Python agents

Race a baseline vs a skill or MCP on real tasks. Hard checks show if it got better, faster, or cheaper. Numbers, not vibes.

The official open-source repository for community-built prototypes and tools powered by the Oxlo API

End-to-end platform for optimizing HSY Blominmäki wastewater pumping using multi-agent forecasts, a FastAPI orchestration backend, a React operator dashboard, and supporting digital-twin tooling.

AI Agent platform for online meeting agents with Google Vertex AI, Datadog and Elevenlabs integration.

⏺ OpenClaw MAS — A multi-agent development system that brings Everything Claude Code workflows into OpenClaw. 60+ skills including TDD, code review, build fixing, and GAN loops, accessible from any chat channel.

Constitutional polis of AoA: ecosystem identity, layer map, federation rules, and program-level direction.

Token-efficient stochastic testing for AI agents. 5-20x cost reduction. 10 framework adapters. Paper: arXiv:2603.02601

AI-powered interactive circuit design workflow — from natural language requirements to verified SPICE netlists and schematics.

Fraud detection MCP server: Isolation Forest + Autoencoder ensemble, behavioral biometrics, agent-to-agent transaction protection, defense compliance (NITTF/SIEM/SEAD). 24 tools, 831 tests.

Synapse AKG: High-performance Agentic Knowledge Graph with hybrid search (KNN + BM25 + RRF) for AI agents

Lean. Compatible. Based OpenClaw. Python ❤️

Intelligent delegation infrastructure for multi-agent AI systems. A protocol layer that sits between goals and agents — providing the organizational intelligence that governs how agents coordinate.

A web search agent that enables you to search, visualize, and listen to information.

Iris Agent is a lightweight, flexible framework for building AI agents in Python. It simplifies the process of creating agents that can use tools, manage memory, and interact with various LLM providers.

Macro behavioral simulation, model how populations respond to regulation, market shocks, sanctions, and policy pressure. 15 jurisdictions, epistemic transparency layer, optional LLM swarm intelligence. Upload a PDF and simulate it!

APEX-SQL is an agentic Text-to-SQL framework that shifts the paradigm from passive schema perception to agentic exploration.

Unofficial pre-ingestion adapter that converts selected FeedOracle MCP evidence into deterministic, auditable seed files for MiroFish.

Evaluate multimodal agents on complex, realistic visual tasks involving multi-step workflows in dynamic environments.

MIF — Memory Interchange Format. A vendor-neutral JSON schema for portable AI agent memories. Convert between mem0, CrewAI, LangChain, and more.

Bilingual agent workflow contracts, PR review templates, and sync automation for AI-assisted development

A cross-platform CLI tool for managing AI project artifacts.

The beginner-friendly, self-healing alternative to Openclaw. High-performance automation, without the overhead.

AI Calendar Agent is our capstone submission for https://www.kaggle.com/learn-guide/5-day-agents

Whire ToolKit - let AI agents send and receive money

Install Stet CLI and agent skill — change control for AI coding behavior

Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.

OpenClaw skill for EVE Online ESI account management

Pit AI models against each other. Score them sealed. Crown a winner. All built using the GitHub Copilot CLI. ⚡

AIDOCS — AI Doctrine Orchestrator, Control & Security.

Zero-code YAML-driven agent orchestration over strands-agents

no-code, controllable AI workflows

Prizolov Agent OS: The Open-Source Orchestration Framework for Autonomous AI Empires. Built by Dm.Andreyanov for RAG-driven business automation.

AgentxSuite is an open-source platform to connect, manage, and monitor AI Agents and Tools across multiple MCP servers — in one unified interface.

🤖 This MCP server enabling AI agents to control Android devices.

A CLI to track the arc of AI-assisted projects. Uses Obsidian as the memory layer so every chat, implementation, and review starts with full context. Works with your coding agent of choice (claude, cursor, codex), optimized for parallel work in a monorepo.

Voice-based mock interview platform featuring intelligent conversation management and time-aware stage transitions

Python SDK for Osmosis AI training workflows. Supports two training modes with shared tooling for testing and evaluation.

A deep research agent implementation using Google's Agent-to-Agent (A2A) framework with Model Context Protocol (MCP) tools

GPU-Accelerated Data Science Agents

Orchestrated planning, security auditing, and code quality skills for Claude Code

Multi-agent Uncertainty Resolution Machine: predict public opinion with local-first swarm intelligence

Provide curated Anthropic-format skills for AI agents focused on robotics software, including practical patterns, code examples, and design principles.

Casra — Claude Code-native personal AI assistant 🦀

A robust city information workflow using Crew-AI, featuring multi-agent orchestration, Pydantic validation, and OpenLIT observability for monitoring AI interactions.

MAIL is the universal communication protocol for AI agent swarms—think SMTP for autonomous systems. It enables any AI agents to seamlessly collaborate on complex tasks across organizational boundaries, unlocking enterprise-scale automation with plug-and-play interoperability.

MCP server for Power BI - Business analytics and data visualization

An AI that builds a mental model of YOU.

This repo was built by using Claude Code and agent skills which are harnessed around the Architecture Compiler, a deterministic compiler turning constraints into reviewable architectural decisions with clear trade-offs and cost impact, based on 180+ curated design patterns. Refer to https://github.com/inetgas/arch-compiler for more details.

Cache-aware orchestration for LLM agents. Fork helpers that share cached prefixes, detect cache breaks, and cut token costs by 38%+.

🔬 Implementation of agent coordination architectures and scaling principles from 'Towards a Science of Scaling Agent Systems' (arXiv:2512.08296). Research-backed multi-agent framework with benchmarks and validation.

