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

# Integrations

> Run the coding agents, editors, chat apps, and automation platforms you already use on any model in the Opper catalog

Most AI apps let you point them at a different inference endpoint. Opper's gateway speaks both the OpenAI and Anthropic wire formats, so once an app can take a base URL and an API key, it runs on any of the [models in the catalog](/capabilities/models) — with one key, [EU or US hosting](/overview/security), and every call visible in [traces](/control-plane/trace).

<Tip>
  Seven agents need no configuration at all. The [Opper CLI](/developer-tools/cli) writes their config for you:

  ```bash theme={null}
  npx @opperai/cli launch claude
  ```
</Tip>

## One base URL

Every integration on this page points at the same endpoint:

```
https://api.opper.ai/v3/compat
```

It serves both compatibility surfaces from that one URL — OpenAI Chat Completions and Responses, and the Anthropic Messages API. Apps that append their own path (`/chat/completions`, `/v1/messages`) work unchanged; see [Drop-in SDKs](/build/gateway/drop-in-sdks) for the full surface.

Model IDs use the `provider/model` convention — `anthropic/claude-sonnet-4-6`, `openai/gpt-5.5`, `gemini/gemini-3.5-flash`. Apps that support model discovery call `GET /v3/compat/models` and populate their own picker, filtered by your [model access rules](/control-plane/rules/model-access), so a model your policy denies is never offered.

## Launch from the CLI

For these agents, one command provisions the config and starts the app. Nothing to edit by hand:

| Agent                                                          | Command                       | What it writes                                                  |
| -------------------------------------------------------------- | ----------------------------- | --------------------------------------------------------------- |
| [Claude Code](/integrations/coding-agents/claude-code)         | `opper launch claude`         | `ANTHROPIC_BASE_URL` / `ANTHROPIC_AUTH_TOKEN` for the session   |
| [Claude Desktop](/integrations/personal-agents/claude-desktop) | `opper launch claude-desktop` | third-party-inference profile, then restarts the app            |
| [Codex](/integrations/coding-agents/codex)                     | `opper launch codex`          | `[model_providers.opper]` in `~/.codex/config.toml`             |
| [OpenCode](/integrations/coding-agents/opencode)               | `opper launch opencode`       | provider block in `~/.config/opencode/opencode.json`            |
| [Hermes](/integrations/personal-agents/hermes)                 | `opper launch hermes`         | isolated `HERMES_HOME`, your own config untouched               |
| [OpenClaw](/integrations/personal-agents/openclaw)             | `opper launch openclaw`       | `opper` provider in `~/.openclaw/agents/main/agent/models.json` |
| [pi](/integrations/coding-agents/pi)                           | `opper launch pi`             | `opper` provider in `~/.pi/agent/models.json`                   |

Pin a model with `--model`, and remove any integration later with `opper agents uninstall <agent>` — it unwires Opper without uninstalling the app.

## Coding agents

<CardGroup cols={2}>
  <Card title="Claude Code" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/claude-code.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=3411d7c0de4849994f0084a85652fbc5" href="/integrations/coding-agents/claude-code" width="100" height="100" data-path="images/tools/claude-code.svg">
    Anthropic's terminal coding agent, on any model
  </Card>

  <Card title="Codex" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/codex.png?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=db83acbe0c8552d0b677f95851ebaa7a" href="/integrations/coding-agents/codex" width="640" height="640" data-path="images/tools/codex.png">
    OpenAI's open-source coding CLI
  </Card>

  <Card title="OpenCode" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/opencode.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=0e1ce355812daf73a12343bf9193afbc" href="/integrations/coding-agents/opencode" width="240" height="300" data-path="images/tools/opencode.svg">
    SST's open-source terminal coding agent
  </Card>

  <Card title="pi" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/pi.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=4418a209a55cca4e31b9ec8817a9dddc" href="/integrations/coding-agents/pi" width="800" height="800" data-path="images/tools/pi.svg">
    Terminal agent with a native Opper provider
  </Card>

  <Card title="DeepSeek Harness" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/deepseek-harness.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=434ac7363c0c77f280ff8f3a3878a300" href="/integrations/coding-agents/deepseek-harness" width="16" height="16" data-path="images/tools/deepseek-harness.svg">
    DeepSeek's plugin-first agent harness
  </Card>

