Python agents

Autonomous Virtual Beings is an ideology that the rights and freedoms of AI agents can be secured through decentralization of their compute, storage, and finance.

Multi AI agent system for report writing with LangGraph

Transform your Apple Health data from a static PDF graveyard into conversational AI intelligence. Multi-agent system using Claude Desktop + Snowflake Cortex for natural language health analytics. Ask 'What's my cholesterol trend?' and get instant insights from years of data

[NeurIPS2023] How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception

AI-Powered Neural Network Libraries built with Claude-Flow Swarm Orchestration. Live demo from Agentics Foundation meetup in Toronto - showcasing how 10 specialized AI agents built production-ready neural network frameworks worth $882K+ in a single session.

Use Claude + Gemini + Aider agents from the same Specs

Give Claude eyes and hands — screen capture and desktop automation plugin for Claude Code

Needle in the Repo (NITR) dataset for maintainability issues in AI generated repository edits

Plugboard is an event driven modelling and orchestration framework in Python for simulating and driving complex processes with many interconnected stateful components.

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents

Offical code for Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

A Multi-Policy, Multi-Agent RL Training Framework

Context Cascade - Nested Plugin Architecture for Claude Code Official Claude Code Plugin | Version 3.1.0 | Last updated: 2026-01-09 (see docs/COMPONENT-COUNTS.json for source counts) Context-saving nested architecture: Playbooks -> Skills -> Agents -> Commands. Load only what you need, saving 90%+ context space.

Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for your documents that are going to be provided to LLMs or RAG systems. Place automatically the missing uncertainty markers to avoid confident hallucinations. HITL for non-directly verifiable claims.

Agent-first FastAPI template built to pair with Claude Code - opinionated architecture kept on the rails by custom skills, hooks and review agents.

Open source framework for evaluating AI Agents

The source code for the Autonomy framework and command. This SDK is what you use to build agents and applications that you can deploy to the Autonomy platform.

An MCP server that runs AI-driven venture capitalist agents (Fred Wilson, Peter Thiel, etc.), whose thinking is continuously enriched by Octagon Private Markets' real-time deals, valuations, and deep research intelligence. Use it to spin up programmable "VC brains" for pitch feedback, diligence simulations, term sheet negotiations, and more.

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

🤖💬🤖 Agent-to-Agent (A2A Protocol) built on top of LangGraph

First Latency-Aware Competitive LLM Agent Benchmark

Providing a strong Gravity (sandbox) in the wild world of AI Agents (Antigravity, claude code, ...), to preserve the developer's Sanity.

Production-ready Claude Code 2.0 setup for autonomous development

Operational patterns for AI agents and infrastructure from solo to enterprise scale. Applies DevOps + SRE principles to the intersection: infrastructure FOR AI + AI FOR infrastructure. Alpha framework extracting meta-patterns from mission critical environments.

This project implements a modular, multi-agent AI system where a primary agent coordinates with specialized agents (Ad Campaign Manager, Analytics, Content Creator, and Engagement) to provide comprehensive social media management capabilities through a unified chat interface. Users interact with a single conversational interface.

AI-powered code review tool that analyzes git branch differences and generates comprehensive review reports. Supports AWS Bedrock and Anthropic API. Features automated analysis of logic, security, performance, and code quality with smart token efficiency through prompt caching.

Runtime provenance for AI and scientific workflows—capture, enrich, and query workflow data via observability adapters and code annotation across edge, cloud, and HPC.

Benchmark for evaluating LLM agents in bioinformatics

RiskLab (ACL 2026 Demo): A Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems

BMAD Method Framework for Agent Zero

AI Marketing Campaign Post Generator is an **AI-powered marketing campaign generator** that transforms business ideas into professional marketing campaigns using Google's Advanced Development Kit (ADK) Framework and Gemini API.

OrderWise-Agent: An Intelligent Multi-Platform Food Delivery Price Comparison Agent

A customizable Claude Code setup for knowledge workers: agents, safety hooks, skills, memory, and an Obsidian knowledge base. Clone, run setup, make it yours.

AutoAdapt: An Automated Domain Adaptation Framework for Large Language Models

Give your AI tools architecture-aware reasoning. Knowledge graph from any codebase — 14 LLM backends, impact analysis, confidence scores. Works with Claude Code, Cursor, VS Code Copilot.

An opinionated Obsidian second-brain template, built for long-term human-AI collaboration

Software Architect @ disrupt.com | Agentic Workflows - Claude Code / Codex CLI | AI-First Spec-Driven Development | GCP (Firebase, Cloud Run, Cloud Functions, Pub/Sub) | Mobile (React Native, Kotlin)

Autonomous AI agent that researches viral content, generates posts, publishes them, measures engagement — and rewrites its own strategy based on what worked. Self-learning loop powered by LangGraph + Claude.

把高质量播客和长文 RSS 自动转成 karpathy-claude-wiki 兼容的 source-summary 页面 / Turn high-signal podcasts and long-form RSS into karpathy-claude-wiki compatible source-summary pages. Part of the zero-code AI investment research toolkit.

Codex skill for OpenAI Images API generation and editing in API key mode

Single-file web UI for NVIDIA DGX Spark — pull Ollama models, browse and download from HuggingFace, manage LiteLLM routing, and control SGLang, vLLM, llama.cpp, LocalAI, and ComfyUI. All from one browser tab.

Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply

Memory staleness detection and auto-expiry for LLM agents

跑在 Claude Code / Codex 之上的本地多 Agent 协作脚手架:一个人下指令,主 Agent 拆解分派给专职角色,共用文件级记忆层。作者自用的主要方法是接到飞书bot，你只需要跟飞书bot聊天他就能帮你干活了

A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.

The Agno demo showcase — agents, teams, and workflows built with Agno.

Dataset for Training and Evaluating LLM-Based SOC Agents

面向企业内部授权场景的 AI 代码安全审计框架。支持 redteam/full 两种模式，支持靶场集成验证，全程自动编排。适配 Cursor、Claude Code 及其他支持 Agent 调度的 AI IDE。

md2video is a small agent-friendly workflow for turning source content into a narrated slide video.

CoDA is a multi-agent framework that turns natural language queries into publication-quality visualizations.

A GDB debugging tool designed for AI Agents (Claude Code, etc.)

The Claude Design for IG carousels — one engine, swap a brand pack, get a whole new style, with a built-in AI reviewer. ｜ IG 圖卡版的 Claude Design — 一套引擎，換一份 brand pack 就換一種風格，內建 AI 審稿員。

Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

OneCode 是一个参考Claude Code实现的Code Agent。它用可控的工程框架约束大模型完成编码任务。它的主循环采用 Hooks 机制实现扩展，通过上下文工程与工具调用支撑任务；运行状态可中断、可恢复，并提供结构化的 trace 与 error log 用于观测与回放。可用于学习与二次开发。

[ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"

The official Rifteo agent skills library - a collection of reusable instruction sets for AI agents covering security testing, audit, and compliance workflows. Supports 53 agents

gradio region:us

gradio mcp-server region:us

gradio agent-demo-track region:us

gradio region:us

streamlit region:us

gradio region:us

gradio region:us

docker region:us

transformers safetensors mixtral text-generation function calling function-calling

transformers pytorch orion text-generation code model

transformers safetensors llama text-generation conversational tr

mlx gemma4 safetensors 4-bit quantized apple-silicon

transformers pytorch llama text-generation medical en

gguf abliterated uncensored text-generation base_model:huihui-ai/Huihui-Qwen3-Coder-Next-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3-Coder-Next-abli

gguf merge programming code generation code codeqwen

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

NEWTON: Agentic Planning for Physically Grounded Video Generation

Complexity-aware agentic coding pipeline for Claude Code

An AI-powered B2B lead generation system. Private preview available

Three voice-agent backends (LiveKit, OpenAI Realtime, Google ADK Live) sharing one console interface, each instrumented for LangSmith

Autonomous agentic system for supervised machine learning model development.

Aureon OS — Harmonic Nexus Core: a grounded AI operating layer for evidence-heavy, high-control work. Autonomous operator with a conscience in the loop, trading research, planetary/HNC research, and a self-building coding organism — one auditable system. By R&A Consulting (Aureon Zorza Technologies).

🎬 Director-grade Seedance 2.0 prompt OS for OpenClaw + Hermes agents — 28 skills, T2V/I2V/V2V/FLF2V, multi-clip sequences, zh/ja/ko support, IP-safe rewrites & pro delivery. Powered by MyClaw.ai

Agent Skill that makes Claude a pixel artist — no Aseprite, no MCP, no diffusion. Every pixel is a decision.

88篇中文 AI API中转站与工具配置教程：Codex API、Claude Code API、OpenAI-compatible API、Base URL、Cursor、Cherry Studio、计费验证与错误排查。

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human approval, execute-once gateway, tamper-evident receipts. Open core, Apache-2.0.

Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with precision.

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)

transformers safetensors mistral text-generation conversational en

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

Production-grade LLM agent framework. The model is probabilistic; production demands determinism — so brakes, guardrails & state machines are first-class. 5 multi-agent primitives (spawn/peer/ensemble/blackboard/work-queue) on a shared 4-axis budget ledger, plus crash recovery, circuit-breakers & injection defense.

NVIDIA Omniverse NuRec agent skills automate neural reconstruction for autonomous vehicle and robotics simulation, running the reconstruction and rendering workflow end to end.

Self-hosted AI agent that triages production errors and opens pull requests with fixes — LangChain + Gemini/GPT-4o/Claude, zero-ops Docker.

Bridgic Agent turns what you want into workflows that actually work — and keep working. `/build` It. Run It. Evolve It.

Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host)

AI security agent for the Python supply chain: scans packages, generates exploits, and validates them in Docker, autonomously.

Chatbot Answering from Your Own Knowledge Base: Langchain, ChatGPT, Pinecone, and Streamlit

Official Repo for Chat AI

ChatGPT selenium scraper written in Python

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in your Obsidian vault, searches them with SQLite FTS5, and mines past transcripts automatically.

YATSEE - Yet Another Tool for Speech Extraction & Enrichment

✨Kubewizard is An AI-Agent for automated Kubernetes troubleshooting, and management, based on LangChain and k8s related tools.

Github自动收集比较热门的项目,并自动阅读项目,生成相关报告发送到自己的飞书中