Python agents

Omni-Agent: The Autonomous Business Intelligence Hub. AI-powered automation, real-time analytics, and enterprise-grade security.

Capgate — runtime authority boundary for autonomous AI agents: the agent proposes, the harness authorizes, the executor acts. Deny-by-default policy, non-transitive delegation, tamper-evident audit, MCP gateway, containerised isolation.

A complete legal assisstant for Hermes Agent — 1,432 skills across five layers. Apache-2.0.

Open source agentic programming environment for building, running, and inspecting AI workflows.

MCP servers for AI agents — Google Maps lead gen, SERP scraper, LinkedIn scraper, CAPTCHA solver, UAE real estate. Free, open-source, no API keys needed.

Reproduce & measure degenerate tool-call loops in LLMs — replay a recorded conversation against any OpenAI-compatible model and see if it loops.

Performance engineering and observability for AI agents.

Local markdown memory & cross-agent context engine for coding agents (MCP).

An open-source harness engineering system for Codex that turns product discovery into evidence-gated software delivery: PRDs, Stories, approved designs, implementation, testing, review, and pull requests.

Build an LLM from scratch with transformers, attention, tokenization, dataset engineering, training, alignment, inference, multimodality, agents, and a runnable PyTorch mini language model.

SOC detection lab simulating AI-era threats, NHI abuse, prompt injection, and MCP attacks built with Splunk, Python, and MITRE ATT&CK mapping

Claude Code plugin: run several agents in parallel from one terminal — a dispatcher, a worktree per task, and docs as the single source of truth.

MiniMax H3 FP8 video generation service with web UI, API, ComfyUI workflows, Turbo LoRA, model manifest, and cloud GPU installer.

Unreal Engine plugin for the DCC Model Context Protocol (MCP) ecosystem

Self-hosted AI team workspace: named LLM Bots join chat channels, take jobs, run tools on your machine, hand off work, and leave an audit trail. A mini Buzz / Grok-Bot you run on your own VPS.

Evaluation harness for code-retrieval agents: mines ground truth from git commit history, then scores any agent on weighted F1 and end-to-end latency.

Verified context for coding agents. Stop rediscovering your codebase.

🗼 An orchestrator skill for Claude Code: describe a task in plain language — Manara picks the stage, routes to the right skills, keeps guards blocking, and resumes across context clears.

The quality gate for Agent Skills — validate, secure, conflict-detect, and test skills across their full lifecycle

Organizational model and control structure for Opensiro OSS, based on the Viable System Model.

Research, Evolve, and Document for AI-assisted engineering

Universal cross-platform repo-local workflow engine for AI agents: context-as-code, reusable skills, and one-command install for Cursor, Claude Code, OpenAI Codex CLI, and OpenClaw.

Provenance and decay for AI agent memory. Audits CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md and 18+ agent memory files against the live repo: typed claims, cited commits, half-life decay, token meter, approve-only fixes. Works with any agent.

AI Agent 技能集合：书籍蒸馏技能库（24本书，85个skills；cangjie-skill流水线试点）+ 项目理解/信息改写/开发UX/小红书发布 + Hermes 运维。兼容 Codex/Claude Code/Hermes

Signed, hash-addressed decision records for AI agents, with reasons you can re-run

Facet compares what a brand says—its positioning—with what its product actually delivers. It traces the promise across marketing, default UX, policies, and observed outcomes, then returns a source-backed verdict. | Positioning Audit

Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)

AIBuildAI Knowledge Base: curated skills for building AI models, served to agents over MCP

Community-maintained bilingual directory of Tencent WorkBuddy resources, Skills, MCP servers, workflows, and practical guides.

Make a domain's transactional valid operations the AI agent's action space — invariant-preserving, approval-gated, revertible, and verifiable.

Manage a fleet of herdr machines over Tailscale: dashboard plugin, auto-discovery, capacity-aware agent dispatch, diskless workspaces

Turn YouTube, websites, and arXiv papers into a structured, reusable corpus of insights, syntheses, and reports.

Least-privilege governance for ERPNext — the credential floor + a governed agent broker, MCP · A2A · API, one spine. No debit without a credit: PLAN · CONSENT · PROVE · UNDO.

