Build agents with visual intelligence
Your agent can watch video. Upload or stream it, then ask for the moment you need.
1,000+ developers and agents use VideoDB every week. 300+ TB of video processed.
Any MCP clienthttps://mcp.videodb.io/mcp
Teams that have built on VideoDB
- 100,000 hourschecked and cut into training samples in under a week for one of the largest video data providersRead the case study
- 3 weeksfrom recordings to a first computer-use agent for a Big Four accounting firm’s capability centersRead the case study
- 2×the next pipeline’s score on a 100-hour action retrieval benchmark, when the clip must line up with the actionSee the benchmark
Add VideoDB to the agent you already use
It takes about a minute. Then paste a link or upload a file and ask.
Claude Code
Two commands in the terminal.
/plugin marketplace add video-db/skills
/plugin install videodb@videodb-skillsCursor, Codex or any MCP client
Add one URL as a remote server.
https://mcp.videodb.io/mcpWhat agents do with VideoDB
| Agent | Asked | What comes back |
|---|---|---|
| Archive agents | Cut three Shorts from this podcast. |
search_video 3 momentsreframe_video vertical clips, 9:16 |
| Computer-use agents | What did the agent click before the error? |
search_video Submit invoice, 14:02:11 |
| Physical agents | Where did you last see the blue bottle? |
search_rtstream kitchen counter, 09:41:07 |
| Research agents | Two arms picking up objects in a kitchen. |
dataset_search episodes from 9 datasetsexport_result_set LeRobot files |
| Fleet agents | A cyclist cutting across at dusk. |
search_collection clips with drive, time and camera |
Memory for agents and physical devices
Everything a camera, a screen or a file shows goes into an index as it arrives. A task gets back only the frames it needs.
Read how a robot remembersFirst on a 100‑hour action retrieval benchmark
VideoDB finds a matching clip for more queries than any other pipeline tested, on an open dataset with 11,369 queries.
Read the benchmarkQueries with a matching clip in the top 10
- VideoDB
- AWS Nova
- Twelve Labs Marengo 3.5
- SigLIP2
- Cosmos-Embed
- Qwen3-VL Embedding
- InternVideo2
- PE-AV
From your files to your agent
Storage, search and streaming for video, in one system.
-
Files stay where they are
Buckets, cameras and screens, read in place.
-
Indexed by what happens
Any model describes every scene. Search runs on what it writes.
-
Frames on request
About half a second from a question to the frames.
Runs onAWSGoogle CloudAzureor your own cloud
Open-source agents to start from
5,000+ stars on GitHub. Each repo runs on VideoDB and is free to fork.
VideoDB on GitHub| Repository | What it does | Stars |
|---|---|---|
| call.md | Meetings as live agent loops: recording, transcription and analysis while the call runs. | 1,975 |
| Director | A framework for AI video agents: reason over a video, then act on it. | 1,566 |
| StreamRAG | A video search agent for ChatGPT. | 503 |
| Bloom | An open-source, agentic screen recorder. Recordings become inputs for AI. | 235 |
What builders say
For a long time, I have been thinking what you are building needs to exist! Glad you are building it!
VideoDB team, nice work! Would love to chat!
VideoDB is cool!
Try it on your own video
$20 of free credits and no credit card. Add it to Claude, or tell us about the video you have.


