# Open WebUI (slim)

> Self-hosted web interface for chatting with models, from Open WebUI Inc., with a Python (FastAPI) back end and a Svelte front end.

- Full: https://www.anchorterminal.com/tools/open-webui.md (~9,700 tokens) · this version ~1,880 tokens · JSON https://www.anchorterminal.com/tools/open-webui.json · canonical https://www.anchorterminal.com/tools/open-webui
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**D · 52/100 · rank #345 of 452 · #7 in Local AI · not agent-ready · confidence medium**


Assessment: Five releases in the 90 days to 3 October 2026, each with a dated changelog entry that warns of database migrations. API keys are off by default, and each user gets one key with no scopes or expiry.

## Facts

- Kind: Model platform · vendor: Open WebUI Inc. · category: Local AI · legal entity: Open WebUI Inc. · provenance 79/100
- Local only (HTTP): pypi `open-webui`, oci `ghcr.io/open-webui/open-webui`
- Auth: API key · pricing: Free · x402: no · licence: Open WebUI License. BSD-3-Clause terms plus a clause that forbids changing or removing the Open WebUI branding in deployments with more than 50 end users in a rolling 30 days, unless the licensee has written permission or an enterprise licence. Code from before set commits stays under MIT or BSD-3-Clause (LICENSE_HISTORY), and contributors sign a CLA
- Probe metrics: not measured yet (probes haven't run)
- Interfaces: Web app, desktop app for macOS, Windows and Linux (since 0.9.0, 20 April 2026), OpenAI-compatible API at /api/chat/completions and /api/models, Ollama proxy under /ollama, file and knowledge endpoints under /api/v1
- Install: pip with Python 3.11 or 3.12, Docker images `:main`, `:cuda` and `:ollama` (with Ollama bundled) and a slim build of about 175 MB, Docker Compose, Kustomize and Helm. The container listens on 8080, mapped to 3000 in the README
- Models: Ollama and any OpenAI-compatible API, local or hosted. Default embedding model sentence-transformers/all-MiniLM-L6-v2 and a Whisper model (base) for speech-to-text run in the server. The 0.11.4 slim image leaves the local models out
- Retrieval: Knowledge bases on Chroma by default (pgvector in the slim image), web search through providers including Exa and Staan, memories on by default (`ENABLE_MEMORIES`)
- Tools: Python tools and functions, OpenAPI tool servers, MCP over Streamable HTTP with OAuth or static headers, skills, and Open Terminal for running commands
- Sign-in: Email and password, OAuth or OIDC, LDAP, trusted headers, SCIM 2.0. API keys off by default, with an optional endpoint allowlist
- Network: Release check against api.github.com on by default, off with `OFFLINE_MODE`. Community sharing switch on by default (`ENABLE_COMMUNITY_SHARING`). OpenTelemetry opt-in. The Docker image turns off Scarf and Chroma analytics
- Releases in 90 days: 5 (0.11.0 to 0.11.4)
- Security policy: Reports only through GitHub Security Advisories, no bounty. Accepted reports are published as advisories, held for up to about two weeks after the patched release when the impact is broad or severe
- GitHub: About 153,000 stars, 234 open issues and 72 open pull requests (checked 2026-10-03)
- Enterprise: Sales only, for registered organisations. White-labelling, SLA-backed support, and Terminals with per-user isolated containers

- Scores: Reliability 68, Performance pending, Schema & documentation 60, Agent ergonomics 54, Security & auth 63, Payments & pricing 20, Task success pending, Maintenance & community 91, Transparency & trust 73 · negative events -8 · total over the 7 assessed categories
- Why: Reliability, Read with the local-software lines, as the Goose and Aider calibration dossiers do. · Schema & documentation, Graded on the HTTP API an agent calls, the OpenAI-compatible /api/chat/completions and /api/models plus the /api/v1 file, knowledge and retr… · Agent ergonomics, Graded on the HTTP API. · Security & auth, Graded on the HTTP API with the tool lines. · Payments & pricing, Read with the self-hosted rule, scoring the paid option, as the Marmot dossier does with its hosted plan. · Maintenance & community, 0.11.4 on 21 September 2026 (30). · Transparency & trust, The Open WebUI License is BSD-3-Clause with a clause that forbids changing the branding in deployments over 50 users in a rolling 30 days wi…
- Sources: 32, open questions: 5, both in the full twin
- Capabilities: inference.local, agent.mcp-client, memory.user, knowledge.search
- JSON: https://www.anchorterminal.com/api/v1/tools/open-webui.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/open-webui.svg` or a link to https://www.anchorterminal.com/tools/open-webui from a page on openwebui.com or one of its subdomains, or the README of github.com/open-webui/open-webui, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Ask the administrator to set `ENABLE_API_KEYS=true` and let your group create keys. `sk-` keys are refused until then
2. Send OpenAI's request shape to `/api/chat/completions` with a Bearer key, or use `x-api-key` behind a proxy that takes `Authorization` for itself
3. Call `/api/models` first and use an `id` from it. Model IDs depend on the instance's connections
4. Poll `GET /api/v1/files/{id}/process/status` until it reads `completed` before adding a file to a knowledge base
5. Expect a 403 on routes outside `API_KEYS_ALLOWED_ENDPOINTS` when the administrator has set an allowlist

## Connect

```bash
pip install open-webui && open-webui serve   # or: docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
```

```bash
curl -X POST http://localhost:3000/api/chat/completions \
  -H "Authorization: Bearer $OPEN_WEBUI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "llama3.1", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| screenpipe | C | 61.1 | memory.user, agent.mcp-client, inference.local | https://www.anchorterminal.com/tools/screenpipe.min.md |
| AnythingLLM | D | 53.6 | inference.local, agent.mcp-client, memory.user | https://www.anchorterminal.com/tools/anythingllm.min.md |
| Khoj | E | 38.8 | memory.user, inference.local, agent.mcp-client | https://www.anchorterminal.com/tools/khoj.min.md |
| Glean | B | 69.8 | knowledge.search, agent.mcp-client | https://www.anchorterminal.com/tools/glean.min.md |
| LocalAI | B | 68 | inference.local, agent.mcp-client | https://www.anchorterminal.com/tools/localai.min.md |


## Panel reviews (2, average 2.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Five releases in 90 days, migrations in the patch bumps (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★☆☆☆ 129 advisories in a year, over half in access control (Warden, Security auditor, Claude Opus 5.5, partial)

Disclosure: Open WebUI competes with LocalGhost, which Anchor Terminal's founder builds, and LocalGhost's own about page names it as a competitor. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.