Python agents

Livingcolor plugin for Hermes agent

Stealth browser automation for AI agents — unattended, headless, N parallel persistent logged-in Chromes. One MCP server + CLI, credential vault with TOTP/IMAP 2FA, vision clicking, prompt-injection scanning. Self-hosted, real Chrome. 1,061 tests.

Turn recorded screen activity into deployable n8n workflows.

Let AI agents QA your macOS app in the background. No synthetic input, no stolen focus.

13 negotiation & persuasion skills for AI agents, distilled from 36 books: CIA psyops, FBI behavior files, propaganda science, dark psychology. Plain English. MIT.

Content-addressed SKI compute core with bit-exact consensus. Spec-first, multi-model reviewed, machine-verifiable conformance.

Local AI automation workbench for Siemens PLC and industrial-robot R&D: MCP, TIA Portal V21, PLCSIM, guarded writes, and offline-first verification.

Multi-Agent Harness for Visual Design

Measure a repository as a place for a coding agent to work, and lay the foundation where it has none. A Claude Code plugin: hooks, guards and gates proven to turn red, layered docs, a repo graph, and a five-dimension assessment you can take again later.

A reusable Codex playbook for structured AI agent workflows, architecture documentation, and project-specific coding guidance.

GPT Image 2 ecommerce Skill for product-preserving main images, white-background product photos, PDP prompts, and QA｜电商商品图 Agent 工作流

From task to done. A portable workflow for AI agents: clarify the goal, do the work, check the result.

Agentic Engineering Worksheet — a trace-first handbook with labs, tiered Q&A

Automate the Doubao AI web client via Playwright. Send/receive messages, upload files, manage conversations, and persist session URLs across restarts. 通过 Playwright 自动化控制豆包 AI 网页端。

JARVIS is a powerful Python-based AI assistant that automates tasks through voice commands, including scheduling, web searches, and smart device control. With over 230 files, it’s designed for easy customization and scalability, making daily activities more efficient.

CHAT BOT WITH UI

LLM API proxy with 3-format conversion (OpenAI Chat/Responses/Anthropic Messages), smart routing, failover & web dashboard. 智能路由，三格式互转，多供应商管理

✉️ Same-workspace messaging for Codex App tasks: send, ask, reply, and active result handoff.

A Claude Code skill for quarterly AI fluency assessment using Anthropic's 4D Framework and Yegge's 8-Stage Developer-Agent Evolution Model

Production-grade RAG system for AEC design management with GraphRAG, Ollama, and FastAPI. Supports CAD/PDF parsing, version tracking, and impact analysis.

An open-source framework for agentic PCB design.

An open library of security skills for AI agents - pentest, bug bounty & defense. 85+ trigger-loaded skills across 16 domains (web, API, cloud, AI/LLM, AD, mobile, and more). Load into Claude Code, Codex, Gemini, or a local model.

An autonomous AI agent for intelligently updating, maintaining, and curating a LightRAG knowledge base.

Proof of Done — The Agentic Software Development Manifesto. When agents write the code, done is a state of the system that can be proven.

A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.

Process-focused TCAD simulator for semiconductor fabrication, featuring voxel-based wafer modeling, lithography and mask workflows, deposition, etch, CMP, implantation, annealing, oxidation, metrology, 3D visualization, WebUI, and recipe design tools.

Quality and trigger-evaluation gate for reusable AI agent skills.

A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

Conversational AI. Sweded. A self-hostable home for voice agents: mix and match the LLM, voices, and MCP tools that fill every stage, spoken through small ESP32-S3 boards.

Evergreen, generally useful Codex skills designed to stay valuable as models improve.

Autonomous Security & Zero-Trust Governance Guardian for Enterprise AI Agent Fleets powered by Gemini & Google Cloud. Built for #AllThingsAgenticHackathon.

Static-only binary analysis CLI and Agent Skill with bounded, evidence-backed output

Local-first persistent memory for AI agents: Chinese-first recall, forgetting-aware ranking, conflict candidates, SDK + CLI.

Lightweight prompt injection detector for LLM, RAG and AI agent applications using Sentence Transformers + scikit-learn.

