> ## Documentation Index
> Fetch the complete documentation index at: https://docs.scitix.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenManus

> Learn how to connect OpenManus to ScitiX Model Inference for general-purpose agent workflows through an OpenAI-compatible model API.

[OpenManus](https://github.com/FoundationAgents/OpenManus) is an open-source general-purpose AI agent. It reads its model settings from a `config.toml` whose `[llm]` section takes a custom `base_url`, so the agent can run on the ScitiX Model Inference API.

Default model here is `glm-5.2`; see the [Models](https://console.scitix.ai/model-inference/models) page for the full list and pricing.

## Configure

Create an API key on the ScitiX [API Keys](https://console.scitix.ai/model-inference/api_keys) page. Copy `config/config.example.toml` to `config/config.toml` and point the `[llm]` section at ScitiX:

```toml theme={null}
# config/config.toml
[llm]
model = "glm-5.2"
base_url = "https://api.scitix.ai/model-api/v1"
api_key = "<Your API Key>"
max_tokens = 4096
temperature = 0.0

[llm.vision]
model = "glm-5.2"
base_url = "https://api.scitix.ai/model-api/v1"
api_key = "<Your API Key>"
```

| Field          | Value                                                                                                            |
| -------------- | ---------------------------------------------------------------------------------------------------------------- |
| `model`        | ScitiX model ID, e.g. `glm-5.2`. Pick a model with native tool calling; OpenManus is an agent that relies on it. |
| `base_url`     | ScitiX OpenAI-compatible endpoint: `https://api.scitix.ai/model-api/v1`                                          |
| `api_key`      | Your ScitiX API key                                                                                              |
| `[llm.vision]` | Set this to the same ScitiX model/endpoint so steps that use the vision LLM also route through ScitiX            |

The default `[llm]` API type is OpenAI-compatible, so no extra `api_type` is needed for ScitiX.

## Verify

Run the agent and give it a simple request — it responds using the configured ScitiX model:

```bash theme={null}
python main.py
# Enter your prompt: In one short sentence, which model are you?
# → I am GLM, a large language model developed by Z.ai.
```

The loaded config resolves to `model: glm-5.2` / `base_url: https://api.scitix.ai/model-api/v1`, confirming requests reach ScitiX.