AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Vision / Multimodal/
vidxp
vidxp logo

vidxp

Active·★ 59·MIT·Updated 2026-10-21

VidXP is a local-first video search engine designed for people, applications, and AI agents. It enables users to search videos by what was said, what appeared on screen, and by identifying recurring faces within a video.

#Video Search#Multimedia Indexing#AI Agents#Local-First#Content Understanding#Face Recognition#Speech Recognition
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#CLI Tool
$ Install
$ uv tool install --python 3.14 --torch-backend cpu "vidxp[local-worker,mcp]" && vidxp init && vidxp prepare && vidxp doctor
↗ Visit site★ GitHub
01

Features

01Dialogue search for specific spoken words or phrases.
02Scene search based on visual descriptions of on-screen content.
03Actor matching to find and highlight recurring faces in videos.
04Ability to build reusable search libraries from single or multiple videos.
05Export downloadable clips and overlays from matching timestamps.
02

Compatibility

Python
Runtime
Verified via docs
Windows
OS
Verified via docs
macOS
OS
Verified via docs
Linux
OS
Verified via docs
Docker
Container
Verified via docs
03

Quick start

1
$ uv tool install --python 3.14 --torch-backend cpu "vidxp[local-worker,mcp]"
2
$ vidxp init
3
$ vidxp prepare
4
$ vidxp doctor
04

Use cases

↳Search through years of personal or family videos to find specific moments.
↳Integrate advanced video search capabilities into an existing video editing workflow.
↳Enable AI agents to answer questions using factual evidence directly from video libraries.
↳Automate video analysis and clip extraction through CLI or API for application integration.
↳Manage and organize large personal or project video collections with meaningful search.
05

Alternatives

⚡Top VS:
VSCrossGen★13→VSOpenChatCut★2.6k→VSpaperbanana★2.4k→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
kiln
★291
→
CrossGen logo
CrossGen★ 13
Local-first AI image workspace for people and agents. Generate, edit, organize, and reuse images through the desktop app, JSON CLI, or MCP.
VSCompare→
OpenChatCut logo
OpenChatCut★ 2.6k
Local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.
VSCompare→
paperbanana logo
paperbanana★ 2.4k
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
VSCompare→
kiln logo
kiln★ 291
Build and revise procedural 3D assets with your coding agent. Local MCP server, CLI and TypeScript engine with rendered review, editable source and GLB export.
VSCompare→
z-image-studio logo
z-image-studio★ 128
A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
VSCompare→
mcp-video-analyzer logo
mcp-video-analyzer★ 102
MCP server for video analysis — extracts transcripts, key frames, OCR text, and metadata from video URLs. Supports Loom and direct video files.
VSCompare→
vision-memory-mcp logo
vision-memory-mcp★ 49
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
VSCompare→
claude-image-gen logo
claude-image-gen★ 77
AI-powered image generation using Google Gemini, integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).
VSCompare→
See all alternatives →
grayhatdevelopers /
vidxp
↗

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

59MIT
Last commit2d ago
StatusActive
CategoryVision / Multimodal
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit