Tag

CC-Switch is a cross-platform desktop application serving as an all-in-one assistant for Claude Code, Codex, and Gemini CLI. It unifies management of provider configurations, MCP servers, Skills extensions, and system prompts, enabling seamless switching between AI APIs, latency testing, import/export, and full lifecycle handling for MCP and Skills.

Hosts a web + multi-platform AI chat platform and an open-source, self-hostable client that connects to many LLMs, offers image generation, and one-click deploy; notable for multi-model support and easy self-hosting.

Runs LLMs, vision, audio and multimodal models locally with an OpenAI-compatible API, supporting CPU-only and GPU acceleration across 35+ backends. Includes built-in agents, multi-user access controls, a model gallery, and privacy-first local inference.

Enterprise-grade multi-agent orchestration framework that builds, runs, and scales autonomous agent swarms for production. Offers modular swarm architectures, protocol support (MCP, AOP), a marketplace, multi-model provider integrations and observability.

Unifies multiple LLMs into a single chat+agent workspace for building custom assistants. Offers provider-agnostic model access (OpenAI, Gemini, Claude, Ollama), RAG knowledge-bases, plugins/MCP marketplace, and self-hosting (Docker/Vercel). ([github.com](https://github.com/lobehub/lobe-chat?utm_source=openai))

Unified Python SDK and self-hostable AI Gateway that exposes 100+ LLMs through an OpenAI-compatible API, with cost tracking, routing/fallback, guardrails and observability—for ML platform teams and engineers building multi-provider LLM integrations.

Framework for unit-testing, evaluating and benchmarking LLM systems with ready-made metrics (G‑Eval, hallucination, task completion), support for local judge models and synthetic datasets, plus CI-friendly integrations for LangChain/OpenAI/Anthropic.

Enables building multi-agent LLM applications where agents converse, call tools, and orchestrate workflows. Ships a Python SDK, multi-provider model clients, MCP tool integrations, and a low-code AutoGen Studio for rapid prototyping. ([github.com](https://github.com/microsoft/autogen))

Qwen-Agent is an open-source agent framework from the Qwen team (Alibaba) for building LLM applications on top of Qwen models (Qwen >= 3.0). It supports function/tool calling, MCP, RAG, code interpreter, and ships with example apps like browser assistants and code-interpreter assistants.

AI Engineering Hub is a comprehensive GitHub repository offering in-depth tutorials and 93+ production-ready projects on LLMs, RAGs, AI agents, and real-world AI applications for all skill levels.

Turns websites into structured APIs and datasets for AI workflows. Offers no-code recorder and LLM-driven extraction, crawl/scrape/search robots, SDK/CLI, self-hosting (Docker), and integrations for spreadsheet exports and RAG pipelines.