# video-db/Director

AI video agents framework for next-gen video interactions and workflows.

Repository: https://github.com/video-db/Director
Canonical: https://ross.abutalabs.com/products/director
Homepage: https://chat.videodb.io
Language: Python
License: MIT
License Family: permissive
Topics: agent, framework, llm, openai, rag, search, video-editing, video-processing, agent-framework, ai-agents, text-to-video, videodb
Last push: 2026-01-23T15:34:16+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 8, longevity 49
- inputs: {"age_days": 688, "days_push": 222, "days_rel": 638, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1517, forks 251 (observed 2026-08-28T04:04:57.385285+00:00)

## What it is
Director is a Python framework for building AI video agents that reason over complex video tasks like search, editing, compilation, and generation, streaming results instantly. It is built on top of VideoDB's video-as-data infrastructure and orchestrates multiple agents from natural language commands.

## Use cases
- build ai agents that edit videos from natural language commands
- summarize long videos automatically
- search for specific moments inside video libraries
- auto-generate highlight clips and send them to slack
- create videos from text prompts
- add overlays and extract frames from footage programmatically

## When to choose
- you want to build conversational video workflows on top of VideoDB
- you need agents that combine video search, editing, and generation
- you want to orchestrate GenAI APIs for media processing

## When to avoid
- you need a standalone video editor GUI
- you don't use VideoDB or want a vendor-independent pipeline
- you need non-video LLM agent orchestration

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, video-processing, search-engine, rag, llm-inference, chatbot
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted
- tags: video-agents, video-editing, text-to-video, videodb, video-search, streaming-results, ai-agents, video, web-server

## Member repositories
- video-db/Director (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:57.385285+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:04.882831+00:00, confidence not recorded.
  - readme: https://github.com/video-db/Director (fetched 2026-08-28T04:04:57.385285+00:00, sha 6211676aa4ad)
  - homepage: https://chat.videodb.io (fetched 2026-08-29T11:35:31.577292+00:00, sha 623129801716)
- Data as of 2026-08-30T08:39:29.467469+00:00.