| 1 |
ollama |
175898 |
16930 |
Go |
2313 |
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. |
2026-07-10T00:42:15Z |
| 2 |
transformers |
162469 |
33861 |
Python |
1029 |
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. |
2026-07-10T22:00:52Z |
| 3 |
JavaGuide |
156942 |
46171 |
JavaScript |
57 |
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发 |
2026-07-06T14:54:42Z |
| 4 |
DeepSeek-V3 |
103890 |
16732 |
Python |
192 |
None |
2025-08-28T03:24:37Z |
| 5 |
DeepSeek-R1 |
91983 |
11710 |
None |
21 |
None |
2025-06-27T08:35:54Z |
| 6 |
vllm |
85945 |
19256 |
Python |
1961 |
A high-throughput and memory-efficient inference and serving engine for LLMs |
2026-07-11T05:20:27Z |
| 7 |
lobehub |
79728 |
15584 |
TypeScript |
209 |
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. |
2026-07-11T05:45:43Z |
| 8 |
LlamaFactory |
73153 |
8936 |
Python |
977 |
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) |
2026-07-10T13:15:44Z |
| 9 |
unsloth |
68011 |
6123 |
Python |
796 |
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. |
2026-07-11T05:39:20Z |
| 10 |
gpt4free |
66459 |
13554 |
Python |
3 |
The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3 |
2026-07-10T14:55:03Z |
| 11 |
openinterpreter |
64335 |
5607 |
Rust |
267 |
A lightweight coding agent for open models like Deepseek, Kimi, and Qwen |
2026-07-07T00:59:25Z |
| 12 |
cherry-studio |
48429 |
4599 |
TypeScript |
937 |
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs |
2026-07-11T05:47:07Z |
| 13 |
CowAgent |
45917 |
10261 |
Python |
21 |
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat) |
2026-07-09T17:03:36Z |
| 14 |
new-api |
41825 |
9693 |
Go |
582 |
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥 |
2026-07-11T05:26:21Z |
| 15 |
chatbox |
40961 |
4145 |
TypeScript |
1117 |
Powerful AI Client |
2026-06-12T08:17:17Z |
| 16 |
LibreChat |
40565 |
8329 |
TypeScript |
313 |
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active |
2026-07-10T19:47:30Z |
| 17 |
CodeWhale |
39680 |
3418 |
Rust |
287 |
Open-source, community-driven agent harness |
2026-07-10T21:16:14Z |
| 18 |
mindshub |
39394 |
6221 |
Makefile |
1 |
Make AI do actual work. Swap the model anytime — keep everything you’ve built. |
2026-07-10T16:53:47Z |
| 19 |
GPT_API_free |
38743 |
2667 |
None |
10 |
Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。 |
2026-07-03T17:18:26Z |
| 20 |
awesome-deepseek-integration |
38167 |
4176 |
None |
36 |
Integrate the DeepSeek API into popular software |
2026-02-23T16:27:47Z |
| 21 |
one-api |
35632 |
6730 |
JavaScript |
924 |
LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI. |
2026-01-09T03:26:43Z |
| 22 |
sglang |
30166 |
7078 |
Python |
692 |
SGLang is a high-performance serving framework for large language models and multimodal models. |
2026-07-11T05:38:01Z |
| 23 |
sim |
29031 |
3696 |
TypeScript |
106 |
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce. |
2026-07-11T05:43:45Z |
| 24 |
FastGPT |
28903 |
7212 |
TypeScript |
142 |
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. |
2026-07-10T10:04:49Z |
| 25 |
repomix |
27055 |
1430 |
TypeScript |
139 |
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more. |
2026-07-11T00:40:07Z |
| 26 |
DeepSeek-Reasonix |
26634 |
1669 |
Go |
920 |
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running. |
2026-07-11T05:14:07Z |
| 27 |
open-r1 |
26400 |
2447 |
Python |
291 |
Fully open reproduction of DeepSeek-R1 |
2026-04-02T14:03:15Z |
| 28 |
DeepSeek-Coder |
23858 |
2881 |
Python |
138 |
DeepSeek Coder: Let the Code Write Itself |
2025-11-11T06:44:56Z |
| 29 |
DeepSeek-OCR |