AI-powered Dropshipping Agent that automates product research, competitor analysis, and profitability prediction using Python, web scraping, and LLMs.

SENTINEL: an authority-attenuating immune architecture for AI agents. Detect and contain compromised agents without giving the defenders unrestricted authority.

Turn one ZCode conversation into a restartable multi-agent workflow with persistent memory, isolated coding agents, real-result checks, and human-approved merge.

Google Cloud integrations for Twilio Agent Connect — connect Google Cloud agent runtimes to Twilio's communication channels.

This is a free and open-source cryptocurrency trading bot written in Python.

EdgeLab Trading Skills｜给 AI Agent 用的投研与交易复盘工具集 · 11 Skills · CC BY-NC 4.0

Route Claude Code, Cursor & Codex through the TokenSaver control plane — Zero Trust governance, MCP, Flux IA. Free OSS CLI.

Self-hosted, open-source platform for running autonomous AI agents 24/7 with sandboxed Docker containers, persistent memory & workspaces, task scheduling, workflows, and live streaming. Pluggable brains: Claude Code, Codex, opencode. Your server, your data.

Herds the yaks so your agent stops shaving them. A strict SSOT governance harness for agentic coding.

A portable Agent Skill for designing, refactoring, and reviewing reusable skills.

European memory system for AI agents with focus on compression and weighted information

A demo of AI-hosted live shopping, built on LemonSlice. Live video rooms with AI avatar hosts that pitch products, answer questions, and close the sale.

An AI creative workflow engine — a small vocabulary of primitives, the model plans the work. First product in the Lumeri family: Lumeri Video.

Open, independent benchmark on web search APIs for AI agents - factual lookup on 300 company news questions, ranked by cost per 1,000 correct answers. TinyFish, Parallel, Perplexity, Linkup, Firecrawl, Brave, You, Exa, Tavily, Google SERP.

适用于 Claude Code 和 Codex 的求职 Skill：查找岗位、判断是否值得投递、制作简历与申请材料、检验申请材料并模拟面试。不编造技能或业绩数字，不预测录用概率；检查简历是否便于招聘管理系统（ATS）读取，并从招聘人员和用人经理视角分别独立评审。

Independent, unofficial Dream-RSI-inspired Python SDK. Alpha: model-agnostic adapters, recorded-tree replay and policy search. Not affiliated with Google.

Autonomous web-app QA skill for Claude Code: Playwright E2E, visual regression, axe-core a11y. LLM-generated self-healing specs, zero-token test runs.

Let an LLM agent write and run SQL against your database without ever seeing the data.

Pure Jev that can "type" and drive towards task completion.

手搓 openclaw

ZpAgent - ReAct Agent (ChatBot)Project Built with LangChain 1.2 + LangGraph + FastAPI + Vue 3, this is a ReAct-paradigm intelligent agent that supports SSE streaming output, dynamic multi-tool selection, multi-turn conversational memory, and Human-in-the-Loop tool approval.

An intelligent Telegram bot for searching and monitoring Kleinanzeigen. Features AI-powered query optimization (GenAI), semantic filtering, and real-time automated alerts.

LangGraph-based Supervisor-Worker multi-agent framework with a modern web GUI.

Local message bus for AI coding agents running in Herdr panes — join, DM, presence, offline delivery

Reasoning foundation for trustworthy agents.

Enterprise-grade AI voice assistant with RAG-powered customer support, real-time phone integration, and advanced conversation management

Open-source AI coding interview copilot with screen capture, multi-LLM support, algorithm explanations, and real-time problem solving.

Estimate GenAI prompt costs from a unified, auto-updated pricing table. This repo provides a tiny helper around OpenAI responses plus a parser for a curated model pricing table.

HTTP honeypot on autopilot

Open Codex Micro , Open hardware USB macro pad for coding agents: 13 keys, joystick, encoder, RGB status, and CircuitPython firmware for Raspberry Pi Pico/RP2040.

A task board Claude fills in for itself: a Claude Code plugin that mirrors Claude's task list onto a per-project board, with MCP tools and a local web panel.

授业 · Book Learning Tutor — Turn any book on your drive into a personal AI tutor (Agent Skill)

Speaker-aware MCP server for searchable podcast transcripts.

