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

# OpenHands

> Connect OpenHands to local Flint through Ollama, Unsloth, or llama.cpp, or to Nebius.

Run OpenHands on your computer and choose a local model server below. For the hosted Nebius path, get your assigned API key through the [1Password access handoff](https://docs.recursive.com/guides/coding-tools#get-access); those model requests go to Nebius.

For cloud access through OpenRouter, see the [OpenRouter sign-in example](https://docs.recursive.com/guides/openrouter#openhands).

## Start OpenHands

Install and start [Docker Desktop](https://docs.docker.com/desktop/), then install [uv](https://docs.astral.sh/uv/getting-started/installation/). On Windows, use WSL. See the [OpenHands local setup guide](https://github.com/OpenHands/docs/blob/main/openhands/usage/run-openhands/local-setup.mdx) for platform requirements.

Replace the project path with a disposable copy of your repository. OpenHands will be able to edit files in that directory.

```bash theme={null}
uv tool install openhands --python 3.12
cd /path/to/project-copy
openhands serve --mount-cwd
```

Keep the terminal open, then visit `http://localhost:3000` in your browser.

## Connect local runtimes

OpenHands is not currently listed in Ollama’s launcher integrations, so it requires a connection profile. Start a compatible Flint server using [Ollama](https://docs.recursive.com/edge/ollama.md), [Unsloth](https://docs.recursive.com/edge/unsloth.md#connect-a-coding-harness), or [llama.cpp](https://docs.recursive.com/edge/llama-cpp.md). In **Settings → LLM → Advanced**, choose **None** for Provider Connection and create a local profile:

| Server | Custom Model | Base URL when OpenHands and the model share a host | API key |
| - | - | - | - |
| Ollama | `openai/flint:40b-a2b-qat-int4` | `http://127.0.0.1:11434/v1` | `ollama` |
| Unsloth | `openai/` followed by the exact loaded Flint model ID | Displayed server URL plus `/v1` | Key from Unsloth Settings → API |
| llama.cpp | `openai/flint-local` — match `--alias` | `http://127.0.0.1:8080/v1` | `local`, or the configured server key |

Name the profile **Flint (local)**, save, select it as active, and start a new conversation. Here `openai/` selects the compatible API protocol; the configured Base URL determines the destination. Verify the model ID with `/v1/models`. Configure enough server context for OpenHands’ system prompt and tools; its [local-model guide](https://github.com/OpenHands/docs/blob/main/openhands/usage/llms/local-llms.mdx) recommends 32K or more when hardware permits.

### Local server networking

The browser’s location does not determine where model requests originate. If the OpenHands process making those requests is in Docker, `127.0.0.1` points inside that container. Use `http://host.docker.internal:11434/v1` for host Ollama, `http://host.docker.internal:8080/v1` for host llama.cpp, or the corresponding Unsloth port. On Linux, the container needs the `host.docker.internal:host-gateway` mapping.

That mapping alone does not make a host loopback listener reachable on Linux. Use a host-network configuration supported by your Docker setup, or bind the model server to a Docker-reachable interface with authentication and firewall restrictions. Do not expose an unauthenticated server to your LAN. Test `/v1/models` from the same container or environment that sends OpenHands’ model requests before starting a task.

Run the [tool-cycle check](https://docs.recursive.com/guides/coding-tools#verify-a-complete-tool-cycle). If you prefer automatic setup with OpenCode, [rec handles it in one command](https://docs.recursive.com/guides/coding-tools#automatic-setup-with-rec).

## Connect Flint

For the separate Nebius partner endpoint, use this profile.

Open **Settings → LLM → Advanced** and create a profile. If a Provider Connection is selected, choose **None** so you can enter the URL and key.

| Field | Value |
| - | - |
| Profile name | `Flint (Nebius)` |
| Custom Model | `nebius/dedicated/shadowlaunch/ll-alpha` |
| Base URL | `https://api.tokenfactory.us-north1.nebius.com/v1` |
| API key | Your assigned Nebius key from 1Password |

Keep the `nebius/` prefix in Custom Model. Select **Save Changes** and make **Flint (Nebius)** active. If your version shows **Settings → Agent**, select an OpenHands agent and this LLM profile.

## Try a task

Start a new conversation and ask:

```text theme={null}
Read this project and explain how to run it. Do not change files yet.
```

Then run the [file-editing and shell-check task](https://docs.recursive.com/guides/coding-tools#verify-a-complete-tool-cycle) to verify tool execution.

If the app will not start, check that Docker is running. If your files are missing, stop OpenHands with `Ctrl+C` and run the launch command again from the project directory. For authentication or model errors, recheck the profile and start a new conversation.

References: [OpenHands LLM profiles](https://github.com/OpenHands/docs/blob/main/openhands/usage/agent-canvas/llm-profiles.mdx) and [LiteLLM’s Nebius provider](https://docs.litellm.ai/docs/providers/nebius).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.