su-kaka/gcli2api
Gcli2api
This project is an AI API gateway and proxy that translates and normalizes requests between different AI model formats to ensure compatibility across client applications. It functions as a middleware service that can transform local command-line binaries into web services, allowing them to be triggered via HTTP requests.
The system is distinguished by its ability to route multimodal text and image inputs and extract internal reasoning chains from model outputs to separate the chain of thought from the final answer. It includes an authentication manager that automatically cycles through multiple OAuth tokens to distribute request load and bypass rate limits.
The capability surface covers credential health tracking, real-time log streaming via WebSockets, and a web administration console for bulk credential management. Data persistence is handled through a pluggable backend supporting either local SQLite or distributed MongoDB instances.
The application can be deployed using Docker container images or through automation for mobile terminal environments via Termux.
Features
- AI API Gateways - Functions as an AI API gateway that translates and normalizes requests between different model formats.
- Dual-Format Request Proxies - Provides a proxy that accepts multiple AI API formats and translates them for various backend model providers.
- AI Gateways - Provides a multimodal gateway for routing text and image data and extracting reasoning chains.
- API Format Standardizers - Translates diverse LLM API specifications into a standardized format to ensure compatibility across clients.
- Multimodal Processing - Integrates text and image modalities within a unified interface for AI model processing.
- Unified Multimodal APIs - Provides a unified API interface for processing combined text and image inputs for visual analysis.
- Provider-Agnostic Request Normalization - Normalizes internal request formats into provider-specific structures to maintain compatibility across different AI models.
- HTTP - Transforms local command-line binaries into web services triggered via HTTP requests.
- HTTP Service Wrappers - Transforms local command-line binaries into web services with standardized request and response formats.
- API Key Rotation - Distributes request load across a pool of authentication keys to automatically bypass provider rate limits.
- AI Provider Proxies - Proxies traffic to AI providers while normalizing request structures for cross-model compatibility.
- API Credential Managers - Centralizes the storage and lifecycle management of authentication tokens required for external AI services.
- Token Load Balancers - Rotates multiple OAuth tokens automatically to distribute request load and ensure stability through redundancy.
- Command-to-API Mapping - Implements logic that maps incoming HTTP requests to local command-line binaries for AI service execution.
- Binary-to-HTTP Wrappers - Transforms local command-line binaries into web services that can be triggered via HTTP requests.
- Streaming Chat Responses - Delivers AI-generated text to clients incrementally with anti-truncation logic for real-time interaction.
- Vision Model Inputs - Intercepts and routes text and image data to enable visual analysis via vision-capable language models.
- Reasoning Chain Parsers - Parses and separates a model's internal chain of thought from the final answer in API responses.
- Credential Rotators - Automatically cycles through OAuth tokens to distribute request load and bypass rate limits.
- Log Streaming - Streams system logs in real-time via WebSockets to a web administration console.
- Incremental Content Streaming - Sends model responses incrementally using a chunked transfer mechanism for real-time UI updates.
