Skip to content
@mixpeek

Mixpeek

Mixpeek makes the world's unstructured data programmable. The multimodal warehouse for AI.

Mixpeek

Turn any data into answers.

The multimodal warehouse for AI. Extract, index and retrieve what's inside
video, images, audio and documents. Skip the infrastructure.

Docs · Get Started · Quickstart · Blog ·


What is Mixpeek?

Mixpeek makes any data searchable by AI. Upload video, images, audio and documents, and Mixpeek extracts features (faces, objects, transcripts, embeddings, structured metadata) and indexes them into searchable collections. Your app or agent queries a single endpoint and gets structured results back. Already have embeddings? Bring your own vectors and search them on object storage with MVS.

Index → Upload files to buckets. Mixpeek runs feature extraction automatically, indexing faces, objects, transcripts, embeddings and structured metadata.

Search → Build retrieval pipelines. Chain semantic, face, object and transcript search into multi-stage retrievers exposed as a single endpoint.

Integrate → Wire Mixpeek into your agent as a LangChain tool, an MCP server, or a direct REST call.

Quickstart

pip install mixpeek
from mixpeek import Mixpeek

mx = Mixpeek(api_key="YOUR_API_KEY")

# Upload a video
mx.buckets.upload(bucket_id="my-bucket", file_path="video.mp4")

# Search across all extracted features
results = mx.retrievers.execute(
    retriever_id="my-retriever",
    inputs={"query_text": "person wearing a red jacket"},
    limit=10,
)

Also available as:

  • JavaScript SDK: npm install mixpeek
  • MCP Server: Connect Claude, Cursor, or any MCP-compatible agent
  • REST API: POST https://api.mixpeek.com/v1/retrievers/{id}/execute
  • CLI: mixpeek --version (included in the Python SDK)
  • Bring your own vectors: POST https://api.mixpeek.com/v1/namespaces/{namespace_id}/documents/upsert

What Gets Extracted

File Type Features
Video Face embeddings (ArcFace), scene descriptions (Gemini), visual embeddings (Vertex AI), transcripts (Whisper), keyframes
Images Visual embeddings (SigLIP / Vertex AI), face embeddings (ArcFace), OCR, descriptions, structured extraction
Audio Transcripts (Whisper), transcript embeddings (E5-Large), multimodal audio embeddings
Documents Text chunks, text embeddings (E5-Large), OCR for scanned PDFs, structured extraction

Each extracted feature becomes an independently searchable document. A single video can produce hundreds of documents: one per face, one per transcript segment, one per scene.

Use Cases

  • Ad creative: Find what makes your best ads work, by searching the hooks and patterns in your top-performing video ads
  • Video understanding: Search surveillance footage by face, scene, or spoken word
  • Content moderation: Detect brand logos, faces, and unsafe content across media libraries
  • Document intelligence: Extract structured data from scanned PDFs, invoices, and forms
  • Media asset management: Find the exact frame across millions of hours of video
  • E-commerce: Visual similarity search, product matching, catalog enrichment

Pinned Loading

  1. awesome-object-storage awesome-object-storage Public

    A curated, opinionated guide to S3-compatible object storage — 21 providers, pricing, features, gotchas, and an interactive comparison tool.

    38 9

  2. amux amux Public

    The agent control plane: run Claude Code, Codex and Gemini CLI agents in parallel with a shared task board, schedules and usage-limit recovery. Native iPhone, iPad and Mac apps plus a web dashboard…

    Rust 563 75

  3. awesome-multimodal-search awesome-multimodal-search Public

    Collections of multimodal search libraries, service and research papers

    19

  4. multimodal-tools multimodal-tools Public

    🧰 Simple, standalone tools for working with multimodal data: video, audio, image, and text.

    Python 12

  5. multimodal-inference-server multimodal-inference-server Public

    Production-grade Rust inference server for multimodal models (image + text → streamed text), with OpenAI-compatible APIs and high-throughput GPU scheduling.

    Rust 8 1

  6. video-embedding-benchmark video-embedding-benchmark Public

    Head-to-head benchmark of multimodal embedding models for text-to-video retrieval. 6 models, 20 CC0 videos, 60 queries, reproducible IR metrics (NDCG, MRR, Recall).

    Python 5 1

Repositories

Showing 10 of 42 repositories
  • amux Public

    The agent control plane: run Claude Code, Codex and Gemini CLI agents in parallel with a shared task board, schedules and usage-limit recovery. Native iPhone, iPad and Mac apps plus a web dashboard. Self-host (Rust + SQLite, Tailscale remote access) or use amux Cloud. MIT + Commons Clause.

    mixpeek/amux's past year of commit activity
    Rust 563 75 1 2 Updated Nov 18, 2026
  • awesome-object-storage Public

    A curated, opinionated guide to S3-compatible object storage — 21 providers, pricing, features, gotchas, and an interactive comparison tool.

    mixpeek/awesome-object-storage's past year of commit activity
    38 CC0-1.0 9 8 4 Updated Nov 18, 2026
  • amux-plugins Public

    amux for Claude Code, Codex and Gemini CLI: hand tasks to background agents that keep running after your session ends, and check on them from one board or your phone.

    mixpeek/amux-plugins's past year of commit activity
    Python 0 0 0 0 Updated Nov 18, 2026
  • momentbench Public

    Find the right moment across a video collection, or say nothing matches. 27 licensed videos, 456 published queries, an agentic and a prediction-file track, and a validated leaderboard.

    mixpeek/momentbench's past year of commit activity
    Python 2 Apache-2.0 1 2 (2 issues need help) 0 Updated Nov 16, 2026
  • homebrew-amux Public archive

    Retired. Install amux with: curl -fsSL https://amux.io/install.sh | bash

    mixpeek/homebrew-amux's past year of commit activity
    Ruby 0 0 1 0 Updated Oct 29, 2026
  • .github Public
    mixpeek/.github's past year of commit activity
    0 0 0 0 Updated Oct 29, 2026
  • connectors Public

    Integration connectors for Mixpeek — modules and plug‑ins that bring Mixpeek’s contextual intelligence to third‑party ecosystems.

    mixpeek/connectors's past year of commit activity
    JavaScript 1 0 0 0 Updated Oct 27, 2026
  • mixpeek-extractors Public

    Multimodal extractors for video, image, audio, text & PDF — turn any file into searchable vector embeddings (SigLIP, Gemini, E5, CLAP, ArcFace).

    mixpeek/mixpeek-extractors's past year of commit activity
    Python 1 MIT 1 0 0 Updated Sep 7, 2026
  • deepagents-mixpeek-fs Public

    Mixpeek-backed BackendProtocol implementation for LangChain DeepAgents — a drop-in alternative to deepagents_mongodb_fs

    mixpeek/deepagents-mixpeek-fs's past year of commit activity
    Python 1 MIT 0 0 0 Updated Sep 3, 2026
  • video-embedding-benchmark Public

    Head-to-head benchmark of multimodal embedding models for text-to-video retrieval. 6 models, 20 CC0 videos, 60 queries, reproducible IR metrics (NDCG, MRR, Recall).

    mixpeek/video-embedding-benchmark's past year of commit activity
    Python 5 1 0 1 Updated Aug 14, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.