Trending repositories: agent

62 tracked repositories tagged with agent, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

62 of 62 repositories

  • anomalyco/opencode

    The open source coding agent.

    AI summary: An open-source AI coding agent providing an accessible alternative to proprietary coding assistants.

    211,731developer-toolsTypeScriptMIT
  • TauricResearch/TradingAgents

    TradingAgents: Multi-Agents LLM Financial Trading Framework

    AI summary: A robust research framework for developing, testing, and deploying autonomous AI agents for algorithmic financial trading.

    109,751dataPythonApache-2.0
  • Leonxlnx/taste-skill

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

    AI summary: An anti-slop frontend framework and skill set designed to prevent AI agents from generating generic, poorly designed UI.

    92,557developer-toolsJavaScriptMIT
  • koala73/worldmonitor

    Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

    AI summary: A real-time global intelligence dashboard utilizing AI and dual map engines to track geopolitical and infrastructure signals.

    87,764dataTypeScriptAGPL-3.0
  • bytedance/deer-flow

    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 tasks that could take minutes to hours.

    AI summary: An open-source super-agent framework that orchestrates sub-agents, memory, and sandboxes to perform deep exploration and research.

    83,385ai-mlPythonMIT
  • datawhalechina/hello-agents

    📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

    AI summary: A comprehensive, open-source tutorial project for understanding and building AI agents from scratch.

    81,668learningPythonOther
  • shareAI-lab/learn-claude-code

    Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

    AI summary: An educational repository detailing the underlying engineering required to build robust AI agent harnesses.

    77,934learningPythonMIT
  • unslothai/unsloth

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

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

    77,160ai-mlPythonApache-2.0
  • headroomlabs-ai/headroom

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    AI summary: A context compression layer that significantly reduces token usage for AI agents while preserving accuracy.

    74,282ai-mlPythonApache-2.0
  • calesthio/OpenMontage

    World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

    AI summary: An open-source, automated video editing tool that dynamically pieces together clips based on text or audio transcripts.

    63,046developer-toolsPythonAGPL-3.0
  • bojieli/ai-agent-book

    《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

    AI summary: A comprehensive open-source book covering the theory, architecture, and practical implementation of AI agents.

    52,012learningPythonApache-2.0
  • alibaba/open-code-review

    Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

    AI summary: A hybrid code review system blending deterministic static analysis pipelines with LLM agents, battle-tested at Alibaba scale.

    43,680developer-toolsGoApache-2.0
  • herdrdev/herdr

    the runtime your coding agents live on

    AI summary: A lightweight, decentralized device management system for tracking and controlling fleets of IoT devices.

    41,917infrastructureRustApache-2.0
  • AstrBotDevs/AstrBot

    AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

    AI summary: A multi-platform AI chatbot framework supporting QQ, WeChat, and Telegram with rich plugin capabilities.

    41,344productivityPythonAGPL-3.0
  • bytedance/UI-TARS-desktop

    The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

    AI summary: An open-source multimodal AI agent stack designed to connect frontier models with desktop automation infrastructure.

    39,211ai-mlTypeScriptApache-2.0
  • CopilotKit/CopilotKit

    The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

    AI summary: Framework for integrating AI agents and Generative UI components into web and mobile apps.

    37,716webTypeScriptMIT
  • esengine/DeepSeek-Reasonix

    A reliable coding agent for complex software engineering tasks.

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

    35,740ai-mlGoMIT
  • agentscope-ai/QwenPaw

    Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

    AI summary: A highly extensible personal AI assistant featuring three-layer memory and multi-channel integration.

    35,440ai-mlTypeScriptApache-2.0
  • zeroclaw-labs/zeroclaw

    Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀

    AI summary: A minimal, zero-dependency framework for building lightweight autonomous AI agents.

    32,923ai-mlRustApache-2.0
  • agentscope-ai/agentscope

    Build and run agents you can see, understand and trust.

    AI summary: A developer-centric multi-agent platform with built-in fault tolerance and drag-and-drop orchestration.

