Connect OpenBulu to your AI applications
Use this page when you are ready to configure a tool. Each example shows the protocol, endpoint, and the minimum values to enter. Field names can vary by client version.
Compatibility means the tool can send requests through a supported protocol; it does not mean OpenBulu is an official plugin or that every advanced feature works automatically.
Client and agent setup examples
- CC Switch setup guide — OpenAI Responses / Anthropic Messages. Best for switching OpenBulu between Codex, Claude Code, and Gemini-compatible desktop tools from one place.
- Cherry Studio setup guide — OpenAI-compatible. Best for desktop chat users who want a graphical provider setup and model selector.
- LangBot setup guide — OpenAI-compatible. Best for connecting OpenBulu models to bots, messaging platforms, and LangBot pipelines.
- Codex Desktop setup guide — OpenAI Responses. Best for Codex desktop users. CC Switch is the simplest setup; manual Responses configuration is also shown.
- Claude Code setup guide — Anthropic Messages. Prefer an Anthropic-compatible Base URL with /v1/messages. If your version only accepts the official service, follow its gateway configuration instead.
- Codex CLI setup guide — OpenAI Responses. Prefer the Responses configuration, usually with the Base URL ending at /v1. Codex-related requests may also use /v1/responses/compact, so validate with a small request first.
- OpenCode setup guide — OpenAI Responses (1.x). Prefer an OpenAI-compatible provider and enter the openbulu Base URL, key, and model ID. Advanced parameters depend on the client version.
- DeepSeek Harness configuration reference — OpenAI-compatible. In Custom model API settings, enter the provider, base URL, protocol, credential, and exact model ID.
- Hermes Agent configuration reference — OpenAI-compatible. For versions that support a custom OpenAI-compatible provider, use the Chat Completions endpoint and an exact model ID.
- OpenClaw configuration reference — OpenAI-compatible. For versions that support a custom OpenAI-compatible provider, use the Chat Completions endpoint and an exact model ID.
- Dify configuration reference — OpenAI-compatible. Choose an OpenAI-compatible provider, then enter the Base URL, key, and model ID. Test workflows and tool calls separately.
Start with the API quickstart, check current model pricing, and use your own API key and an available model ID for each integration.