Python agents

A powerful task-oriented dialogue agent that can collect information through structured conversations. It supports dynamic field validation, multi-field information extraction, and state management.

A copy of Home Assistant's built-in OpenAI Conversation Agent, with support for changing the base url

RobotFramework-AI is a library that adds AI functionality to the Robot Framework. It can generate test data for you using the RealTestDataGenerator but also reply to your messages with the Chatbot.

An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.

Online-adaptive multi-agent framework for enterprise API orchestration. Adaptive circuit breakers, SLA-driven routing, hybrid LLM+rule intent parser. Apache 2.0.

ToolAgents is a lightweight and flexible framework for creating function-calling agents with various language models and APIs.

AI-powered crypto perpetual futures trading bot for Hyperliquid DEX.

TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.

Neural Interactive Responsive Agent (N.I.R.A)

One command to turn any codebase into an MCP server

Efficient multi-agent task automation and management system.

Code for "Context-aware Communication for Multi-agent Reinforcement Learning"

ggplab이 실제로 쓰는 1인팀 운영 플레이북 — 전략·시간계측·AI 업무시스템

Scholar-Agent Intelligent Research Assistant, Literature Search, Metric Extraction, AI Analysis

📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent workflows (ReAct/Plan-Act/RePlan), long-term memory, and traceable evidence. Built with LangChain + LangGraph + Streamlit.

Self-hosted AI technical workbench. Visual, persistent, multi-stream. Development, architecture, and operational analytics without losing context.

Cortex is a fast, private desktop AI assistant for running local Large Language Models with Ollama. Everything stays on your device: no cloud, no external servers, and no third parties.

[ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents

AgenticInternet is an innovative project focused on empowering agents to autonomously browse, interact, and collaborate across the web. Our goal is to create an intelligent assistant capable of executing complex online workflows, enhancing productivity and creativity for end-users and organizations.

Submit your AI tool or AI Agent in AI directories

Enterprise-grade distributed AI agent framework | Develop → Deploy → Observe | K8s-native | Dynamic DI | Auto-failover | Multi-LLM | Python + Java + TypeScript | MCP + A2A + REST

AI-powered chatbot designed specifically for legal professionals. It aims to streamline client interactions, provide preliminary legal guidance, and enhance law firm efficiency. The chatbot offers features such as legal document analysis, client intake automation, legal research assistance, appointment scheduling, multi-language support,.

Real-time Polymarket tracker with news aggregation, large activity monitoring, price movement signals, top holder analysis, and AI Agents debate floor.

AI-powered fashion recommendation system leveraging LLMs, embeddings, and retrieval techniques to deliver personalized shopping experiences.

Fake API Server for AI-Bypass

A hands-on lab to get started with AI Native Development with GitHub Copilot

CORE is a governance runtime for autonomous AI systems. It enforces constitutional rules during execution, prevents governance bypass, and creates auditable authority chains for agent actions across operational domains.

🌼 AI stack centered on an agent hypervisor. Automates tasks, graph-powered repo wiki, and Q&A, and searches across all your connected tools. Access it from browser, terminal, or API.

SPY put-credit validation and real-money control plane with broker-backed ledgers, deterministic risk gates, hybrid RAG, reconciliation, and $1k/mo after-tax evidence tracking.

Strategy-first landing page generation kit for Claude Cowork & OpenClaw. Extract, route, write, build, and QA pages without inventing proof.

Deterministic governance for AI coding agents. Cedar-based policy engine that intercepts every agent action and evaluates it against deterministic rules before execution.

[AAAI 2026] The offical implementation of paper "FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation"

A Model Context Protocol (MCP) server for Elsevier Scopus. Allows AI assistants like Claude to search academic papers, retrieve abstracts, and analyze author profiles directly.

Your personal multi-asset quant research team, powered by LLMs. Crypto + A-share + HK + US, with backtest engine, factor lab and event-driven news intake.

💹 StockSim: Multi-Agent LLM Financial Market Simulator — A realistic trading simulation platform for evaluating large language models in dynamic financial environments.

Benchmark and execution environment for evaluating LLM agents on end-to-end AI Research. [ICLR 2026]

[AAAI 2026] LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

FAT Agent (Fix, Audit, Test) — a Claude Skill that automates post-launch website QA. Audits SEO, security, accessibility, performance, and more.

Full Apple Music integration for Claude via MCP — search catalog, manage library & playlists

Code for Paper: Benchmarking Multi-step Scientific Tool-use in LLM Agents

A Claude Code skill that builds a persistent context system (atlas) for any git repository — directory trees, entrypoints, architecture docs, and agent on-ramp for fast LLM onboarding.

An end-to-end demo of an autonomous agentic mobile manipulator for warehouse robotics, showcasing fully on-device perception, reasoning, and natural language control in a ROS 2 simulation using AMD Ryzen™ AI hardware.

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

Claude agent skill: Reverse-engineer any competitor video ad into a reusable template. 12 format catalog + 7-step analysis.

Turn any website into clean, LLM-ready data. Open-source web crawler with stealth mode, distributed crawling, real-time WebSocket progress & Markdown output. Power your AI apps with GcrawlAI.

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemini and Windsurf.

One command installs 670+ security tools on Linux & Termux. Its authorization-gated MCP server works with Claude Code, OpenCode, Codex, Gemini CLI, Ollama-backed agents and other MCP clients. Includes 870+ agent skills for CTF, pentesting, bug bounty, DFIR and red/blue teams—companion by default, autonomous when asked.

