Shared chat transport for the Open Responses API — an async-iterable client over POST /v1/responses, plus a normalizer that folds backbone's three error envelopes into one shape.

火山方舟 Coding Plan LLM provider for DeepSeek Harness — provider-scoped PDF、图片与 Responses API 流式支持

Unified wrapper over OpenAI Responses API and Google Gemini (@google/genai), with streaming + usage/cost metrics.

Enhanced Qwen Token Plan CN provider for pi. Speaks the OpenAI Responses API (not chat-completions) to activate the platform's server-side Harness tools — web search, code interpreter, web extraction, and image search — that the built-in qwen-token-plan-c

Complete model providers for pi — Alibaba Model Studio (Plan subscription + Cloud pay-per-token, Anthropic + OpenAI + Responses API shapes, native thinking levels. Qwen 3.8/3.7/3.6, DeepSeek V4, Kimi K2.6/K2.7, GLM-5.1/5.2, MiniMax M2.5) and DeepSeek offi

MCP server for xAI X search via Responses API

<p align="center"><code>npm i -g @eriz1818/xcodex-responses-api-proxy</code> to install <code>xcodex-responses-api-proxy</code></p>

OpenCode plugin for OpenAI Responses API over WebSocket and HTTP SSE.

Local proxy that lets the latest OpenAI Codex CLI / desktop talk to Xiaomi MiMo (V2.5 Pro) via the Responses API by translating to Chat Completions on the fly.

OpenAI Responses-API completion port for the bentway kernel

Safety-focused AI terminal agent for Tabby with multi-session permissions and OpenAI Responses API support

DSH web search provider with three selectable protocols: any OpenAI-compatible Responses API gateway exposing the native web_search tool, Zhipu's Web Search API (basic retrieval), and Zhipu's Web Search in Chat (answer augmentation). Registers a ctx.web s

Local proxy that translates OpenAI Responses API format to Coding Plan Dashscope Chat Completions format for Codex

Anthropic Messages API to Azure OpenAI Responses API proxy

pi extension + skill: visual understanding via a configurable vision model (pi-registry reuse or custom responses API; default gpt-5.6-luna) when the main model cannot see images — pure TypeScript, single runtime

Wrap OpenAI function-calling (Responses API + Chat Completions tool path) with OC Agent scope enforcement and emit a signed agent-action envelope per function invocation.

MCP Server for OpenAI Codex /v1/responses API integration with Claude Code

SDK that exposes the OpenAI Responses API on top of any /v1/chat/completions backend (vLLM, Ollama, llama.cpp, TGI, etc.). Handles conversation state, MCP tool execution, and streaming event translation.

<p align="center"><code>npm i -g @jojoyo/codex-responses-api-proxy</code> to install <code>codex-responses-api-proxy</code></p>

<p align="center"><code>npm i -g @openai/codex-responses-api-proxy</code> to install <code>codex-responses-api-proxy</code></p>