Image & video
Refs
Video reference library that turns launch films and explainers into blueprints and prompt recipes Claude and other agents can build from.
What Refs does
Refs is a library of video references prepared for AI coding agents. It collects launch films, motion pieces and explainers, measures each one cut by cut, and turns it into a blueprint and a prompt recipe that an agent such as Claude can build from. The homepage counts 3,199 films, 70,762 shots measured and 28 formulas.
Each film gets a measured cut timeline with shot boundaries, cuts per minute and average shot length. A blueprint has 15 plates, running from the hook in the first seconds to a final plate about swapping in your own story. Formulas group what strong films of one format have in common. Recipes are prompts meant to be pasted into Claude Code; the sample on the homepage asks for a showreel built with Remotion.
Refs does not host the footage. Every film plays from its original post on X or YouTube, and the pricing page says you pay for the measurements, blueprints, formulas and recipes.
Pro subscribers can add the Refs MCP server to Claude Code with one command, and the site also names Codex and Cursor. The server exposes tools to search the library, fetch blueprints and frames, plan a video from up to five references and score a render against a reference. Searching is free, while pulling content out costs credits.
Refs suits developers and designers who make product videos with code tools like Remotion and want their agent to work from studied examples.
- Studying the pacing and shot structure of product launch films
- Giving a coding agent a blueprint and recipe to build an original video
- Planning a video from a brief and one to five reference films
- Checking a finished render against a reference
Who should use it
- Developers who build videos with Claude Code and tools such as Remotion
- Designers who want measured references for motion and launch films
Who should look elsewhere
- People who need stock footage to reuse, since Refs does not rehost video
- Free users who want MCP access, which is a Pro feature
Strengths
- Every film has a measured cut timeline with shot-level data
- Blueprints, formulas and recipes are written for agents to act on
- MCP server installs into Claude Code with one command
- Search and formula listing through the MCP do not cost credits
Limitations
- Free tier shows only blueprint plates 01 to 02
- MCP access requires Pro and is metered in credits that reset monthly
- The connect page shows setup steps only for Claude Code
- No standalone documentation site was found
Privacy notes
The privacy page says Refs stores your email address to sign you in and does not sell personal data or run third-party advertising trackers.
Sources
- Refs: give Claude better referencesOfficial sitePrimaryrefs.video
- Pricing · RefsPricing pagePrimaryrefs.video
- refs.video/connectWeb
- refs.video/privacyWeb
Refs alternatives
ngram
Image & video
AI video generator that turns a prompt or screen recording into onboarding, training, demo and explainer videos for teams.
FreemiumFree tierAPIVerifiedWeftCut
Image & video
A free, open-source desktop video editor that AI agents drive over MCP while you watch each edit and can undo it.
Open sourceFree tierVerifiedRunway
Image & video
Web and mobile app plus API for generating and editing AI video, images and audio with Runway's Gen-4.5 and other models.
FreemiumFree tierAPIVerifiedDescript
Image & video
Audio and video editor where you edit a recording by editing its transcript, with AI tools for cleanup, clips and translation.
FreemiumFree tierAPIVerified
Related open-source projects
codebase-memory-mcp is an MCP server, written in C, that parses a code repository into a knowledge graph so an AI coding agent can ask structural questions (what calls this function, which HTTP routes exist, what a change affects) instead of reading files one by one. It ships as one native executable for macOS, Linux and Windows. Parsing uses tree-sitter grammars compiled into the binary, and the README lists 162 languages. A hybrid LSP layer adds type resolution for a smaller set, including Python, TypeScript, Go, Java and Rust. Agents reach the graph through 17 MCP tools covering search, call tracing, architecture overviews, change detection, Cypher queries and architecture decision records. A 3D graph viewer is built into the binary and opens at localhost:9749. The installer finds supported agents on your machine and writes their MCP configuration; the README counts 45 client surfaces, among them Claude Code, Codex, Gemini CLI, Cursor and Windsurf. The authors describe the design in an arXiv preprint and report 83% answer quality with 10 times fewer tokens than file-by-file exploration across 31 repositories. Indexing and queries run locally without an API key.