An AI legal workflow running on Claude Code. Four legal agents — each with their own jurisdiction, knowledge base, and MCP tools — collaborate to produce legal opinions with full audit trails.

A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert rules, workflows, and custom personas in Cursor, Claude Code, and Windsurf with one CLI command.

Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Code for paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents

Deterministic agentic-style multi-hop RAG at research-SOTA parity on commodity LLM APIs — no GPU, proof tree per answer.

Run MoE LLMs on Apple Silicone via MLX that your Mac should not normally be able to run

Turn failed Python tests and CI runs into replayable debug sessions.

AI-driven toolkit that automates evaluation processes for AI agents

Agent skills for GitHub Copilot CLI

Task-plan driven SEO and LLM-friendly website skill cluster

An autonomous, self-healing Pinterest Growth Agent that automatically researches SEO trends, generates images, and publishes pins daily to organically grow traffic.

五运六气 AI Agent 技能包 — 中医运气学说推算引擎。干支推算 + 六气步移 + RAG五层知识库(104键) + ReAct推理工作流 + 自进化引擎。支持 Claude Code/Codex CLI/Cursor/Cline/OpenClaw 等 AI 客户端。

A unified OpenAI / Anthropic / Responses API gateway with built-in vision model injection — let any text-only model "see" images.

MoltTrend Claw is a privacy-first, autonomous AI agent that monitors cryptocurrency trends, analyzes market narratives, and generates actionable reports with long-term memory.

欢迎大家提issue。 AI Test Agent 是一个基于人工智能的自动化测试平台，利用大语言模型（LLM）和浏览器自动化技术，实现测试用例的智能生成、自动执行、Bug 分析和报告生成。 Enterprise_AI_QA_Agent 是一个面向企业级质量保障场景的 Agent 工作台项目，目标是参考 claude_code 的运行骨架

Calibre library automation via FastMCP — metadata, shelves, RAG-friendly export. Companion to Calibre, not a replacement. For Cursor / Claude Desktop.

CubePi — An async-first Python agent kernel inspired by Pi, built for coding agents, tools, and continuous sessions.

Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one token-economy result schema, with StatsPAI cross-validation. | 面向实证研究的智能体 Stata 桥接器——在 Claude Code、Jupyter、VS Code 中用一套省 token 的结果格式跑 DiD/IV/RDD 与出版级表格，并支持 StatsPAI 跨栈交叉验证。

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

gradio leaderboard region:us

transformers safetensors llama text-generation code granite

transformers safetensors qwen2 text-generation code codeqwen

Turn domain experts into production AI agents.

一个极简、可读、可 fork 的终端 AI coding agent —— 把 Claude Code的核心思想用 ~1300 行纯 Python 写出来

GEZHI (格致): a scholar-centered agent architecture for traceable, reviewable, and verifiable empirical social-science research.

An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.

205 production GTM agent skills for Claude Code — sales, outbound, prospecting, RevOps, ABM, PLG, CS, automation. Framework-cited playbooks with artifacts + QA scripts.

Liki — Professional Skill for Chinese Metaphysics. BaZi, ZiWei, QiMen, LiuYao, XuanKong, BaZai. Liki 灵机 — 命理师的Skill。命理，起名，问卦，风水。八字、紫微、奇门、六爻、玄空、八宅。

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.

transformers gguf llama llama-2 text-generation code

An MCP Server to utilize Lineai's rich software dependency data in your AI programming assistant.

Delta-MFP: counterfactual-replay failure diagnosis for local tool-use agents (FAGEN @ ICML 2026)

Get your repo ready for AI.

通用视觉识别 Skill 模板：为无多模态能力的 AI agent（如 DeepSeek）补上图片识别能力，支持本地图片与 URL。纯净模板 + scripts/setup.py 一键配置 Key/端点/模型，遵循开放 Agent Skills 标准，兼容 Claude Code / Codex / OpenClaw / Reasonix。

An autonomous Kubernetes SRE agent. It monitors cluster health, diagnoses issues, and applies fixes — with human approval required before any write operation.

Git-based test distillation for Codex agents: catch aggressively, commit reluctantly

A local-first hardware control surface for Codex — live task status, quota, pets, and safe actions on MiraBox N4 Pro.

Local-first skill routing for agent builders — index SKILL.md bundles, get ranked skill plans with confidence and evidence, and serve them to any agent over MCP.

Google Search Console MCP Server for Claude, Cursor, Windsurf and other MCP Clients

Marketing operations toolkit for Claude Code — 12 skills, 5 specialist subagents, and Python scripts for audits, CRO, SEO, copy, emails, ads, and client reports.

AI orchestrator that runs until done. Define what "done" means, go to sleep, wake up to verified results. Supports OpenCode, Codex, Claude Code,

QChunker: Learning Question-Aware Text Chunking for Domain RAG via Multi-Agent Debate

tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.

Chat with your PDFs, built using Streamlit and Langchain. Allows the user to ask questions to a LLM, which will answer based on the content of the provided PDFs.

🧱 CrewNews is an AI news generator that delivers an unbiased version of the news for a given topic, using Streamlit for the GUI, Llama 3.1 as the LLM (inferenced via the AIML API), CrewAI for building AI agents, AgentOps for testing AI agents, and Exa & Firecrawl as tools

Chat bot based on Bing web ai bot.

A minimal speech-to-structured output app built with Azure OpenAI Realtime API.

Multi-agent AI system for automated code review using Google's ADK - Kaggle Agents Intensive Capstone Project 2025