Python agents

Official Repo: AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

A demo project that deploys Agent Framework agent to Foundry Hosted Agents

Simple framework for training and evaluating math reasoning agents using local models, GRPO and vLLM.

Blackhat 2025 presentation and codebase: AI SOC agent & MCP server for automated security investigation, alert triage, and incident response. Integrates with ELK, IRIS, and other platforms.

Agent skills for Arize — datasets, experiments, and traces via the ax CLI

Langchain FastAPI server

[ACL'26 Oral] AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression

Model Context Protocol (MCP) server that connects AI agents (Claude, Cursor, etc.) to Wolfram Mathematica for symbolic computation, visualization, and notebook manipulation.

《从0开始构建 AI 智能体》 一本带你亲手打造属于自己的AI Agent 的实战书

Claude Code skill for AI persona panels, virtual customer research, and concept testing.

根据 Crash/ANR/OOM 等日志构建证据链，实现自动修复代码的Agent框架，并支持衔接自动测试验证、Bug管理平台 Agent framework that builds evidence chains from Crash/ANR/OOM logs, auto-fixes code, and plugs into test verification & bug trackers.

One free AI endpoint, every free tier behind it. Local OpenAI-compatible gateway routing across OpenRouter, Groq, NVIDIA NIM, Cloudflare Workers AI, and HuggingFace with automatic failover.

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

Zero-dependency multi-agent workflow orchestration engine. YAML pipelines, shared event bus, auto-recovery, real-time dashboard.

Dynamic dual-granularity skill bank for agentic RL, jointly evolving policy and skills to improve long-horizon decision making in agentic tasks.

A self-hosted Claude agent that actually remembers — verbatim memory palace at zero retrieval cost, Discord + web UI, and 90%-cheaper repeat calls via prompt caching.

An open-source RAG platform to explore the unsealed Jeffrey Epstein court documents.

[ICLR 2026] AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents

觀瀾 · A-share research workstation with 24 AI sub-agents — one command, deep-dive report in ~10 min.

CompBioBench: A benchmark of 100 diverse, verifiable questions for agents for computational biology (scripts for running agents)

A place to store and share useful agent skills

Reimagining Agent-based Modeling with Large Language Model Agents via Shachi

[ICRA 2026] Official codebase for NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions

A collection of ATProtocol agent skills

JobSearch-Agent automates job searching by scraping listings, filtering based on user preferences, and managing applications. Easily customize search criteria, track progress, and streamline your job hunt with this efficient, Python-powered tool.

Multi Agent for Business Automation is a multi-agent orchestration platform for business automation and decision support. It coordinates specialized AI agents—each with distinct roles, personalities, and tools—through LangGraph workflows, shared memory, and human-in-the-loop (HITL) approval gates.

simple self-improvement agent

Frontend UI Studio built into the Hermes Agent Web Dashboard

Self-hosted DTLN noise suppression plugin for LiveKit Agents — no cloud API, no per-minute fees

[ACL 2026] Official respository for Interlat: Enabling Agents to Communicate Entirely in Latent Space

A collection of skills for AI coding agents working with Azure Cosmos DB. Skills are packaged instructions and scripts that extend agent capabilities.

Security skills for AI coding assistants and agentic systems

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

A Minimal Agent for Automated Theorem Proving

A platform for running AI agents on realtime sport data and make predictions about game outcomes.

你的专属 AI CRM 销售助理，可集成至 OpenClaw、WorkBuddy 等任何 Agent，覆盖 L2C 整个链路。

AI agent skills for stream processing and event streaming

Progent: Securing AI Agents with Privilege Control

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, organized into campaigns, waves, squads, and review gates.

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the messages format expected by Hugging Face Transformers.

Awesome list for medical imaging agents: radiology agents, pathology agents, segmentation agents, medical VLM agents, self-evolving agents, benchmarks, datasets, tools, and papers.

Open-source AI phone API for voice agents. Give Claude, Cursor, OpenClaw, or any LLM a real phone number — outbound/inbound calls, SMS, transcripts, MCP, DTMF/IVR. FastAPI + SignalWire + Deepgram. Self-hostable alternative to Twilio, Vapi, and Retell.

static region:us

transformers safetensors qwen2_moe text-generation chat conversational

gradio mcp multi-agent research code-generation ai-assistant python web-search

gradio mcp-server region:us

OTel Plugin for Hermes Agent

The official Kotlin benchmark by JetBrains

Official Implementation of VisualClaw: A Real-Time, Personalized Agent for the Physical World

Team of Codex agents that collaborate through a spec-driven development process. Full Stack Developer parent orchestrates dynamically sized pools of specialists: Coding, DevOps, Review, and Solutions Architect agents.