23551 |
2173 |
Python |
249 |
Contexts Optical Compression |
2026-01-27T03:45:14Z |
| 30 |
promptfoo |
23139 |
2068 |
TypeScript |
94 |
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic. |
2026-07-11T05:47:10Z |
| 31 |
9router |
21664 |
3646 |
JavaScript |
640 |
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. |
2026-07-10T11:14:10Z |
| 32 |
dyad |
20892 |
2519 |
TypeScript |
253 |
Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it! |
2026-07-11T00:40:37Z |
| 33 |
DB-GPT |
19442 |
2812 |
Python |
371 |
open-source agentic AI data assistant for the next generation of AI + Data products. |
2026-07-10T05:17:54Z |
| 34 |
kirara-ai |
18846 |
1832 |
Python |
3 |
🤖 可 DIY 的 多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenAI | 工作流系统、网页搜索、AI画图、人设调教、虚拟女仆、语音对话 | |
2025-06-28T19:24:48Z |
| 35 |
ds4 |
18168 |
1564 |
C |
100 |
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm |
2026-07-03T17:30:19Z |
| 36 |
easy-vibe |
18038 |
1719 |
JavaScript |
12 |
💻 vibe coding 2026 | Your First Modern Coding course beginners to master step by step. |
2026-07-06T14:19:33Z |
| 37 |
ai-guide |
17117 |
1932 |
JavaScript |
0 |
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cursor / Claude Code / TRAE / Codex / Copilot）、AI 开发框架教程（Spring AI / LangChain）、AI 产品变现指南，帮你快速掌握 AI 技术，走在时代前沿。本项目为开源文档 aiguide，已升级为鱼皮 AI 导航网站 |
2026-07-01T14:44:50Z |
| 38 |
agency-agents-zh |
17092 |
2912 |
Shell |
3 |
🎭 266 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 50 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。 |
2026-07-07T06:51:48Z |
| 39 |
LangBot |
16828 |
1486 |
Python |
105 |
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow |
2026-07-11T04:39:18Z |
| 40 |
OmniRoute |
15194 |
2318 |
TypeScript |
204 |
Never stop coding. Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA. |
2026-07-11T05:15:45Z |
| 41 |
ms-swift |
14777 |
1526 |
Python |
615 |
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, …) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, …) (AAAI 2025). |
2026-07-10T07:52:05Z |
| 42 |
TinyZero |
13192 |
1582 |
Python |
73 |
Minimal reproduction of DeepSeek R1-Zero |
2026-02-27T05:42:07Z |
| 43 |
Fay |
13005 |
2306 |
Python |
124 |
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。 |
2026-06-18T09:14:38Z |
| 44 |
OpenLLM |
12388 |
822 |
Python |
6 |
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. |
2026-06-29T16:55:17Z |
| 45 |
wechat-bot |
11175 |
1268 |
JavaScript |
114 |
🤖 Multi-platform IM AI Agent for Telegram, WhatsApp, Lark, and WeChat. Connects ChatGPT / Claude / Kimi / DeepSeek / Ollama / Pi for auto-replies, community analysis, contact management, and inactive-friend detection. |
2026-07-08T18:36:31Z |
| 46 |
Bob |
9703 |
523 |
None |
108 |
Bob 是一款 macOS 平台的翻译和 OCR 软件。 |
2025-12-30T13:26:12Z |
| 47 |
all-in-rag |
9408 |
4689 |
Python |
13 |
🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/ |
2026-06-05T08:29:26Z |
| 48 |
oumi |
9338 |
783 |
Python |
0 |
Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM! |
2026-07-11T03:13:51Z |
| 49 |
Noi |
8953 |
704 |
TypeScript |
217 |
🚀 Less chaos. More flow. |
2026-02-04T12:11:52Z |
| 50 |
ipex-llm |
8863 |
1428 |
Python |
1213 |
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc. |
2026-01-28T17:32:40Z |
| 51 |
magic-resume |
8736 |
977 |
TypeScript |
5 |
free online AI resume editor，the only official website is https://magicv.art |
2026-06-15T15:56:37Z |
| 52 |
read-frog |
8372 |
559 |
TypeScript |
107 |
🐸 Read Frog - Open Source Immersive Translate | 🐸 陪读蛙 - 开源沉浸式翻译 |
2026-07-10T21:07:24Z |
| 53 |
deep-searcher |
7940 |
769 |
Python |
