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, and stops there.

OmniSeek keeps seeking: through languages, logins, comment threads, audio, and pixels, all 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 (persistent retrieval memory plus a typed, source-traced evidence graph).

Crossing languages draws on the index OmniSeek builds as you use it, so a fresh install starts at a floor. The published benchmark runs on exactly that fresh install, which makes its cross-lingual number the coldest case rather than the typical one.

Every source in the catalog, the curated roster of everything OmniSeek can reach, earned its place by beating plain search at one of five jobs (structure, unwalling, transcription, recall, monitoring): citation graphs, regulatory filings, login-walled forums, 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 · Benchmark (latest results) · Source health, updated weekly

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).

Two paths from here. The prebuilt core image (docker pull ghcr.io/battam1111/omniseek, amd64 + arm64) needs no build and carries every core sense; it is Apache-clean and ships without PDF reading, hearing (ASR + video frames), and login-walled sources. Wanting those extras is what triggers a local build: set EXTRAS="[pdf,asr,walled]" and run docker compose build, then up -d (the first build also fetches headless Chromium; later starts are instant). 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

The bare install is the Core tier: every keyless API and static source, document reading minus PDF, and the lexical memory index. pip install "omniseek[pdf,asr,recall,ocr]" wakes the Research tier (PDF, hearing, cross-lingual vectors, OCR); omniseek[walled] adds the login-walled tier, which stays off until you bring your own accounts; omniseek[all] takes everything. The server prints which senses are online, and which are dormant, at every boot.

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.

Prefer stdio? The install also ships an omniseek command that speaks MCP over stdio, for clients that launch servers themselves; Dockerfile.stdio wraps the same thing in a container.

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

Related MCP server: Augent

Tools

One MCP connection; no model, no agent loop inside. Your model thinks, your harness drives the loop, OmniSeek reaches. Start with omniseek_search; explore what's available with omniseek_sources.

The login-walled tier has no tool of its own: once you opt in per source, the same omniseek_search(..., sources=["xiaohongshu"], raw=True) runs through your own logged-in browser. See walled 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

There is no OmniSeek cloud. No telemetry, no accounts, no relay: a query leaves your machine only as direct requests to the sources you enabled, and OmniSeek adds no other party to that path. Walled-source credentials stay in your own browser, presented only to the site they belong to; OmniSeek never stores, uploads, or even sees your passwords. The retrieval memory and evidence graph it accumulates over months are local files you own: stop running OmniSeek and 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.

Your agent seeks what search can't find.

Apache-2.0 · NOTICE · Security · Cite