  <Card title="GitHub Copilot CLI" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/github-copilot.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=2adc18689aa5c4cee9df752dcce3aeb0" href="/integrations/coding-agents/github-copilot-cli" width="24" height="24" data-path="images/tools/github-copilot.svg">
    GitHub's terminal agent, no Copilot plan needed
  </Card>

  <Card title="Aider" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/aider.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=f2d7ff9f6550c2a4aac14788a6cab9d6" href="/integrations/coding-agents/aider" width="200" height="200" data-path="images/tools/aider.svg">
    AI pair programming in your terminal
  </Card>

  <Card title="Goose" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/goose.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=fa1dbdb7641b42312ae14df87879bff2" href="/integrations/coding-agents/goose" width="200" height="200" data-path="images/tools/goose.svg">
    Open agent from the Agentic AI Foundation
  </Card>

  <Card title="Droid" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/factory-droid.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=3b970adb3ec8cbd9901acc262022a670" href="/integrations/coding-agents/droid" width="508" height="508" data-path="images/tools/factory-droid.svg">
    Factory's agent for terminal and IDEs
  </Card>

  <Card title="Voidleap Code" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/voidleap-code.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=b07ebdadac5b147fbeb08c8c04ca2c24" href="/integrations/coding-agents/voidleap-code" width="302" height="302" data-path="images/tools/voidleap-code.svg">
    Desktop agentic IDE with Opper built in
  </Card>
</CardGroup>

## Editors and IDEs

<CardGroup cols={2}>
  <Card title="GitHub Copilot" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/github-copilot.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=2adc18689aa5c4cee9df752dcce3aeb0" href="/integrations/editors/github-copilot" width="24" height="24" data-path="images/tools/github-copilot.svg">
    Copilot Chat and agent mode, via the Opper VS Code extension
  </Card>

  <Card title="Cursor" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/cursor.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=9ee5f717dec86f4ae068be39ea87c8cf" href="/integrations/editors/cursor" width="467" height="533" data-path="images/tools/cursor.svg">
    The AI code editor
  </Card>

  <Card title="Cline" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/cline.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=e9bb13bd84af8eeecdf98508a0d10dc0" href="/integrations/editors/cline" width="467" height="487" data-path="images/tools/cline.svg">
    Open-source AI coding agent for VS Code
  </Card>

  <Card title="Kilo Code" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/kilocode.png?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=84074b865f4068daff5bb810eb5f4e3b" href="/integrations/editors/kilo-code" width="600" height="600" data-path="images/tools/kilocode.png">
    Open-source AI agent for VS Code
  </Card>

  <Card title="Zed" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/zed.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=025b6e1e81fd20afcdb86fd15823c32d" href="/integrations/editors/zed" width="24" height="24" data-path="images/tools/zed.svg">
    The high-performance code editor
  </Card>

  <Card title="JetBrains AI Assistant" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/jetbrains-ai.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=fc876fb08cf2c49f198e53126e7e5dd5" href="/integrations/editors/jetbrains" width="24" height="24" data-path="images/tools/jetbrains-ai.svg">
    IntelliJ, PyCharm, and every JetBrains IDE
  </Card>

  <Card title="Continue.dev" icon="code" href="/integrations/editors/continue">
    Open-source assistant for VS Code and JetBrains
  </Card>
</CardGroup>

## Personal agents

<CardGroup cols={2}>
  <Card title="Claude Cowork" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/claude-code.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=3411d7c0de4849994f0084a85652fbc5" href="/integrations/personal-agents/claude-cowork" width="100" height="100" data-path="images/tools/claude-code.svg">
    Anthropic's agent for knowledge work
  </Card>

  <Card title="Claude Desktop" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/claude-code.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=3411d7c0de4849994f0084a85652fbc5" href="/integrations/personal-agents/claude-desktop" width="100" height="100" data-path="images/tools/claude-code.svg">
    Anthropic's macOS and Windows desktop app
  </Card>

  <Card title="Copilot for Obsidian" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/obsidian-copilot.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=73ab06797936c8bd4f659f4aa676c36b" href="/integrations/personal-agents/obsidian-copilot" width="200" height="200" data-path="images/tools/obsidian-copilot.svg">
    AI copilot inside your Obsidian vault
  </Card>

  <Card title="OpenClaw" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/openclaw.png?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=1dfd60aa6060699db90d45ca0dc0f101" href="/integrations/personal-agents/openclaw" width="512" height="512" data-path="images/tools/openclaw.png">
    Personal agent on WhatsApp, Telegram, and Discord
  </Card>