- Stars
- 46K
- Language
- C
- License
- MIT
- Momentum
- +1.6% 7dEstablished
VoiceStudio is a desktop app that runs speech AI on your own computer: it clones and designs voices, generates speech from text, dubs videos, transcribes audio and has a dictation widget. The app is built on Electron with a Python backend. Its default speech engine is k2-fsa's OmniVoice, and the feature catalog lists more than a dozen alternatives, among them CosyVoice 3, KittenTTS, MLX-Audio and IndexTTS 2.5. Transcription defaults to WhisperX, with Faster-Whisper, Parakeet, Moonshine and others available. Models are downloaded when a workspace first needs them. The project says its tools cover 646 languages, a figure that also appears in the transcription tool of its MCP docs. Beyond the desktop workspaces, VoiceStudio exposes a local API and an MCP server on port 3900, so coding agents can generate speech, clone a voice or transcribe a file. The README states that local workflows stay on your hardware, remote workers are optional and usage analytics only run with consent. Version 0.5.3 was the last release built on Tauri; current releases are Electron only, and Tauri users have to install the new app separately.
- Stars
- 61K
- Language
- Python
- License
- AGPL-3.0
- Momentum
- +16.0% 7dTrending
qwen-audio-agent is a realtime voice runtime that sits in front of a coding or task agent. You talk to a voice model, longer jobs go to a backend agent while the conversation continues, and when a task finishes its result comes back into the same conversation. The voice side is swappable. Cloud options listed in the README include Qwen Audio 3.0 Realtime, GPT-Live / OpenAI Realtime, Google Gemini Live and Doubao Seeduplex 3.0 Realtime, each needing that provider's API key. Hugging Face Speech-to-Speech and MiniCPM-o 4.5 can run locally. Backend agents connect mostly over ACP: the list covers Qwen Code, OpenCode, OpenClaw and Kimi Code, with Codex and Claude Code joining through an external ACP adapter. You can use it from a WebUI, a terminal TUI or a desktop floating orb on macOS, Windows and Linux. The README also lists parallel background tasks you can query or cancel, cross-session memory, and scheduled reminders. The package is published on npm under Apache-2.0, a technical report is on arXiv, and the repository sits in the QwenAudio GitHub organization.
- Stars
- 2.9K
- Language
- JavaScript
- License
- Apache-2.0
- Momentum
- Emerging
ECC is an open-source system that adds reusable engineering workflows, skills, agents, memory, rules, hooks and security checks to coding agents. Its main path is Claude Code, with guided installation also available for Codex and Kimi Code. The repository also contains adapters for other coding agents, but the project warns that support is not equal across them. The current repository includes 68 agents, 293 skills and 94 legacy command shims. The supplied workflows cover tasks such as planning, testing, implementation, review, build repair, security and architecture. ECC also includes AgentShield integration for scanning agent configuration, prompts, hooks, MCP settings, permissions, secrets and related files. Hooks and memory can enforce checks outside the prompt, store session information and support its continuous-learning system. The easiest starting point is the ecc-universal guided installer. Claude Code setup needs Node.js 18 or newer, Git and Claude Code 2.1 or newer on PATH. The multi-agent installer can configure Claude Code, Codex and Kimi Code in one reviewed flow. Kimi installation is more limited: ECC writes managed project files but does not configure Kimi hooks, model or provider settings, or authentication.
- Stars
- 278K
- Language
- JavaScript
- License
- MIT
- Momentum
- +2.2% 7dEstablished
Related guides
- Weekly digest
The week on HuiaHub: sandboxed agents, RAG tooling and local models
41 new HuiaHub pages this week: sandboxing coding agents, RAG retrieval, local models on Macs and phones, Claude Haiku 5.5 and six how-to guides.
4 min read