Search results for "qwen"
โก Lightweight offline AI agent for local models. No cloud, no API keys โ just your GPU.
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
ๅงๆฌๅ้ๆบ่ฝไฝ๏ผPenShot๏ผ๏ผๅงๆฌโๅ้โ็ๆฎตโprompt | ๅบไบ LangGraph+LLM๏ผ่ชๅจ่งฃๆไปปๆๆ ผๅผๅงๆฌ๏ผ็ๆ Sora/Veo/Runway ็ญๆจกๅๅฏ็จ็่ฟ่ดฏtext-to-videoๆ็คบ่ฏใไฟๆ่ง่ฒ/ๅงๆ ่ทจ็ๆฎตไธ่ด๏ผๆฏๆ MCP/REST API/ๅฝๆฐ่ฐ็จ | Pythonๅบ + A2A้ๆใ๏ผLLM-powered screenplay-to-video-prompt a
Secure, Fast, and Extensible Sandbox runtime for AI agents.
๐ซ CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controllin
Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.
An open-source AI assistant framework with skills and agent architecture
LightAgent: Lightweight AI agent framework with memory, tools & tree-of-thought. Supports multi-agent collaboration, self-learning, and major LLMs (OpenAI/DeepSeek/Qwen). Open-source with MCP/SSE prot
MCP Server for Computer Use in Windows
[GenAI Application Development Framework] ๐ Build GenAI application quick and easy ๐ฌ Easy to interact with GenAI agent in code using structure data and chained-calls syntax ๐งฉ Use Event-Driven Flow
Tool that just makes your open source project better using LLM agents
auto-wing is a tool that uses LLM to assist automated testing
Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
Open-source multi-agent AI assistant powered by LangGraph, FastAPI & Next.js โ 16+ agents, Human-in-the-Loop, MCP integration, voice TTS, RAG, 500+ metrics, 6 languages.
An offline AI-powered video analysis tool with object detection (YOLO), image captioning (BLIP), speech transcription (Whisper), audio event detection (PANNs), and AI-generated summaries (LLMs via Oll
A modular RAG (Retrieval-Augmented Generation) system with MCP Server architecture. Using Skill to make AI follow each step of the spec and complete the code 100% by AI.
A High-Availability, Transparent, and Smart Multi-Vendor Proxy for Claude Code. Support Claude Plans, GitHub Copilot, Google Antigravity, ZAI/GLM, MiniMax, Qwen, Xiaomi, Kimi, Doubao...
Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.
Open Framework for AI Agents to play Red Alert through Reinforcement Learning
RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.
Agentic RAG R1 Framework via Reinforcement Learning
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX bac
Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta
Build and run agents you can see, understand and trust.
๐ 2026 ๆ็ณป็ป็ AI Agent ้ๆๆๅ๏ฝๆบ่ฝไฝๅฎๆๆ็จ ยท ๅฎๆดๅญฆไน ่ทฏๅพ + ๅฎๆ้กน็ฎ + ้ข่ฏ้ขๅบ ยท ๅฏนๆ ๅคงๆจกๅๅบ็จๅผๅๅทฅ็จๅธๅฒไฝ ยท ่ฆ็LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / ๆ็คบ่ฏ ยท ไผไธ็บง้จ็ฝฒไธๅพฎ่ฐ ยท ไป0ๅฐไผไธ็บง่ฝๅฐ + ไปๅญฆไน ๅฐไธ็บฟ้กน็ฎ + ้ข่ฏๅๅคไธไฝๅ
[NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents & [arXiv 2026] GTA-2
A high-throughput and memory-efficient inference and serving engine for LLMs
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Open-Source Intelligent Command Layer
OllamaFreeAPI: Free Distributed API for Ollama LLMs Public gateway to our managed Ollama servers with: - Zero-configuration access to 50+ models - Auto load-balanced across global nodes - Free tier w
Unified framework for building enterprise RAG pipelines with small, specialized models
Advanced AI Real Estate Assistant using RAG, LLMs, and Python. Features market analysis, property valuation, and intelligent search.
MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, and Hugging Face's Open Deep Research
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. ๐ Official updates only via twitter @Martin993
A lightweight AI agent framework for vertical domain applications | ้ขๅๅๅๅบ็จ็่ฝป้็บง AI Agent ๆกๆถ
Connect any LLM to OpenClaw โ production-tested middleware for Qwen3-235B and beyond
Agentica: Lightweight async-first Python framework for AI agents. ่ฝป้็บงๅผๆญฅไผๅ ็AI Agentๆกๆถ๏ผๆฏๆๅทฅๅ ท่ฐ็จใRAGใๅคๆบ่ฝไฝๅMCPใ
Lightweight semantic code search engine โ 2-stage vector + FTS + RRF fusion + MCP server for Claude Code
A desktop AI agent that controls your local machine โ runs commands, manages files, executes code, browses the web autonomously etc. Supports Claude, GPT, Gemini, Llama, DeepSeek, and more. .exe avail
Claude Code skills, architectural principles, and alternative approaches for AI-assisted development
Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine โ zero data sent to external services.
The API layer for AI agents. Dashboard + 22K APIs + 18 Direct Call providers. MCP native.
Watchtower is a simple AI-powered penetration testing automation CLI tool that leverages LLMs and LangGraph to orchestrate agentic workflows that you can use to test your websites locally. Generate us
One memory layer for every AI agent. Local-first, markdown source of truth, and CLI/HTTP/MCP native. Your agent forgot who you are. Again. Dory fixes that.
Open-Sable is a local-first autonomous agent framework with AGI-inspired cognitive subsystems (goals, memory, metacognition, tool use). It can run continuously on your machine, integrate with chat int
๐งญ PromptDrifter โ oneโcommand CI guardrail that catches prompt drift and fails the build when your LLM answers change.
KawaiiGPT โ Open-source LLM gateway accessing DeepSeek, Gemini, and Kimi-K2 through reverse-engineered Pollinations API with no API keys required, built-in prompt injection capabilities for security r
Computer Environments Elicit General Agentic Intelligence in LLMs
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Provide a local, privacy-focused AI assistant for Telegram that runs fully on your machine without sending data to the cloud.
Provide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.