42 |
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python. |
2025-11-19T06:04:16Z |
| 54 |
forgecode |
7455 |
1446 |
Rust |
34 |
AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models |
2026-07-11T01:36:30Z |
| 55 |
Awesome-MCP-ZH |
7417 |
637 |
None |
2 |
MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients |
2026-07-03T22:06:18Z |
| 56 |
open-codesign |
7240 |
766 |
TypeScript |
47 |
Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT. |
2026-06-28T22:04:03Z |
| 57 |
DeepSeek-LLM |
7191 |
1272 |
Makefile |
54 |
DeepSeek LLM: Let there be answers |
2024-02-04T12:22:16Z |
| 58 |
DeepSeek-Coder-V2 |
6897 |
1097 |
None |
66 |
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence |
2025-11-11T06:44:45Z |
| 59 |
go-stock |
6828 |
1213 |
Go |
14 |
🦄🦄🦄AI赋能股票分析：AI加持的股票分析/选股工具。股票行情获取，AI热点资讯分析，AI资金/财务分析，涨跌报警推送。支持A股，港股，美股。支持市场整体/个股情绪分析，AI辅助选股等。数据全部保留在本地。支持DeepSeek，OpenAI， Ollama，LMStudio，AnythingLLM，硅基流动，火山方舟，阿里云百炼等平台或模型。 |
2026-07-11T03:43:18Z |
| 60 |
WeChatFerry |
6762 |
1556 |
C++ |
1 |
微信机器人，可接入DeepSeek、Gemini、ChatGPT、ChatGLM、讯飞星火、Tigerbot等大模型。微信 hook WeChat Robot Hook. |
2026-07-10T15:38:48Z |
| 61 |
codecompanion.nvim |
6739 |
435 |
Lua |
0 |
✨ AI Coding, Vim Style |
2026-07-10T21:45:23Z |
| 62 |
yn |
6653 |
927 |
TypeScript |
60 |
A highly extensible Markdown editor. Version control, AI Copilot, mind map, documents encryption, code snippet running, integrated terminal, chart embedding, HTML applets, Reveal.js, plug-in, and macro replacement. |
2026-06-30T07:53:56Z |
| 63 |
ClawRouter |
6648 |
626 |
TypeScript |
26 |
The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402. |
2026-07-11T02:08:20Z |
| 64 |
Firefly |
6645 |
584 |
Python |
203 |
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型 |
2024-10-24T02:27:42Z |
| 65 |
open-multi-agent |
6558 |
2407 |
TypeScript |
10 |
TypeScript multi-agent orchestration framework. Describe a goal, a coordinator decomposes it into a task DAG that runs on any LLM: Claude, ChatGPT, Gemini, DeepSeek, or local models. |
2026-07-11T04:07:44Z |
| 66 |
SQLBot |
6384 |
783 |
JavaScript |
87 |
🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG. |
2026-07-10T09:34:07Z |
| 67 |
chinese-llm-benchmark |
6265 |
256 |
None |
14 |
非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 |
2026-07-09T02:42:12Z |
| 68 |
Everywhere |
6152 |
381 |
C# |
22 |
On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps. |
2026-07-10T15:11:11Z |
| 69 |
deepchat |
6093 |
692 |
TypeScript |
7 |
🐬DeepChat - A smart assistant that connects powerful AI to your personal world |
2026-07-11T04:54:32Z |
| 70 |
Awesome-AITools |
6080 |
667 |
Python |
4 |
Collection of AI-related utilities. Welcome to submit pull requests /收藏AI相关的实用工具，欢迎提交pull requests |
2026-07-08T01:49:17Z |
| 71 |
rikkahub |
5986 |
454 |
Kotlin |
192 |
RikkaHub is an Android APP that supports for multiple LLM providers. |
2026-07-10T11:34:48Z |
| 72 |
paperless-ai |
5809 |
317 |
JavaScript |
54 |
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents. |
2026-07-05T00:37:35Z |
| 73 |
pyspur |
5754 |
428 |
TypeScript |
29 |
A visual playground for agentic workflows: Iterate over your agents 10x faster |
2026-06-29T17:53:12Z |
| 74 |
UltraRAG |
5638 |
435 |
Python |
7 |
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines |
2026-07-11T05:24:17Z |
| 75 |
Awesome-LLM-Inference |
5382 |
421 |
Python |
1 |
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉 |
2026-06-23T03:48:43Z |
| 76 |
deepreasoning |
5364 |
439 |
Rust |
50 |
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1’s CoT reasoning traces with Anthropic Claude models. |
