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

# Agents on Sideren — the full list.

> If a tool has an OpenAI-compatible setting, it runs on Sideren: an API base pointed at the gateway, an sdn_ key, and a catalog model id. Every agent has its own page with the exact config.

## All agents

Every agent below runs on Sideren. Each page carries the exact, tested config for that
agent — plus the quick check that it works.

<CardGroup cols={3}>
  <Card title="Claude Code" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/claude-code.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=dd653454701cd4d6a0407eb39b84f224" href="/guides/claude-code" width="24" height="24" data-path="logos/claude-code.svg">
    Anthropic Messages dialect, four environment variables.
  </Card>

  <Card title="Codex CLI" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/codex.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=e440905921ad31e98989b29b653510ad" href="/guides/codex" width="24" height="24" data-path="logos/codex.svg">
    OpenAI Responses protocol, one provider block in config.toml.
  </Card>

  <Card title="Cursor" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/cursor.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=d8591baa17e0abf699ed5e146232400f" href="/guides/cursor" width="512" height="512" data-path="logos/cursor.svg">
    OpenAI base-URL override in Cursor's models settings.
  </Card>

  <Card title="opencode" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/opencode.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=4e81cc0f9a1a2266c6f97353cb93cdb4" href="/guides/agents/opencode" width="512" height="512" data-path="logos/opencode.svg">
    A Sideren provider in opencode.json.
  </Card>

  <Card title="Crush" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/crush.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=d9c1059ba7102cad858a0e216f5b99e7" href="/guides/agents/crush" width="50" height="50" data-path="logos/crush.svg">
    An openai-compat provider in Charm's crush.json.
  </Card>

  <Card title="Goose" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/goose.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=59646795942d45b0c4ca2a089893f2d7" href="/guides/agents/goose" width="1648" height="1648" data-path="logos/goose.svg">
    Goose via the built-in openai provider.
  </Card>

  <Card title="Hermes Agent" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/hermes-agent.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=caa286ccea44044bf35d800c99485163" href="/guides/agents/hermes-agent" width="256" height="256" data-path="logos/hermes-agent.svg">
    A named provider in \~/.hermes/config.yaml.
  </Card>

  <Card title="OpenClaw" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/openclaw.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=c573cabaf072b58c0af396338ed9b7e4" href="/guides/agents/openclaw" width="24" height="24" data-path="logos/openclaw.svg">
    models.providers in \~/.openclaw/openclaw\.json.
  </Card>

  <Card title="Qwen Code" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/qwen-code.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=fdf248d3c8d3c834527598466da97262" href="/guides/agents/qwen-code" width="136" height="136" data-path="logos/qwen-code.svg">
    Three variables in a .qwen/.env file.
  </Card>

  <Card title="OpenHands" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/openhands.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=25ad62eaba592b3ad47c8efd8f5f9031" href="/guides/agents/openhands" width="24" height="24" data-path="logos/openhands.svg">
    Advanced LLM settings with an openai/-prefixed model.
  </Card>

  <Card title="Aider" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/aider.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=dea00ddc91eaf2e20872d93dea52d261" href="/guides/agents/aider" width="384" height="384" data-path="logos/aider.svg">
    \~/.aider.conf.yml on the OpenAI-compatible route.
  </Card>

  <Card title="Zed" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/zed.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=c98628cdf2a171d193ecbe164374d9c9" href="/guides/agents/zed" width="24" height="24" data-path="logos/zed.svg">
    An openai\_compatible provider in settings.json.
  </Card>

  <Card title="Continue" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/continue.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=1280e01451a1439da41a172eca56762d" href="/guides/agents/continue" width="300" height="300" data-path="logos/continue.svg">
    One models entry per catalog id in config.yaml.
  </Card>

  <Card title="Cline" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/cline.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=dd6594d28f0f5f02d320832c375d5f6d" href="/guides/agents/cline" width="1024" height="1024" data-path="logos/cline.svg">
    OpenAI Compatible provider in Cline's GUI.
  </Card>

  <Card title="Kilo Code" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/kilo-code.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=6e57706a42af189a5251f9476aa0eac8" href="/guides/agents/kilo-code" width="32" height="32" data-path="logos/kilo-code.svg">
    Custom provider dialog in the VS Code GUI.
  </Card>
</CardGroup>

## Compatibility at a glance

Every tool here speaks the OpenAI [Chat Completions](/api/chat-completions) dialect, which
the gateway serves at `https://api.sideren.io/v1/chat/completions`. The only thing that
differs between tools is *where* you set the three values and whether the API base carries
the `/v1` suffix.

| Tool | Configured in | API base |
| - | - | - |
| opencode | `opencode.json` | `https://api.sideren.io/v1` |
| Crush | `crush.json` | `https://api.sideren.io/v1` |
| Goose | `env / goose configure` | `https://api.sideren.io` |
| Hermes Agent | `~/.hermes/config.yaml` | `https://api.sideren.io/v1` |
| OpenClaw | `~/.openclaw/openclaw.json` | `https://api.sideren.io/v1` |
| Qwen Code | `.qwen/.env` | `https://api.sideren.io/v1` |
| OpenHands | `Settings → LLM (Advanced)` | `https://api.sideren.io/v1` |
| Aider | `~/.aider.conf.yml` | `https://api.sideren.io/v1` |
| Zed | `settings.json` | `https://api.sideren.io/v1` |
| Continue | `~/.continue/config.yaml` | `https://api.sideren.io/v1` |
| Cline | `GUI settings` | `https://api.sideren.io/v1` |
| Kilo Code | `GUI settings` | `https://api.sideren.io/v1` |

<Note>
  Almost every tool wants the base URL to **include** `/v1` — it appends the method path
  (`/chat/completions`) itself. `Goose` is the one exception on this page: its
  `OPENAI_HOST` takes the bare origin and adds `/v1/chat/completions` for you. Claude Code
  and Codex have their own pages — [Claude Code](/guides/claude-code),
  [Codex CLI](/guides/codex), [Cursor](/guides/cursor). Cursor CLI (`agent`), Antigravity
  (`agy`), and Kiro CLI have **no** OpenAI-compatible hook — `npx sideren setup --tool
      cursor-cli,antigravity,kiro` prints that and a Hermes/Codex/Claude one-liner instead of
  writing a fake config.
</Note>

## Anything OpenAI-compatible

The universal recipe, for tools not listed here:

* Base URL: `https://api.sideren.io/v1` (append `/v1` unless the tool documents that it
  adds it — as Goose and Claude Code do).
* API key: your Sideren key, usually in the tool's "OpenAI API key" field. The gateway accepts
  it as either an `Authorization: Bearer` or `x-api-key` header, so whichever the client
  sends works.
* Model: any id from the [catalog](/models) — the tool does not need to know the list in
  advance. Use the public id (`@sdn/glm-5` for an open-weight model, `gpt-6.1-sol` for a
  closed-weight one); older spellings such as `sdn-glm-5` and `glm-5` work too.

<Note>
  The setup helper (`npx sideren`) automates every setup it can write a file for: Claude Code, Codex,
  opencode, Hermes, Aider, Continue, Crush, Goose, Qwen Code, OpenClaw, Zed, Kilo Code,
  Cline and more — see [setup helper](/setup). Cursor CLI, Antigravity (`agy`), Kiro and Gemini CLI
  are recognized `--tool` ids too; they have no custom OpenAI hook, so setup prints that
  limit instead of writing a config that would fail. For every tool above, the by-hand
  config lives on its page.
</Note>


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