Side-by-side comparison · mcp servers
agenthook vs claude-real-video
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
MCP Servers
agenthook
Your agent makes character-consistent UGC video. Create one AI influencer, reuse that same face in every clip, image, and caption. Add it as a skill, CLI, or MCP server.
MCP Servers
claude-real-video
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Checked facts
Line by line
| Measure | agenthook | claude-real-video |
|---|---|---|
| Security check (static checks) | 100 out of 100 | Not checked yet |
| Days since the last commit | 122 | 25 |
| GitHub forks | 0 | 207 |
| GitHub stars | 2 | 2,323 |
| Open issues | 0 | 3 |
| Releases in the last 90 days | 0 | 7 |
| Days to a first reply on issues | Not checked yet | 0.9 |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.