2025-10-07T05:28:22Z |
| 77 |
ComfyUI-Copilot |
5355 |
347 |
TypeScript |
43 |
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance |
2026-04-07T04:23:08Z |
| 78 |
DeepSeek-VL2 |
5312 |
1811 |
Python |
101 |
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding |
2025-02-26T05:03:42Z |
| 79 |
gpustack |
5300 |
566 |
Python |
576 |
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances. |
2026-07-10T08:44:05Z |
| 80 |
cube-studio |
5067 |
884 |
Python |
33 |
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台自动化标注，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型市场，支持国产cpu/gpu/npu 昇腾生态，支持RDMA，支持pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/ray/volcano等分布式 |
2026-06-10T03:00:21Z |
| 81 |
EasyR1 |
5057 |
375 |
Python |
48 |
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL |
2026-04-06T09:05:50Z |
| 82 |
openclaw-zero-token |
5053 |
1205 |
TypeScript |
1 |
OpenClaw: Use All Major AI Models NO API Token! Claude/ChatGPT/Gemini/DeepSeek/Doubao/Grok/Qwen/Manus/Kimi |
2026-07-10T03:57:33Z |
| 83 |
PasteMD |
5038 |
300 |
Python |
24 |
一键将 Markdown 和网页 AI 对话（ChatGPT/DeepSeek等）完美粘贴到 Word、WPS 和 Excel 的效率工具 | One-click paste Markdown and AI responses (ChatGPT/DeepSeek) into Word, WPS, and Excel perfectly. |
2026-07-06T03:49:23Z |
| 84 |
DeepSeek-V2 |
5015 |
544 |
None |
85 |
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model |
2024-09-25T10:23:55Z |
| 85 |
fastllm |
4845 |
478 |
C++ |
293 |
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。 |
2026-06-25T08:15:49Z |
| 86 |
ds2api |
4748 |
1556 |
Go |
26 |
DeepSeek-Compatible Middleware Interface: A technical exploration project in Go, focusing on high-concurrency protocol adaptation. It serves as a reference implementation for converting diverse web protocols into standardized formats. |
2026-05-10T15:33:52Z |
| 87 |
axonhub |
4657 |
579 |
Go |
59 |
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing. |
2026-07-11T05:12:28Z |
| 88 |
deep-research |
4634 |
1054 |
JavaScript |
31 |
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server. |
2026-06-18T14:43:29Z |
| 89 |
awesome-deepseek-agent |
4629 |
558 |
None |
91 |
None |
2026-06-17T01:24:37Z |
| 90 |
costrict |
4289 |
186 |
TypeScript |
5 |
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion. |
2026-07-09T13:15:06Z |
| 91 |
SmartSub |
4235 |
295 |
TypeScript |
33 |
本地优先的一站式桌面字幕工具，内置 6 种 ASR 引擎与全平台 GPU 加速及 17+ 翻译服务商，覆盖音视频转写、翻译、校对、字幕烧录封装全流程，跨 Windows/macOS/Linux 运行 |
2026-07-10T07:27:45Z |
| 92 |
ruby_llm |
4235 |
474 |
Ruby |
33 |
One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code. |
2026-07-07T20:15:37Z |
| 93 |
csghub |
4181 |
523 |
Vue |
24 |
CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️ |
2026-07-06T01:13:10Z |
| 94 |
DeepSeek-VL |
4133 |
592 |
Python |
44 |
DeepSeek-VL: Towards Real-World Vision-Language Understanding |
2024-04-24T05:01:06Z |
| 95 |
archestra |
3959 |
1108 |
TypeScript |
36 |
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator |
2026-07-11T03:24:48Z |
| 96 |
autoMate |
3929 |
490 |
Python |
0 |
Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves |
2026-04-30T08:58:08Z |
| 97 |
deep-chat |
3663 |
445 |
TypeScript |
31 |
Fully customizable AI chatbot component for your website |
2026-07-10T13:54:48Z |
| 98 |
Awesome-LLM-Reasoning |
3648 |
212 |
None |
5 |
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓 |
2026-04-20T00:57:27Z |
| 99 |
MCP-Chinese-Getting-Started-Guide |
3537 |
222 |
None |
6 |
Model Context Protocol(MCP) 编程极速入门 |
2025-04-23T14:06:41Z |
| 100 |
command-code |
3479 |
339 |
None |
134 |
Command Code AI |
2026-06-26T14:28:35Z |