Python agents

Human-vetted, community-curated skills for AI coding & agent tools.

SFLO — Simon Factory Lights Out: a gated pipeline protocol for building software with AI agents

🐦 AI agent that assembles production-ready OpenUSD scenes from natural language, so you focus on creative decisions, not pipeline work

Hệ thống phân tích chứng khoán Việt Nam chuyên sâu sử dụng kiến trúc Multi-Agent RAG với CrewAI và Google Gemini.

Official code for the paper: "Multi-User Large Language Model Agents"

Local-first Python CLI and MCP server for versioned, cited context from web and document sources.

This is a fully autonomous, self-operating computer automation system designed to automate tasks on Windows without any user interaction. It runs scheduled or trigger-based workflows using Python, system tools, and smart agents — ideal for repetitive tasks, bots, or self-executing pipelines.

Text2Sim MCP Server is a conversational simulation engine that transforms natural language into working simulation models. Supporting Discrete-Event Simulation (DES) and System Dynamics (SD), it integrates with LLMs via the Model Context Protocol (MCP) to transform plain English descriptions into simulation models within environments like Claude.

Adaptive Hypernetworks for Multi-Agent RL. NeurIPS 2025.

멀티에이전트 Claude Code 하네스를 위한 토큰 비용 lint — 10 카테고리 × 31 sub-patterns 분류학 + 정적 감사 스크립트 + LLM 0회 결정 트리. Korean primary, English mirror.

A high-performance, memory-efficient inference server for diffusion models (image/video generation), compatible with the OpenAI client

OpenAI Router 轻量级、持久化、零配置的 OpenAI API 统一网关

A collection of AI solutions for oracle.ai

Autonomous multi-agent system for intelligent HDB resale search — combining geospatial analytics, MRT proximity, and XGBoost price valuation using DeepAgents, LangGraph, FastAPI, and Gradio UI. No database required; reads data directly with SQLite. Dockerized, with reproducible data-ingestion pipelines and support for local LLMs.

A Deception Security Layer for MCP Servers. It injects "ghost tools" (fake security-sensitive tools) that act as honeypots.

🌐 Automate Browser using AI with ease.

Persistent memory for AI agents. Extract once, recall forever.

A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

A lightweight, agent-style framework for fact-checking atomic claims using iterative retrieval and verification. Reduces LLM and search cost while maintaining strong factuality performance.

OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate results, and makes complex multi-step agents more modular, efficient, and extensible.

AWS payment demo of x402 using Bedrock AgentCore, Strands SDK, and CloudFront.

A collection of reusable AI agent prompts for development workflows.

🧳 A state-of-the-art multi-agent travel planning system powered by OpenAI Agents SDK and LangGraph orchestration. Leverages Stagehand/Playwright for browser automation, Supabase for data persistence, and Firecrawl/Tavily for intelligent research.

An imperative command-line-interface for AI workload orchestration — v6.2.16

Hermes Agent plugin for crypto: wallets, DEX trading, lending and staking, governance, on-chain automation.

Example AI agents using AgentMail — hiring screener, legal intake, receipt parser, contract redline, and more.

A Pexels MCP Server for Images and Videos searching

Claude Code plugin that turns a PCB idea into a wired .kicad_pcb ready for EasyEDA auto-routing and one-click JLCPCB ordering — LCSC part sourcing, EasyEDA pin-map auto-fetch, and session-persisted workflows.

🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.

The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 22 parsers (incl. EPUB, DOCX, ODT), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.

Latent Embedding Operating System

Local-first Memory Framework for AI Agents · 99.2% LongMemEval-S retrieval @ k=10 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable

Batched file operations for autonomous Claude Code runs. Collapses N reads/greps/globs into one Bash round-trip — fewer output tokens, less cache growth, less wall time.

Agentic AI plugin that transforms a dashboard request into a Tableau specification — with interactive HTML mock, implementation blueprint, and experimental .twbx generation. Works with Claude Code, Cursor, and other AI coding tools

Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, type-contract breaches & async hazards that linters miss. Six skills · Claude Code · Codex CLI · Gemini CLI.

Intent-bound action authorization for AI agents — deterministic, per-action approval a prompt injection can't re-point, with a signed, tamper-evident audit trail.

Turns vague requests into structured prompts, execution plans, and policy-aware workflows — with readiness verdicts, PR merge-safety checks, agent packs, and MCP tool exports. Offline-first, deterministic, provider-agnostic.

This multi-agent template is support Vietnam stock

Centralized LLM configuration and documentation management system. Tools for building skills, commands, agents, prompts, and managing MCP servers. Multi-LLM support (Claude Code, Codex, OpenCode).

The SQL-RL-GEN is an algorithm based on a Reinforcement Learning approach with a reward function generated by a LLM to guide the agent's training process in solving the specific text2SQL generation task.

Multi-agent crypto research bot — scout, verify onchain, score risk, synthesize a research brief via long-chain LLM reasoning. Built on the Xiaomi MiMo platform.

Multi-agent occlusion inference using observed driver behaviors. A driver sensor model is learned using a conditional variational autoencoder. Information from multiple drivers is fused into an ego vehicle's map using evidential theory.

VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments

ReAct agent with access to Python REPL to execute simple workflows. Uses OpenAI GPT-family as language model.

Curated rules, skills, and agents for Claude Code — clone into .claude/ and go

Create a domain specific (GRC) agent with the Claude Agent SDK

This is a base-react agent for AssetOpsBench

Kilo-Kit is a comprehensive, modular framework for building and managing AI agent systems at scale (kilo-code = thousands of lines, hundreds of files). It introduces a revolutionary Cognitive Flow Architecture (CFA) that treats AI interactions as continuous flows rather than discrete events.

Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.

Official codebase for the paper "WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction"

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

Публичный пакет инженерных skills для Codex

Bodhiorchard is the open-source, self-hosted alternative to Jira and Linear for AI-native software teams. Specialised agents draft every spec, forecast cycle times, and reason over your real repositories, commits, and pull requests — replacing story points, standups, and stale tickets so engineers can focus on building.

⚡ The ultimate collection of 136+ OpenCode Skills (Codex Subagents port) featuring auto-sync and 1-click deployment.

Let's Qitos! A torch-like agent-native framework for researchers.

Identity-first cognitive agent OS with memory, multi-channel ingress, Operating Room orchestration, and desktop surfaces.

The AI Operating System for Consumer Brands — Open Playbook

OpenMontage: 100% Free Local AI Video Production System using Ollama and FFmpeg

Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)

Governed AI workflow orchestration for complex software development, coordinating specialist skills, validation, security review, human gates, and execution continuity.

Catch silent failures in AI agents before your users do

Open-source desktop client for the xAI Grok API — chat, image & video generation, voice, and an agentic coding module with local file access. Bring your own key, no telemetry.

transformers safetensors glm text-generation chatglm conversational

transformers gguf llama legal text-generation en

transformers safetensors llama text-generation code granite

gradio region:us

transformers safetensors jais2 text-generation conversational ar

transformers safetensors gguf gemma3_text text-generation tool-calling

gguf atomic-chat gemma gemma4 google llama.cpp

transformers safetensors qwen2 text-generation code codeqwen

Archived first-generation Claude Code framework with agents, commands, rules, templates, and MCP integrations.

175+ pip-installable tool integrations for the ModuleX runtime — one pydantic manifest contract, entry-point discovery, async httpx tools

AI-Powered Multi-Agent Crypto Investment Analysis Platform

This project leverages Large Language Models (LLMs) and a multi-agent framework to analyze stock prices, gather relevant news, and generate comprehensive financial investment reports for companies.

Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".

[EMNLP 2024] FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents

🍞 记得住、学得会、能进化的个人 AI 助手。持久分类记忆 · 闭环经验引擎 · 子代理并行 · 长任务不漂移 · 9 大平台 · 4 类 LLM · MCP 生态 · 桌面自动化，只有你需要的轻量。｜ The AI assistant that remembers, learns, and evolves. Persistent memory · Experience engine · Sub-agents · 9 platforms · 4 LLM providers · MCP tools.

[2026 IEEE RA-L] Multi-Agent Workflow with Chain of Thought Reasoning for Surgical Intelligence

Simple code sandbox supporting jupyter notebook style code execution. Used for agent training

Code for ICML25 paper "HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning"

Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control

Rapidly build a multi-Agent management dashboard based on Claude Code, integrating daily work and remote IM collaboration. It includes Claude Code monitoring, channel configuration and message notifications, with a Codex GUI optimized for non-technical users.

🔧 LRA - AI Agent长任务超稳定执行框架 ⚡ 轻量 | pip一键安装｜突破上下文限制 📌 7种状态管理 | Long-Running AI Agent Framework • One-click pip install｜Break context barriers • 7-status management. 5.0全面支持CLAUDE/OPEN CLAW/OPEN CODE/CUSOR/TREA 等全部Agent编程工具，仅需运行 lra init命令，就会生成Agent.md/CLAUDE.md/lra.md. 你的agent会自动学会如何使用

Research Harness for Claude Code. Keep your agent grounded in context, not lost in vibe coding.

An autonomous, 100% local Agentic GraphRAG system for codebase intelligence. Paste any GitHub URL or local directory to chat with your code. Powered by LangGraph, NetworkX, and Ollama (qwen2.5-coder).

A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.

Clint is the AI Era Outreach System. It is a Python library and CLI (Command Line Interface) designed for production-grade lead discovery, evidence-based personalization, and safe outreach automation. It bridges the gap between raw data scraping and personalized human-like communication.

AI brain for your Paperless-ngx archive — chat with your documents via local (Ollama) or cloud LLMs, with agentic tool use, semantic search, and long-term memory.

Turn reference images into Minecraft-native Blockbench models using agent reasoning and deterministic compilation.

The framework that powers your Agentic Company

Governance-grade, OKF-compatible knowledge-base format with a single-writer MCP server and CLI. Pre-release.

The first Algorithmic Trading DePIN. Get paid to trade via Proof-of-Trade mining & Swarm AI. A self-hosted visual crypto bot with a No-Code builder.

Give Claude Code an intern: drive Antigravity (Gemini), Codex, Copilot, Cursor and opencode — plus experimental Grok & Kimi — as sub-agents. Text answers, image generation, real repo work and parallel swarms, on quota you already pay for.

Cross-platform desktop dashboard for Claude Code usage — Windows, macOS & Linux. Live session & weekly limits with reset countdowns, token counts, and one reactive Clawd mascot per active session. Plus a Stats page valuing your local transcripts against API rates, 16 themes and a custom theme editor. Lives in your tray.

Open-source, self-hosted runtime and SDK for AI applications. One tenant/project deployment serves many users and apps with governed tools, scoped credentials, isolated generated code, and cost controls.

Security-posture-first list of sandboxes for running AI coding agents' code, ranked by isolation, egress control and secrets handling

채용공고(JD)를 지원·면접·설명 가능한 IT 인턴 프로젝트로 바꾸는 한국형 AI 스킬 · JD → 오픈소스 선정 → 코드 분석 → 이력서·면접팩

LongCat-Flash-Chat safetensors text-generation transformers conversational custom_code

Agentic Theorem Prover for Rocq for Program Verification