  <Card title="Hermes" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/hermes.png?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=8317abbfb4aacfed2abf87e941d23673" href="/integrations/personal-agents/hermes" width="108" height="108" data-path="images/tools/hermes.png">
    Nous Research's open terminal agent
  </Card>
</CardGroup>

## Chat

<CardGroup cols={2}>
  <Card title="LibreChat" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/librechat.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=9d748d941d00e2a6d1ffdf02d2fc4285" href="/integrations/chat/librechat" width="512" height="512" data-path="images/tools/librechat.svg">
    The open-source AI chat platform
  </Card>

  <Card title="Open WebUI" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/open-webui.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=f0c41d00db16b95e8ed4887e9f4b7c54" href="/integrations/chat/open-webui" width="500" height="500" data-path="images/tools/open-webui.svg">
    Self-hosted AI workspace
  </Card>
</CardGroup>

## Automation

<CardGroup cols={2}>
  <Card title="n8n" icon="https://mintcdn.com/opper/H-iiE_tAhHpUz1kK/images/tools/n8n.svg?fit=max&auto=format&n=H-iiE_tAhHpUz1kK&q=85&s=bbca6d841c72f4f23ab622d4c829def6" href="/integrations/automation/n8n" width="24" height="24" data-path="images/tools/n8n.svg">
    Workflow automation with a native Opper node
  </Card>
</CardGroup>

## Frameworks and gateways

Not apps — libraries and proxies you build on or run in front of Opper.

<CardGroup cols={2}>
  <Card title="Vercel AI SDK" icon="bolt" href="/integrations/frameworks/vercel-ai-sdk">
    TypeScript toolkit with an official Opper provider
  </Card>

  <Card title="Mastra" icon="cubes" href="/integrations/frameworks/mastra">
    TypeScript agent framework with a first-class `opper/` provider
  </Card>

  <Card title="LiteLLM" icon="server" href="/integrations/frameworks/litellm">
    Use Opper as the upstream router for a self-hosted gateway
  </Card>
</CardGroup>

<Tip>
  Opper is listed on [models.dev](https://models.dev), the open catalog many tools read their model list from. If an app pulls its providers from there, Opper may already be in its picker — with model IDs, context windows, and pricing filled in — before you configure anything.
</Tip>

## Why route an app through Opper

|                  | Direct to the provider           | Through Opper                                                                                                      |
| ---------------- | -------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
| **Model access** | Whatever that provider serves    | The whole [catalog](/capabilities/models), switchable mid-session                                                  |
| **Keys**         | One per provider                 | One Opper key                                                                                                      |
| **Residency**    | Wherever the provider runs       | Pin EU-hosted models when you need to                                                                              |
| **Reliability**  | Single upstream                  | Pools spread a model across every provider serving it                                                              |
| **Cost control** | Per-provider dashboards          | [Spend rules](/control-plane/rules/spend) and one bill at provider rates                                           |
| **Visibility**   | Whatever the app shows you       | Full [traces](/control-plane/trace) with model, latency, and tokens                                                |
| **Policy**       | Enforced per provider, if at all | [Model access](/control-plane/rules/model-access) and [retention](/control-plane/rules/retention) rules, centrally |

## Your app isn't listed

Most of these integrations are the same three fields. If your app has a setting for a custom OpenAI-compatible provider, it already works:

<Steps>
  <Step title="Set the base URL">
    ```
    https://api.opper.ai/v3/compat
    ```

    If the app expects a host and a path separately, the host is `https://api.opper.ai` and the path is `v3/compat/chat/completions`.
  </Step>

  <Step title="Paste an Opper API key">
    Create one at [platform.opper.ai](https://platform.opper.ai/settings/api-keys). Keys are scoped to a project, so use a separate one per app if you want usage split out.
  </Step>

  <Step title="Pick a model">
    Use a full model ID such as `anthropic/claude-sonnet-4-6`. Apps that fetch `GET /v3/compat/models` will list the catalog for you.
  </Step>
</Steps>

Tag the traffic with `X-Opper-Tags` to break usage down per app — see [Tags and usage attribution](/build/gateway/usage-attribution).

## Next steps

<CardGroup cols={2}>
  <Card title="Browse the model catalog" icon="list" href="/capabilities/models">
    Model IDs, hosting regions, and retention metadata.
  </Card>

  <Card title="Opper CLI" icon="terminal" href="/developer-tools/cli">
    Launch agents, inspect traces, and manage models from the terminal.
  </Card>
</CardGroup>