9x Vision open-sources video perception for agents: timestamped evidence via MCP and CLI
koto9x · x · 2026-10-21
Developer koto9x open-sourced 9x Vision, a vision substrate for AI agents and part of a larger personal project. It lets any MCP-speaking or CLI-capable agent (Claude Code, Codex, Cursor, etc.) ingest video files and URLs, screen recordings, cameras, microphones, screens, or image folders, and get back timestamped, structured evidence instead of a handful of random frames.
Underneath is one substrate: every input becomes the same kind of searchable, cached record, so the same tools work across all media types. The repo ships a Claude plugin, skills, a benchmark, and tests under MIT license.
More from coding & agent
- OpenAI's dots can now use company tools via Merge for Workforce with employee-bound permissions — shensi · 2026-10-21
- The topology of an LLM agent: where the model, loop, and tools run shapes cost and security — davidcrawshaw · 2026-10-21
- Agents with full-disk and accessibility access are an enterprise security nightmare, argues Runlayer — leveragedupside · 2026-10-21
- Acellera runs an unsupervised virtual lab of AI scientists on a real IL-23 molecular discovery program — gdefabritiis · 2026-10-21
- Pydantic author experiments with JS/TS and React support in the Monty sandbox — samuelcolvin · 2026-10-21
- Supabase lets coding agents query your logs to catch errors and slow queries — dshukertjr · 2026-10-21