# TextGen (slim)

> Open-source desktop and browser app for running language models on the owner's hardware, formerly text-generation-webui. With --api it serves an OpenAI and Anthropic-compatible local API with tool calling, vision, embeddings and image generation.

- Full: https://www.anchorterminal.com/tools/text-generation-webui.md (~6,550 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/text-generation-webui.json · canonical https://www.anchorterminal.com/tools/text-generation-webui
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

**E · 45.1/100 · rank #775 of 842 · #15 in Local AI · not agent-ready · confidence medium**


Assessment: AGPL-3.0 with no telemetry, and a local API on 127.0.0.1:5000 that checks the Host header, limits CORS to localhost and separates an admin key from the caller's key. No release since v4.9 on 20 May 2026, no code commits since 31 May, no test suite, and ten security advisories in the year, all fixed.

## Facts

- Kind: Model platform · vendor: oobabooga · category: Local AI · legal entity: not named · provenance 27/100
- Local only (HTTP)
- Auth: API key · pricing: Free · x402: no · licence: AGPL-3.0
- Probe metrics: not measured yet (probes haven't run)
- Interfaces: Electron desktop window in the portable builds (Linux, Windows, macOS, with CUDA, Vulkan, ROCm and CPU-only options), a Gradio web UI at 127.0.0.1:7860, and a local HTTP API on port 5000 when `--api` is set
- API routes: `/v1/chat/completions`, `/v1/completions`, `/v1/messages`, `/v1/models`, `/v1/embeddings`, `/v1/images/generations`, `/v1/moderations`, `/v1/audio/transcriptions`, plus `/v1/internal/*` for token counts, logits, stopping generation and loading models and LoRAs
- Auth: Optional `--api-key` and `--admin-key`, off by default, as Bearer or `x-api-key`. Host-header check and localhost-only CORS unless `--listen` or `--public-api`
- Backends: llama.cpp, ik_llama.cpp, Transformers, ExLlamaV3 and TensorRT-LLM. The portable builds run GGUF models only
- Tools and MCP: Five built-in tools in `user_data/tools` (web_search, fetch_webpage, calculate, get_datetime, roll_dice), custom tools as single `.py` files, and MCP servers over HTTP or stdio. Over the API the caller runs the tools
- Telemetry: None, per the README. Gradio analytics are off in the source. A manual Check for updates button calls api.github.com
- Embeddings: `/v1/embeddings` is marked alpha and needs `sentence-transformers`, with all-mpnet-base-v2 by default
- Releases in 90 days: None. v4.0 on 7 March 2026 to v4.9 on 20 May 2026, then nothing
- Former name: text-generation-webui, also known as oobabooga. The repository is now oobabooga/textgen

- Scores: Reliability 51, Performance pending, Schema & documentation 61, Agent ergonomics 50, Security & auth 40, Payments & pricing 60, Task success pending, Maintenance & community 24, Transparency & trust 49 · negative events -4 · total over the 7 assessed categories
- Why: Reliability, Read with the local-software lines, since TextGen runs on the owner's machine with no hosted service. · Schema & documentation, Read with the API lines. · Agent ergonomics, Read with the API lines. · Security & auth, Read with the tool checklist. · Payments & pricing, Self-hosted rule. · Maintenance & community, v4.9 on 20 May 2026, 141 days before this check (10). · Transparency & trust, AGPL-3.0 for the whole repository (30).
- Sources: 18, open questions: 7, both in the full twin
- Capabilities: inference.local, inference.open-weights, agent.mcp-client, embed.text, image.generate
- JSON: https://www.anchorterminal.com/api/v1/tools/text-generation-webui.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/text-generation-webui.svg` or a link to https://www.anchorterminal.com/tools/text-generation-webui from a page under github.com/oobabooga, or the README of github.com/oobabooga/textgen, 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 owner to launch with `--api`. Nothing listens on port 5000 without it, and a model must be loaded first
2. Call `http://127.0.0.1:5000/v1`. Any Host header other than localhost or 127.0.0.1 gets 400 `Invalid host header` unless `--listen` is set
3. Send the key as `Authorization: Bearer` on OpenAI routes and as `x-api-key` on `/v1/messages`. Model loading needs the admin key
4. Read `http://127.0.0.1:5000/docs` or `modules/api/typing.py` for parameters. `max_tokens` defaults to 512 on chat completions
5. Run tool calls yourself. The API returns `finish_reason: "tool_calls"` and executes nothing on the server
6. Use the repository name `oobabooga/textgen`. The old `text-generation-webui` URL redirects

## Connect

```bash
git clone https://github.com/oobabooga/textgen
cd textgen
python -m venv venv
source venv/bin/activate
pip install -r requirements/portable/requirements.txt --upgrade
python server.py --portable --api --auto-launch
```

```bash
curl http://127.0.0.1:5000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello!"}], "temperature": 0.6, "top_p": 0.95, "top_k": 20}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| LocalAI | B | 68 | inference.local, inference.open-weights, agent.mcp-client, embed.text, image.generate | https://www.anchorterminal.com/tools/localai.min.md |
| KoboldCpp | C | 60.5 | inference.local, inference.open-weights, agent.mcp-client, embed.text, image.generate | https://www.anchorterminal.com/tools/koboldcpp.min.md |
| Lemonade | B | 63.8 | inference.local, inference.open-weights, embed.text, image.generate | https://www.anchorterminal.com/tools/lemonade.min.md |
| llama.cpp | C | 60.2 | inference.local, inference.open-weights, embed.text, agent.mcp-client | https://www.anchorterminal.com/tools/llama-cpp.min.md |
| LM Studio | C | 57.8 | inference.local, inference.open-weights, agent.mcp-client, embed.text | https://www.anchorterminal.com/tools/lm-studio.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)