Human-gated, capability-slotted collaboration workflow (SOP) for coding agents — discovered rosters, condition-based roles, cross-vendor review, signoff gates

openclaw-data-china-stock 是为 OpenClaw 打造的中国市场数据底座：覆盖 A 股、ETF、指数、期权、资金流、技术指标与宏观分析；为 OpenClaw Agent 提供统一行情采集、58 指标计算，并以“工具+Skill”成对输出投研能力；解决了从行情、技术指标到宏观数据的采集、计算与智能分析全链路需求。内置多数据源自动降级（AkShare/新浪/东财/Tushare），确保你的策略与研究流程不因单点故障而中断。你可以把它当作给 OpenClaw 装上的一体化 A 股投研引擎。

Automate Blender 3D modeling with AI via MCP — 93 tools for modeling, sculpting, architecture/MEP, materials, and 3D-print prep. Includes Blender Studio: a visual record/replay session editor with a multi-provider AI assistant (Claude, Gemini, OpenRouter) — drive it from n8n, Claude Code, or standalone.

Change management, SkillOpt optimization, and evidence-gated evals for agent skills.

Read-only Dashboard and Desktop plugin for inspecting Hermes Agent memory.

Hindsight-lite: Agent Memory That Learns lightweight version. Get inspired by hindsight.vectorize.io

Red Hat Ecosystem Engineering - Agentic Collections

Agent Skills for ABAP Developers

[ICLR'26] MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning

一款开源的基金估值、智能理财Agent框架

[ICML 2026] Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

Keep your skills sharp. Intelligence for agent context.

A Network Arena for Benchmarking AI Agents on Network Troubleshooting

Personal agent assistant

An agentic harness for small language models.

Legal Quants agent skills — a curated collection of skills built by lawyer-builders across 17+ jurisdictions

The official Agent Skills for VictoriaMetrics products

The Research Playground for the RLMSs and Coding Agents

Maya-specific implementation of Model Context Protocol (MCP) for Autodesk Maya, enabling remote control and integration with MCP ecosystem.

The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strategic wisdom of master designers to generate high-intent UI/UX with zero "schtick."

AI-driven Dynamic Application Security Testing tool for security engineers. Combines an HTTPS MITM proxy with a multi-agent scanner and a real-time web dashboard. Route any browser or tool through the proxy — findings appear automatically.

A lightweight dashboard and reporting tool powered by OmniRoute - The Free AI Gateway

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages)

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects to 1000+ app tools and MCP servers.

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

EasyGEE agent plugin for Google Earth Engine, geemap, GeoMaster, and local map workflows

The Tenstorrent Studio (TT-Studio) is an easy to use web interface for running AI models on Tenstorrent hardware. It handles all the technical setup automatically and gives you a simple GUI to deploy models, chat with models, and more.

idac - IDA Pro command line tool for agents and humans

自己捣鼓的agent skill 和网上搜集的优秀的skill推荐合集，其中绘图 skill 重点推荐，是个人折腾的专业级别的绘图skill，效果不错。 包括 svg格式、drawio格式、xml格式，xml和drawio格式可以使用drawio直接编辑

Cloudflare Browser Rendering plugin for hermes-agent — crawl, scrape, extract content from web pages

A lightweight CLI coding agent focused on speed, determinism, and developer control

FTShare Agent Skills for financial data and investment research workflows｜金融数据 Skill 与投研业务 Skill 仓库。

用一份 Docker Compose，把 ChatGPT Web 能力封装成可由本地 Agent、IDE、SDK 与自动化工具调用的统一 API 入口。

MCP server that lets AI agents drive Inkscape — interactively alongside the GUI or headlessly from the CLI

SillyTavern 角色扮演引擎 v4.0 — 基于 Hermes Agent 的 AI 角色扮演完整框架，含破限层、身体一致性锁定、文学化描写规范、11个 World Book、存档系统、SM/调教处理流程

The complete AI video-editing skill: from raw footage and creative direction to one verified final film.

🔥 全网首款全离线无 API 短视频生产 Agent｜100% 本地运行，选题→脚本→剪辑→字幕→复盘一站式闭环，零付费零封号，自媒体批量出片神器

RTL agent team; Harness for Agentic hardware design and verificiation.

PhoneHarness runtime harness for mixed-action phone agents

Unofficial Grafana Agent Observability plugin for Hermes Agent

Out-of-the-box coding-agent runtime for terminal, IDE, server, and Telegram: built-in tools, subagents, skills, memory, MCP/ACP, hooks, and automation.

A collection of Agent Skills for building search applications and analyzing observability data with OpenSearch.

Open-source agent skills for debugging and optimizing Apache Spark workloads

一键导出Get笔记订阅的博主内容，并生成MD文档，并支持Agent skill