Fauxpilot

Fauxpilot is a self-hosted AI coding assistant and local inference server. It functions as a proxy and API gateway that redirects traffic from IDE plugins to a local large language model, allowing for AI-assisted programming without external cloud dependencies.

The project provides a specialized API emulation layer that mimics coding assistant protocols and a standardized OpenAI-compatible interface. This enables supported code editors to use local models for completions and suggestions by overriding default proxy URLs.

The system includes capabilities for downloading and deploying local models, as well as a format-conversion pipeline to transform model files into optimized versions for specific inference engines. A model-agnostic backend allows for switching between different inference engines while maintaining the same API interfaces.

Features

Copilot API Emulators - Replacing a paid subscription service with a self-hosted server that mimics the same API for IDE plugins.

Local Model Inference Servers - Hosts large language models on a self-hosted server to provide local AI-assisted programming.

OpenAI-Compatible APIs - Provides a standardized OpenAI-compatible API for prompts and completions.

AI Coding Assistant Proxies - Functions as a middleware service redirecting IDE plugin traffic from remote clouds to a local backend.

Coding Assistant Protocol Emulation - Implements a specialized API interface that mimics coding assistant protocols for IDE plugin compatibility.

OpenAI-Compatible - Implements a standardized REST interface compatible with OpenAI for AI client communication.

Self-Hosted AI Models - Provides capabilities for downloading, optimizing, and launching large language models on private infrastructure.

Self-Hosted Coding Assistants - Runs a local language model as a private server to provide AI-powered code completions in development environments.

Large Language Model Deployments - Enables downloading and converting large language models to run on private hardware for secure assistance.

AI Proxy Integrations - Connects code editor plugins to a local backend by overriding default proxy URLs.

Cloud API Emulators - Emulates proprietary cloud service APIs to allow editor plugins to use a local server as a drop-in replacement.

Model Conversion Pipelines - Transforms deep learning model files into optimized formats required by specific inference engines.

Model Conversion Utilities - Transforms deep learning model files into optimized formats required by specific inference engines.

Provider-Agnostic Model Interfaces - Separates the API interface from the underlying model to allow switching between different inference engines.

Model Request Proxies - Intercepts network requests from IDE plugins and routes them to the local AI model backend.

AI Coding Assistants - Acts as a self-hosted alternative to proprietary AI coding servers.

AI Code Completion - Self-hosted alternative for code completion suggestions.

fauxpilotfauxpilot

Features

Star history