| 08/27 | 8 |
Framework for building agents and LLM-powered applications with modular components and integrations.
|
| 08/27 | 8 |
Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.
|
| 08/27 | 7 |
Proxy server providing OpenAI, Gemini, Claude, Codex, and Qwen compatible API interfaces for CLI models with multi-account support.
|
| 08/27 | 7 |
Local-first Gemini-focused AI workflow WebUI integrating multimodal chat, canvas, file handling, real-time search, code execution, and advanced reasoning.
|
| 08/27 | 7 |
Gemini web proxy that exposes an OpenAI-compatible API with model mapping, token usage reporting, Chrome 146 impersonation, and SQLite-backed settings via an admin UI.
|
| 08/27 | 7 |
High-performance AI API transparent proxy with intelligent key management and load balancing for enterprise use.
|
| 08/27 | 6 |
Framework for building agents and LLM-powered applications with modular components and integrations.
|
| 08/27 | 6 |
Framework for building agents and LLM-powered applications with modular components and integrations.
|
| 08/27 | 6 |
Framework for building agents and LLM-powered applications with modular components and integrations.
|
| 08/27 | 6 |
Framework for building agents and LLM-powered applications with modular components and integrations.
|
| 08/27 | 6 |
Minimal CLI and web UI for GPT Image 2 generation with OAuth or API-key auth, parallel and image-to-image workflows, and persistent history.
|
| 08/27 | 4 |
Multi-model development system orchestrating Codex for backend and Gemini for frontend with Claude coordinating and reviewing patches.
|
| 08/27 | 4 |
Command-line AI workflow tool that connects to tools, understands code, and accelerates workflows.
|
| 08/27 | 3 |
High-performance AI API transparent proxy with intelligent key management and load balancing for enterprise use.
|