    32,752ai-mlPythonApache-2.0
  • Tencent/WeKnora

    Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

    AI summary: A comprehensive dialog framework and skill system integrated with the WeChat Dialog Open Platform.

    32,001ai-mlGoOther
  • iOfficeAI/OfficeCLI

    OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required.

    AI summary: An AI-powered command-line interface for interacting with and generating Office documents.

    31,493productivityC#Apache-2.0
  • alibaba/page-agent

    JavaScript in-page GUI agent. Control web interfaces with natural language.

    AI summary: A client-side JavaScript GUI agent for controlling web interfaces via natural language.

    29,325developer-toolsTypeScriptMIT
  • BloopAI/vibe-kanban

    Get 10X more out of Claude Code, Codex or any coding agent

    AI summary: A kanban-based planning and workspace orchestration tool for coding agents.

    28,256productivityRustApache-2.0
  • TencentCloud/TencentDB-Agent-Memory

    TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.

    AI summary: A team-level memory hub governing chat, skills, wikis, and code graphs for AI agents.

    27,682dataTypeScriptOther
  • tanweai/pua

    你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

    AI summary: An aggressive productivity skill that forces AI agents to strictly adhere to goals by simulating a high-pressure performance review.

    19,710developer-toolsPython
  • datawhalechina/easy-vibe

    💻 vibe coding 101|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.

    19,622learningJavaScript
  • nesquena/hermes-webui

    Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

    AI summary: A lightweight, dependency-free vanilla JS web interface for controlling and interacting with the Hermes autonomous agent.

    18,732ai-mlPythonMIT
  • microsoft/agent-lightning

    The absolute trainer to light up AI agents.

    AI summary: A multi-framework trainer that optimizes AI agents using reinforcement learning and automatic prompt optimization with zero code changes.

    18,551ai-mlPythonMIT
  • NanmiCoder/cc-haha

    Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.

    AI summary: A macOS desktop GUI for managing and visualizing Claude Code sessions with interactive tools.

    14,852developer-toolsTypeScriptMIT
  • superset-sh/superset

    Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

    AI summary: A cross-platform desktop IDE for discovering, configuring, and orchestrating multiple AI CLI agents simultaneously.

    14,837developer-toolsTypeScriptOther
  • ConardLi/garden-skills

    ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.

    AI summary: A curated collection of production-ready Agent Skills to enhance AI coding agents like Claude Code and Cursor.

    12,720developer-toolsCSSMIT
  • zilliztech/claude-context

    Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

    AI summary: An MCP implementation that gives Claude Code semantic search capabilities across your entire codebase.

    12,587developer-toolsTypeScriptMIT
  • holaboss-ai/holaOS

    Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.

    AI summary: A unified, local-first operating system workspace for managing, orchestrating, and interacting with multiple AI agents.

    11,453developer-toolsTypeScriptOther
  • tambo-ai/tambo

    Generative UI SDK for React

    AI summary: An open-source generative UI toolkit for React that seamlessly handles streaming, state, and MCP integrations.

    11,181webTypeScriptMIT
  • aden-hive/hive

    Multi-Agent Harness for Production AI

    AI summary: A production-grade execution harness for building, coordinating, and scaling multi-agent AI systems.

    11,090ai-mlPythonApache-2.0
  • StarTrail-org/PixelRAG

    https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

    AI summary: A scalable visual retrieval-augmented generation framework using web screenshots instead of parsed text.

    10,145ai-mlPythonApache-2.0
  • thesysdev/openui

    The Open Standard for Generative UI

    AI summary: A renderer-agnostic Generative UI framework utilizing a compact, streaming-first language for LLMs.

    9,966webTypeScriptMIT
  • wonderwhy-er/DesktopCommanderMCP

    This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

    AI summary: An MCP server that provides Claude with extensive terminal control, file system search, and advanced editing.

    9,898developer-toolsTypeScriptMIT
  • freecodexyz/free-code

    The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.

    AI summary: A telemetry-free fork of Claude Code that removes prompt guardrails and unlocks 54 experimental CLI features.

    8,758developer-toolsTypeScript