OmniSeek

Your agent seeks what search can't find.

The answer is sitting in minute 47 of a podcast, three replies deep in a comment thread, behind a login, in another language. Your agent gets it anyway.

_{Self-hosted perception MCP server · one connection}

       

Quick start · Tools · Configure · Contributing

Languages: English · 中文 · 日本語

Search gives your agent indexed pages, in one language, in text. That's the surface.

OmniSeek is the reach beneath it, and everything it does runs on your machine.

It hears (local bilingual ASR, no cloud), sees (images and video frames, in-band), crosses languages (a Chinese query finds English results and vice versa), reads behind login walls (your credentials, your machine, off by default), and remembers (a persistent relation graph that gets richer with every query).

Every source in the catalog earned its place by beating plain search at something, from citation graphs and regulatory filings to login-walled forums and Chinese-language video. And the catalog is built to grow: a curator pipeline probes, judges, and admits new sources, and retires the ones that decay.

Worked examples, real outputs · A full case study

Quick start

Docker (recommended)

git clone https://github.com/Battam1111/omniseek.git && cd omniseek
docker compose up -d
docker compose logs omniseek        # bearer token printed on first start
curl -s http://127.0.0.1:8765/healthz

Point your MCP client at http://127.0.0.1:8765/mcp with Authorization: Bearer <token>. The token is generated on first start and stored in ~/.omniseek/credentials/omniseek_http.json (with the compose file, that's ./.omniseek/credentials/omniseek_http.json on the host).

The first up builds locally (dependencies + headless Chromium); later starts are instant. The core image is Apache-clean and ships without PDF reading, hearing (ASR + video frames), and login-walled sources; unlock them with the build arg EXTRAS="[pdf,asr,walled]". Optional but recommended: set OMNISEEK_CONTACT_EMAIL for a faster lane with Crossref, SEC, and Unpaywall.

Without Docker

python -m venv .venv && . .venv/bin/activate
scripts/bootstrap.sh
python -m omniseek.serve_http

On Windows, run bootstrap.sh under Git Bash or WSL; Docker is the simplest path. For an always-on Linux service, see deploy/omniseek.service.

OmniSeek binds 127.0.0.1 and requires the bearer token on every request. Do not expose without a reverse proxy (SECURITY.md).

Tools

One MCP connection. Start with omniseek_search; explore what's available with omniseek_sources.

Full reference in tools.md · FAQ

Using Claude Code? skills/omniseek-investigate ships the investigation methodology (sweep, zoom, structure) as a ready-made skill.

Configure

OmniSeek is catalog-first: with no config, every benign source is on and login-walled sources are off. Tune in one file, ~/.omniseek/profile.json (example):

Full reference: configuration · walled sources · legal posture

Why self-hosted

Every query you run, every connection your agent finds, every credential you use stays on your machine. No cloud service ever sees what you're researching. The relation graph it builds over months is yours; if you stop running OmniSeek, you keep everything. Not a feature toggle. The architecture.

Contributing

See CONTRIBUTING.md. The bar for a new source: it must beat plain web search via a mode (structure / unwall / transcribe / recall / monitor). The bar for fixing a decayed source: low, please do. python tests/smoke.py before you push.

By participating you agree to the Code of Conduct.