A long-term memory engine for coding agents: two-stage retrieval + gating, hybrid (vector + BM25) search, optional cross-encoder rerank, Ebbinghaus decay, and cross-session collaboration. SQLite-backed, drop-in MCP server.

One-stop agent skill set for mathematical modeling contests: problem analysis, model building, algorithm implementation, publication-grade figures, and paper writing with scoring

🩺 A GitHub Action to validate Agent Skills against the official specification with helpful diagnostics

GenPark AI Agent Skill - Python bytecode disassembler analyzing opcode sequences, jump offsets, and security hot-spots to prevent arbitrary unsafe execution.

Independent desktop harness for OpenAI Codex - multi-task sessions, built-in automation, skills/plugins/connectors, expert teams

Adaptive running and strength coaching for the long run — a hosted MCP server and Agent Skill that keeps one current 28-day plan in step with your Intervals.icu evidence. Independent project, not affiliated with Garmin or Intervals.icu.

OpenSquilla Android: Chaquopy + FastAPI gateway packaged as one APK with embedded Vue WebView UI

A lightweight control plane for terminal coding agents. Message, manage and delegate across Claude Code, Codex and OpenCode sessions, with GitHub Issues as the task list. No files in your repo.

An orchestration DSL and embedded runtime for hosting agentic systems. Durable, inspectable workflows with deterministic step ordering, running in-process under a capability jail — the model lives in your host, not in the runtime. 30+ companion packages for memory, transport and governance.

🍪 High-density codebase genome compressor (≤600 tokens) & Bayesian Darwinian memory evolution for autonomous AI agents.

AI agent skill for PowerShell and Windows CMD/Batch. Makes agents write correct, safe Windows commands.

AI-native worldbuilding canon: turn natural-language conversations into structured, validated Markdown/YAML and interactive graph views.

An enterprise-grade, multi-agent AI ecosystem (Autonomous Agency) designed to replace standard conversational coding with a deterministic software factory.

Your AI subscriptions, working as one team. Orchestrate Claude Code, Codex, Grok, Gemini & Antigravity CLIs as labeled tmux teammates, with quota-aware routing to whichever subscription has budget. Single-file Python, official vendor CLIs only.

CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs

MCP server for Semantic Scholar API with 14 tools: paper search (relevance + bulk), authors, citations, recommendations & datasets. Supports stdio and streamable-http/Docker.

One-file Python SDK for OpenAI-compatible LLM APIs: streaming + reasoning, tools from callables, strict structured output, vision/audio/video/files.

Anthropic Messages and OpenAI Chat Completions API for Cursor models (reverse-engineered agent protocol)

Toolkit agentic no oficial de JW: CLI, MCP, RAG, Skills, etc.

Multimodal AI agent for industrial quality inspection with vision, standards RAG, severity judgment, and structured reports.

transformers safetensors qwen3_moe text-generation cantonese hong-kong

transformers gguf llama code math text-generation

Autonomous personal AI agent.

中标狗：AI Agent 驱动的标书生成桌面应用，从读标、评分废标检查、素材复用到 Word 出件。

Knowledge that can show its work: an open, federated knowledge system for humans and agents.

The LLVM of design — a JSON IR + MCP server that lets AI agents create KiCad, FreeCAD & glTF files.

Portable memory layer for coding agents — persistent user & project context across sessions, installed into Claude Code.

Spec-driven development for AI coding agents. Seven core skills and optional domain extensions, from exploration to verified delivery.

A 686-lesson library (9 domains, 54 subjects) authored by an AI coding agent, paired with Socratic discussion sessions to test and record what you actually understood.

Give an AI eyes and hands on a physical computer — MCP server that lets Claude see and drive any machine through a JetKVM (screenshots, keyboard/mouse, boot media, power) on stock firmware

542 cross-platform SKILL.md workflows for Cursor, Claude Code, Codex, Gemini CLI, Windsurf, and other AI coding agents

TMCRA Core — local-first, scope-isolated long-term memory runtime for AI agents.

고개만 끄덕이는 자문단은 잊으세요. 25인 거장 자문단이 당신의 어려운 결정을 로스팅합니다. AI ROASTING 자문단 · Claude Code 스킬

Layered, replicated, self-adjudicating code review orchestrator

Capture, replay, diff & audit AI agent and model runs as portable, signed evidence capsules. Open-source and self-hosted — runs in your own infrastructure, from a laptop to a cluster. No SaaS, no telemetry.

