agent-zero/knowledge/main/about/setup-and-deployment.md
Alessandro b3b5e44cc3 Patch LiteLLM security pins
Upgrade LiteLLM to 1.88.1 so Agent Zero is above the CVE-2026-42271 patched floor, and move the OpenAI SDK pin to 2.41.1 to satisfy LiteLLM's new dependency range.

Pin Starlette to the patched 1.0.1 release for the Host-header request.url.path advisory.

Fold requirements2.txt back into requirements.txt now that browser-use is no longer part of the repo dependency set, and update installer and setup docs to use a single requirements file.
2026-06-11 03:47:58 +02:00

31 lines
855 B
Markdown

# Agent Zero Setup And Deployment
Docker image:
```bash
docker pull agent0ai/agent-zero
docker run -p 50001:80 agent0ai/agent-zero
```
Persist user data by mounting `/a0/usr`:
```bash
docker run -p 50001:80 -v /path/on/host:/a0/usr agent0ai/agent-zero
```
After first start, configure API keys, chat model, utility model, and embedding model in Settings. Embeddings are required for memory and knowledge recall.
For local development:
```bash
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python run_ui.py
```
Typical troubleshooting:
- Web UI unreachable: check `docker ps`, port mapping, and startup logs.
- Model errors: verify provider, model name, and API key.
- Memory/knowledge not recalling: verify embedding config and reindex if needed.
- Host-local access: use A0 CLI connector tools, not Docker tools.