linux-do/override

Health v2 · maintenance only

Adoption not part of the score

1187 stars · 234 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Go-based local proxy service that overrides GitHub Copilot's API endpoints in VSCode and JetBrains IDEs, redirecting code completion and chat requests to alternative LLM providers such as OpenAI-compatible APIs, DeepSeek, Siliconflow, or local Ollama models. It runs on 127.0.0.1 and is configured via config.json or environment variables.

Use cases

• use custom LLM API keys with GitHub Copilot in VSCode
• route Copilot code completion to DeepSeek Coder FIM
• use local Ollama models for IDE code completion
• map Copilot chat requests to a different chat model
• avoid Siliconflow TPM rate limits with multiple API keys
• override Copilot endpoints in JetBrains IDEs

When to choose

• you have your own LLM API keys and want IDE-native Copilot-style completion and chat
• you want to use free or local models (Ollama, Qwen) for code completion
• you need model mapping and multi-key rotation behind Copilot's interface

When to avoid

• you have an official Copilot subscription and don't need custom backends
• you need a fully supported, warrantied product rather than a community proxy hack
• your organization prohibits redirecting Copilot traffic to third-party endpoints

Facets

service · maturity active

proxy llm-inference http-server configuration-management developer-tools large-language-models apis windows self-hosted go copilot-proxy code-completion api-override vscode jetbrains ollama deepseek siliconflow linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="linux-do/override")