Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Repository Index
47,133 repositories indexed
1–24 of 50 · Most stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
- fine-tuning
- llama
- llms
- gemma
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
- chatglm
- langchain
- llm
- knowledge-base
SGLang is a high-performance serving framework for large language models and multimodal models.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
- semantic-search
- emacs
- obsidian-md
- chat
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
- claude-code
- cursor
- ai-agents
- ai-gateway
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Translated🔥 MaxKB is an open-source platform for building enterprise-grade agents. A powerful and easy-to-use open-source enterprise-grade agent platform.
TranslatedThe official repo of Qwen chat & pretrained large language model proposed by Alibaba Cloud.
- chinese
- large-language-models
- natural-language-processing
- flash-attention
Translated🎭 277 plug-and-play AI expert roles — supporting 20 tools such as Claude Code/Cursor/Copilot, covering 20 departments including engineering/design/marketing/finance. Includes 64 original agents for the Chinese market (Xiaohongshu/Douyin/WeChat/Feishu/DingTalk/Qt host computer software/mechanical design). Paired with the orchestrator agency-orchestrator, a single sentence lets multiple experts collaborate automatically as a DAG.
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
- chatbot
- chatgpt-api
- chatglm
- claude
TranslatedLangGPT: Empowering everyone to become a prompt expert! 🚀 📌 Proposer of Structured Prompt 📌 Initiator of Meta-Prompt 📌 The most popular paradigm for putting prompts into practice | Language of GPT The pioneering framework for structured & meta-prompt design 10,000+ ⭐ | Battle-tested by thousands of users worldwide Created by 云中江树 (Yunzhong Jiangshu, "river and trees amid the clouds")
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- decision-model
- jev
- qwen3
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
- interpretability
- mechanistic-interpretability
- qwen
- steering
Local CLI Copilot, powered by Ollama. 💻🦙