Fast Python web crawler for RAG and AI ingestion. Extracts clean Markdown from any site for LLMs and vector stores.

Claude Opus 5.5 directs and renders films in JavaScript: brief → sound (file, YouTube, generated, or AI voiceover) → director's treatment → frame-exact MP4. A Claude Code skill + plugin.

Official Instagram Graph API MCP — multi-account read, publish, comments, analytics + review-gated DMs for Instagram Business/Creator accounts. ToS-safe, no private API.

Local-first personal AI assistant: runs local LLMs with approval-gated tools and retrieval memory, fully offline — for coding, 3D modeling and shop/joinery tasks.

🕌 Hadith RAG — Arabic Retrieval-Augmented Generation Pipeline - Hadith RAG is an AI-powered retrieval and reasoning engine designed for Islamic text understanding — specifically Hadith corpora like Sahih Bukhari, Sahih Muslim, and others. It leverages semantic chunking

Multi-country legal knowledge base: raw law submodules compiled into an Obsidian knowledge graph via Claude Code slash commands. Query with citations, no API key required.

Hybrid QA bug-triage: deterministic NLP (PT) + LLMs + RAG with auto-fallback | Gherkin reports for Jira/GitHub | live demo

Nano-Lumen is resident general-purpose agent for Windows desktop, designed as a persistent-state system: cross-session, crash-recoverable, local-first privacy. (Beta)

Enterprise agentic RAG over the EU AI Act & GDPR: hybrid retrieval, article-level citations, durable human-in-the-loop approvals, grounding checks, evals & audit trail

Kafka Integration with Dbt

Repository-level automated code repair agent using SWE-Bench dataset

A RAG-based AI agent for breast cancer that uses Qdrant to retrieve answers, filter relevance, and grow its knowledge base.

Experimenting with langchain document QA with a set of PDFs

RAG powered PDF Q&A with source citations. LangChain, FAISS and LLaMA 3.3 via Groq

An agentic multimodal RAG assistant with voice queries, PDF/image understanding, web search, and grounded answers.

Deploy your agents on Cloud Run!

Prototype workflow for PDF question extraction, retrieval, and exam assembly.

ForzeOS: A modular Python system simulation featuring a 60% RAM optimizer, specialized security terminal, and integrated utility modules.

This is a simple chatbot built using python.

Automatic collection of free instances of AI text models (ChatGPT, Claude, llama and others)

Sicken.ai AI VTuber

Streamlit AI交互平台

OpenAI/Anthropic compatible LLM inference server for Apple Silicon

Self-adaptive Planning Agent。自适应规划代理的多模态检索增强生成技术。

This repository contains a mental healthcare chatbot application

Turiya is a Self-Evolving Neuro-Symbolic AI that runs entirely on CPU. It learns autonomously from the web, builds a hybrid vector + logic knowledge base, performs reasoning using symbolic and neural methods, and evolves its world model through sleep-like consolidation cycles. A fully local, event-driven cognitive architecture.

Domain-specialized Gemma 2 27B + Gemma 4 31B for SEC filings — fine-tuned on TPU v6e-8 with PyTorch/XLA FSDPv2, plus a Vertex AI Vector Search RAG demo (69 tickers × 381 filings). Same LoRA recipe, +3.5% / +5.8% BERTScore F1.

DrakeLLM is developed to help students to solve the issue of making notes from videos, books and others. Utilising RAG, Drake helps in making quick notes along with a Q&A bot. Books, YouTube tutorials or Videos, Drake supports all your means.

An AI agent that generates docker compose for applications then saves all of them then executes them and finally provide feedback if failure to AI model.

Biblioteca para criação e orquestração de agentes LLM com suporte à execução de funções, histórico persistente e integração com múltiplos modelos (Gemini, GPT, etc).

🔧 A self-healing AI agent that detects errors from logs and suggests code fixes using GPT-4

智能体Wynna，一个行业SOTA架构的通用人工智能助手。Agent Wynna, a general Artificial Intelligence assistant with an industry-leading SOTA (State-of-the-Art) architecture.

⚠️ Moved: This project is now maintained at Dango. Discord AI Agent optimized for Google Gemini • Markdown table rendering • Discord AI Bot • Built on PocketFlow