Privacy and advertising choices
Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy
Edit videos with coding agents
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
Problem solved
Traditional video editing requires manual timeline manipulation or preset-based tools, which are slow and inflexible. video-use bridges the gap by giving LLMs a structured, token-efficient representation of video (transcript + visual composites) so they can make precise editorial decisions and execute them via ffmpeg, enabling fully automated, conversational editing.
Deployment reality
The available setup signal starts with: git clone https://github.com/browser-use/video-use ~/Developer/video-use && ln -sfn ~/Developer/video-use ~/.claude/skills/video-use && cd ~/Developer/video-use && uv sync && brew install ffmpeg. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.
Commercial use
The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.
Capability ceiling
Developers can build automated video editing pipelines for talking heads, tutorials, travel vlogs, interviews, and more. The framework supports filler-word removal, auto color grading, subtitle burning, animation overlays (via HyperFrames, Remotion, Manim, or PIL), and self-evaluation loops. The ceiling is high: with custom ffmpeg chains and parallel sub-agents, users can create complex, stylized edits from raw footage with minimal human intervention.
Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.
browser-use/video-use is tracked as a Python project in the AI Agent area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.
Momentum check: the repository has 19k total stars, with +320 today, +0 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.
Maintenance check: current activity is Moderate; the latest push was 53 days ago, and the open issue queue is 60, about 0.31% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.
Adoption check: 2.4k forks and 19k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.
Practical fit: this project is most relevant when you need Python teams evaluating ecosystem-native tooling. Be cautious when you need a legal review, security audit, or production SLA.
Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 320. Follow the original GitHub repository for final install, security, and release information.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyMIT is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
19k Stars
Reuse
2.4k Forks
Attention
19k Watchers
Maintenance
moderate
License
MIT
Open issues
60
video-use is an open-source tool that enables editing videos through natural language conversations with Claude Code or other AI agents. It processes raw footage, applies professional edits like filler word removal, color grading, subtitles, and animations, and outputs a final video file.
Key Features
- Cuts filler words and dead space, auto color grades, adds audio fades, burns subtitles, and generates animation overlays. - Self-evaluates rendered output at cut boundaries and persists session memory in project.md. - Works with any content type and integrates with multiple AI agents.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
git clone https://github.com/browser-use/video-use ~/Developer/video-use && ln -sfn ~/Developer/video-use ~/.claude/skills/video-use && cd ~/Developer/video-use && uv sync && brew install ffmpeg70
Health Score
Moderate
Commit Activity
Apr 12, 2026
Created
Jul 1, 2026
Last push
+0
Today's growth
+0
7-day growth
+0
30-day growth
Forks
Open
Watchers
browser-use
GitHub profileobra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
anomalyco/opencode
The open source coding agent.
✓
License
✓
Forked
~ Moderate
Maintained
Problem Solved
Traditional video editing requires manual timeline manipulation or preset-based tools, which are slow and inflexible. video-use bridges the gap by giving LLMs a structured, token-efficient representation of video (transcript + visual composites) so they can make precise editorial decisions and execute them via ffmpeg, enabling fully automated, conversational editing.
Capabilities
Developers can build automated video editing pipelines for talking heads, tutorials, travel vlogs, interviews, and more. The framework supports filler-word removal, auto color grading, subtitle burning, animation overlays (via HyperFrames, Remotion, Manim, or PIL), and self-evaluation loops. The ceiling is high: with custom ffmpeg chains and parallel sub-agents, users can create complex, stylized edits from raw footage with minimal human intervention.
Bottom Line
video-use is ideal for content creators, developers, and teams who want to automate video editing using AI agents and are comfortable with command-line tools and API keys. It's not for non-technical users or those needing pixel-perfect manual control. The key trade-off is token efficiency and automation versus the loss of fine-grained manual editing and reliance on external services like ElevenLabs.