Repolode
Enviar
Zen4-bit

Zen4-bit/Proxima

A local MCP server that routes prompts from Cursor, VS Code, Windsurf or Claude Desktop to ChatGPT, Claude, Gemini, Perplexity, BYOK APIs or local Ollama models.

Ver no GitHubSite
Estrelas
1,198
Forks
163
Issues abertas
28
Último commit
há 3 dias

O que é?

Proxima is a local gateway that exposes several AI models as one MCP server and OpenAI-compatible HTTP endpoint on 127.0.0.1. Coding clients such as Cursor, VS Code, Windsurf and Claude Desktop connect to it over stdio and can call tools like ask_claude, ask_gemini, smart_query or deep_search.

There are two routing modes. Session mode sends prompts through the user's existing logged-in browser sessions for ChatGPT, Claude, Gemini and Perplexity, without storing passwords. BYOK mode uses official API keys for providers such as OpenAI, Anthropic, Google, DeepSeek, Groq and Mistral, and can also connect to local models served by Ollama or LM Studio. BYOK keys are stored through the operating system's keychain via Electron SafeStorage.

The project also includes proxima-agent, a Python assistant that edits code, runs tests and drives Chrome over CDP, with permission modes from full auto to suggest-only. It keeps SQLite databases for conversation history, learned fixes and reusable skills. A desktop app, CLI, REST API, WebSocket interface and Python and JavaScript SDKs are provided.

Recursos principais

  • 01Exposes ChatGPT, Claude, Gemini and Perplexity to editors as MCP tools via browser sessions.
  • 02Supports BYOK routing to OpenAI, Anthropic, Google, DeepSeek, Groq, Mistral and other providers.
  • 03Connects to local models running on Ollama or LM Studio.
  • 04Offers multi-model tools such as smart_query, verify and crew.
  • 05Includes an OpenAI-compatible REST API and WebSocket streaming on localhost.
  • 06Provides a Python agent that runs tests and edits code with gated approval modes.

Casos de uso

  • Letting Cursor or VS Code agents query several frontier models without buying separate API plans.
  • Routing coding questions to a fully local Ollama model so code stays on the machine.
  • Cross-checking a model's answer against another provider with the verify or consensus tools.
  • Adding one local OpenAI-compatible endpoint that existing tools can point to.

Tópicos

#mcp#mcp-server#llm#ai-agents#multi-model#ollama#byok#developer-tools#agent#agents

Perguntas frequentes

O que é Proxima?
A local MCP server that routes prompts from Cursor, VS Code, Windsurf or Claude Desktop to ChatGPT, Claude, Gemini, Perplexity, BYOK APIs or local Ollama models. Proxima is a local gateway that exposes several AI models as one MCP server and OpenAI-compatible HTTP endpoint on 127.0.0.1. Coding clients such as Cursor, VS Code, Windsurf and Claude Desktop connect to it over stdio and can call tools like ask_claude, ask_gemini, smart_query or deep_search.
Proxima é gratuito? Qual é a licença?
Proxima é open source sob a licença Other. Confira os termos da licença antes de usá-lo em produtos comerciais.
Proxima ainda é mantido?
Manutenção ativa. O último commit de Proxima foi em 16 de out. de 2026.
Para que posso usar Proxima?
Letting Cursor or VS Code agents query several frontier models without buying separate API plans. Routing coding questions to a fully local Ollama model so code stays on the machine. Cross-checking a model's answer against another provider with the verify or consensus tools. Adding one local OpenAI-compatible endpoint that existing tools can point to.
Onde consigo Proxima?
O código-fonte e as instruções de instalação estão no GitHub: https://github.com/Zen4-bit/Proxima

Resumo gerado por IA a partir do README do projeto. As estatísticas do GitHub são atualizadas diariamente.

Projetos relacionados