Trending repositories: deepseek

21 of 21 repositories

• unslothai/unsloth

  Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.

  AI summary: A local UI and framework for efficiently training and running large language models.

  69,627ai-mlPythonApache-2.0agentdeepseekfine-tuninggemma

• diegosouzapw/OmniRoute

  Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, 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 500+ contributors

  AI summary: A free AI gateway providing access to 290+ providers and 500+ models through a single endpoint.

  42,038ai-mlTypeScriptMITa2aai-agentsai-gatewayanthropic

• Hmbown/CodeWhale

  Open-source, community-driven agent harness

  AI summary: A local, privacy-first AI coding assistant that indexes your entire codebase for deep context awareness.

  40,521developer-toolsRustMITclideepseekllmrust

• Hmbown/CodeWhale

  Open-source, community-driven agent harness

  AI summary: A terminal-based coding assistant that brings LLM-driven file editing and command execution directly to your CLI.

  40,198developer-toolsRustMITclideepseekllmrust

• esengine/DeepSeek-Reasonix

  DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

  AI summary: An optimized reasoning engine designed to enhance the analytical capabilities of DeepSeek models.

  32,837ai-mlGoMITagentagent-frameworkai-agentai-coding

• decolua/9router

  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.

  AI summary: An AI coding gateway connecting multiple tools to 40+ providers with token-saving features.

  24,863ai-mlJavaScriptMITai-agentsai-gatewayanthropicchatgpt

• antirez/ds4

  DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

  AI summary: Lightweight native inference engine optimized for DeepSeek V4 Flash on consumer hardware.

  20,836ai-mlCMITinference-enginedeepseekggmllocal-ai

• datawhalechina/easy-vibe

  💻 The first course for AI-native product builders.

  AI summary: A beginner-friendly, step-by-step tutorial for building applications using modern 'vibe coding' AI workflows.

  18,797learningJavaScriptagentaicodingcourse

• liyupi/ai-guide

  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

  AI summary: A comprehensive, free AI knowledge base focusing on practical tools, deep learning concepts, and LLM application development.

  18,140learningJavaScriptaiartificial-intelligencechatgptclaude

• lidge-jun/opencodex

  Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

  AI summary: A universal provider proxy that allows tools like OpenAI Codex and Claude Code to use any LLM backend.

  8,282developer-toolsTypeScriptMITai-gatewayai-toolsanthropicchatgpt

• OpenCoworkAI/open-codesign

  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.

  AI summary: An open-source, local-first alternative to AI UI generators like Claude Design and v0.

  7,669developer-toolsTypeScriptMITai-designanthropicbyokclaude

• open-multi-agent/open-multi-agent

  TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).

  AI summary: A dynamic TypeScript AI orchestration framework that plans and executes multi-agent workflows at runtime.

  6,736ai-mlTypeScriptMITagent-frameworkagent-orchestrationagentic-aiai-agents

• BlockRunAI/ClawRouter

  The agent-native LLM router for autonomous agents. 66 models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.

  AI summary: LLM router explicitly built for autonomous AI agents using crypto authentication.

  6,683infrastructureTypeScriptMITaiai-agentsanthropiccost-optimization

• open-multi-agent/open-multi-agent

  TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).

  AI summary: A TypeScript orchestration framework that plans multi-agent task DAGs dynamically at runtime.

  6,669developer-toolsTypeScriptMITagent-frameworkagent-orchestrationagentic-aiai-agents

• KunAgent/Kun

  Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

  AI summary: A unified AI agent workspace integrating requirements, design, and code generation.

  5,730developer-toolsTypeScriptOtheragentic-workflowai-agentai-assistantai-design

• OpenBMB/UltraRAG

  A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

  AI summary: A highly-optimized toolkit for building retrieval-augmented generation systems.

  5,689ai-mlPythonApache-2.0deepseekdemoeasyembedding

• deepseek-ai/Engram

  Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

  AI summary: An advanced memory management system for LLMs enabling long-term contextual retention and retrieval.

  4,579ai-mlPythonApache-2.0llm-memorycontext-retrievalai-agentsvector-database

• archestra-ai/archestra

  Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

  AI summary: Secure enterprise AI platform with built-in guardrails and MCP registry.

  4,098infrastructureTypeScriptOthera2aa2a-mcpacpagent

• thu-pacman/chitu

  High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

  AI summary: A high-performance LLM inference engine supporting diverse GPUs and complex deployments.

  3,155infrastructurePythonApache-2.0deepseekgpullmllm-serving

• dwgx/WindsurfAPI

  Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。

  AI summary: A zero-dependency translation layer that converts Windsurf and Devin AI models into standard API formats.

  2,926developer-toolsJavaScriptMITanthropic-compatibleapi-gatewayclaudeclaude-code

• aattaran/deepclaude

  Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.

  AI summary: Run Claude Code's agent loop using DeepSeek V4 Pro or any Anthropic-compatible backend.

  2,238developer-toolsJavaScriptMITclaude-codedeepseekcost-optimizationapi-routing