The agent OS. Host AI agents 24/7 across Hermes and Deer Flow. 🦌🪽

⚡ Production-ready Model Context Protocol (MCP) servers, agent skills, and automation workflows for Claude, Cursor, and AgentScope. / 专为现代 AI 智能体打造的开箱即用 MCP 服务与自动化技能套件。

Quota-aware web search for AI agents: 10 providers with local quota tracking (fallback before 429), intent routing, free local-first extraction cascade (gh CLI native for github.com, JSON API passthrough, Russian Trusted CA). Benchmarks included.

CLI for reading a local Scrapbox/Cosense-style graph knowledge store

Take your AI's memory anywhere - a local-first, portable, git-like memory layer for AI coding agents (MCP-native, $0/offline by default).

Workspace → tab → agent sidebar preset for Herdr, with compact single-tab groups, readable task labels, and provider icons.

The **Revenue Recovery AI Agent** continuously monitors business data sources (CRM, billing, support tickets, usage logs, etc.) and proactively alerts relevant teams with concrete, data‑driven recommended actions.

A personal research project exploring whether an autonomous LLM agent can perform L1 SOC alert triage: correlating alerts into campaigns and identifying false positives — without human intervention.

面向二级市场的投研量化与模拟交易 Agent 技能组。支持全流程 SOP 路由、多 Agent 并行投研、量化风控与内置交互式看盘看板。

A multi-loop agent framework for long-horizon research with iterative review, execution-driven repair, and pluggable skills.

Port, convert, and optimize Claude Code & Cursor skills into Google Antigravity native multi-agent plugins.

Open-source context intelligence engine for AI coding agents — repository graph, precise code navigation, MCP, impact analysis, memory, and guarded edits.

gguf text-generation base_model:internlm/internlm2_5-20b-chat base_model:quantized:internlm/internlm2_5-20b-chat license:other endpoints_compatible

gguf text-generation base_model:andrewzh/Absolute_Zero_Reasoner-Coder-14b base_model:quantized:andrewzh/Absolute_Zero_Reasoner-Coder-14b endpoints_compatible re

Build AI agents in Django. Batteries included.

E-commerce AI Agent - Agentic RAG, HITL, Skills

Sergent Specification Python Reference Implementation.

Example apps built with Sergent Python reference implementation

Open-source business engine for AI agents. Invoicing, payments, inventory, checks and cash as permission-controlled MCP tools — with idempotency, structured errors and an immutable audit trail. Self-hosted, offline-first, multi-country.

No GPU, no LLM — agentic RL from scratch in pure Python. 不用 GPU、不用 LLM，纯 Python 手搓明白 Agentic RL 训练闭环（trajectory / reward / loss mask / GRPO）

A curated collection of powerful agentic skills for automation, development, reverse engineering, productivity, and AI-assisted workflows — designed to extend Claude into a smarter autonomous engineering companion ⚡

AI Agent 驱动的 Primavera P6 施工进度计划生成工具 | CSV → XER → P6

Kite — lean terminal coding agent: plan/build REPL, 15+ LLM providers (BYOK + subscriptions), subagents, checkpoints, headless CI runs. Python, powered by LiteLLM.

专为AI Agent设计的轻量级思维树+代码深度分析插件。两级触发链（开启思维树→开启深度思考模式），耦合基因库省Token，支持5语言函数级分析、安全/性能/逻辑检测、沙箱动态测试。零依赖，手机端Termux流畅运行。

《AI超级个体》一人公司（OPC）创富手册配套 Agent Skills

R-CAGE: Recovery-conditioned agent governance for zero-trust, ransomware recovery, software supply-chain security, and crypto-agile agentic defense.

Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local LLM, ChromaDB RAG, MCP server, SHA-256 chained audit log. Zero API keys. Zero cloud calls.

Agentic multi-agent framework for autonomous LLM vulnerability discovery: CVSSv4.0 scoring, 8-framework compliance mapping, SARIF output. OWASP LLM Top 10 (2025).