit for AI coding agents. Domain-aware markdown skills + bash. Works with Claude Code, Codex, and Cursor. Auto-activates on voice-anonymization projects.
MCPLink only★ 2Few stars
Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, a
OfficialSkillMIT★ 40k in collectionNo key
Recordings in. Agent-ready evidence out. Local-first MCP for transcripts, keyframes, OCR, speakers, and wall-clock evidence.
PythonMIT★ 32No key
An open-source, modular pipeline for translating manhua pages. Detect speech bubbles, extract text with OCR, translate using LLMs, and regenerate localized pages while preserving the original reading
SkillAGPL-3.0★ 7No key
Drop raw clips in a folder, get silence-cut, subtitled video. Subtitles in 90+ languages (auto-detected), filler-word removal, runs locally. Claude Code plugin + CLI.
SkillMIT★ 1Few starsNo key
Online Video Agent Harness for Long Video Understanding.
SkillApache-2.0★ 2Few starsNo key
lightweight MCP server for universal document ingestion into parsable Markdown
PythonMIT★ 2Few starsNo key
Turn iPhone voice notes into safe, reviewable updates in a Git-backed Markdown vault.
SkillMIT★ 2Few starsNo key
MCP server to help me edit media like video files and audio files for various purposes
PythonMIT★ 1Few starsNo key
An evidence-backed Agent Skill that turns video links into structured Markdown analysis.
SkillMIT★ 2Few starsNo key
Record meetings on your iPhone. Audio and transcripts land in a folder you own, ready for whatever assistant you already use. Fully on-device, no network calls.
SkillMITFew starsNo key
Local MCP toolkit for AI agents: OCR, speech recognition, vision, document conversion, and browser automation with self-hosted local runtimes.
SkillMITFew starsNo key
These are the project files that were created for my capstone project for the 5 Days Intensive Agentic Coding course. The course was offered by Kaggle
SkillMIT★ 1Few starsNo key
RAG-Sandbox is a comprehensive, multi-tenant Agentic RAG (Retrieval-Augmented Generation) platform that redefines how users interact with their data. It moves beyond simple text retrieval to offer a f
SkillMITFew starsNo key
WordCast is a browser-based text-to-speech reader that converts written content into audio entirely on your device. There is no backend server involved: text, files, and URLs are processed locally usi
SkillMITFew starsNo key
Who stands behind it