Prompts for AI-Driven Development Lifecycle (AI-DLC v1)／AI-DLC（v1）プロセスのためのプロンプトです

Open-source agent skills for Claude Code, Claude Cowork, Codex, Cursor, and Gemini CLI. Connect AI agents to Google Analytics, Search Console, and Drive. From Temi (usetemi.com).

Agentic memory for the masses.

Cybersentry is a Python-powered cybersecurity tool designed for monitoring, incident detection, and active defense automation. It enables real-time network scanning, threat analytics, and response orchestration, providing security teams with actionable intelligence and customizable alerts.

Claude-Gemini MCP Bridge - Seamlessly integrates Google's Gemini AI with Claude Code via Model Context Protocol. Get dual AI perspectives on code review, brainstorming, and development. One-command setup with automatic configuration. Bridge two powerful AI models for enhanced workflows.

Python AI agent Framework

AI-powered self-hosted media automation agent — replace your entire arr stack with one intelligent pipeline

🐻 BearStrike AI: High-Signal Pentesting Console (MCP-First, Model-Agnostic). Build fast, low-noise security workflows with queue-first execution, skills-aware planning, and 150+ integrated tools.

A Python application that automates the organization of your Gmail emails into predefined categories (Passwords and Logins, Online Purchases, Promotions, Personal) using the Google APIs. The application automatically analyzes the content of the emails and applies appropriate labels based on configurable keywords. It also uses AI.

🧠 Drupal DevOps Co-Pilot — an open-source AI assistant that automates Jira, GitLab, Drush, and EC2 deployments using FastAPI and Ollama. From issue to deployment — faster, smarter, auditable.

2025 research prototype of an agent that adapts its own success criteria per iteration (MCDM-scored loop). Preserved as the conceptual origin of Bernstein — retrospective inside.

84 production-ready AI agent prompts + LLM-powered generators that create more. 12 departments, 20 industry playbooks, growing glossary. Not just prompts — a self-expanding library.

MemProcFS Agent Skill

Servidor local de skills com busca semântica para agentes de IA — reduz 85% do consumo de tokens tornando o conhecimento do agente reutilizável entre sessões.

Head-to-head benchmark comparing the official MCP to the MCP auto-created by Hintas.

AI-first web scraping engine with stealth bypass, MCP server, and multimodal output (Markdown, JSON, PDF) for agents and automation.

My learning and projects from Google’s 5-Day AI Agents Intensive course.

# This is no longer being update or maintained!A powerful command-line tool for interacting with Ollama models as a cybersecurity agent with pre-built expert prompts and specialized tools.

Modern cloud-native Agency Management System (AMS) for insurance agencies

AI-powered UNSPSC classification tool leveraging semantic search, vector embeddings, and large language models for enterprise-grade accuracy and performance.

A local agent architecture for semantic-aware interaction between large language models and multidimensional microscopy datasets inside napari

Lightweight and extensible memory layer for LLMs

Open-source standard for AI-readable web actions - enabling AI browsers to interact with websites efficiently

Temporal memory for your AI agents, financial research, and knowledge workflows.

A framework for resonance-based decision-making in artificial agents, combining celestial influences, memory feedback, and symbolic emergence.

AIDA-AUDIT: IDA Pro + MCP + AI agents for automated binary audit.

Cross-model shared memory for AI agents. One canon every model reads. Free OSS via pipx install memee. memee.eu hosts the Team edition with shared scope, SSO, audit log.

A reinforcement learning environment simulating hospital navigation, where AI agents learn to transport patients to treatment areas, optimize triage workflows, and manage medication logistics.

🎓 StudyAlpha is an intelligent, end-to-end AI Study Coach powered by multi-agent collaboration, memory-augmented reasoning, adaptive quizzes, and ML weakness prediction. Built for the Google × Kaggle Agents Intensive — Freestyle Track. 💡 Personalized plans • 🧠 RAG memory • 📝 Quizzes • 📊 ML evaluation • ⚙️ Streamlit UI

soami adalah starter framework modular yang bisa anda customisasi untuk membangun dan menjalankan AI Agents (seperti `Researcher`, `Planner`, dan `Coder`) berbasis Python, Flask. Cocok untuk membangun prototype AGI atau AI tooling dengan sistem orchestrator, memory, tools, dan vectorstore.

A comprehensive template for developing and deploying AI agent applications. Features Microsoft Agent Framework, AG-UI integration, CopilotKit frontend, Azure-native services, observability, and IaC-based deployment.

Helps you organize file systems with YAML-based rules for automated operations.

The free agentic AI course. 12 lessons, 12 concepts, real models. Read the framework — it's the textbook.

A curated map of agentic AI systems — covering architectures, frameworks, memory, evaluation, and safety. 🌟 Star if you like it!

A deterministic, reproducible test environment for AI browser agents

Ready-to-read fresh context for personal agents

Local-first Obsidian memory bank CLI for AI coding agents, with run logging, linked project notes, compaction, and search.

Intelligent middleware platform for Claude Code — route to any model, track costs, cache responses, auto-failover, with a 31-agent AI development team built in

An MCP server that provides a secure isolated environment for executing Python code.

Observantio's Resolver is a ground-up AI engine for modern observability. It correlates metrics, traces, and logs into a unified intelligence layer that detects anomalies, forecasts trends, and automates root cause analysis (RCA).

loafer is an AI agent designed to automate the ETL (Extract, Transform, Load) process, enabling data engineers to efficiently transform and load data into their target systems.

Advanced Claude skill to analyze Polymarket traders. Fetches on-chain data, computes ROI/performance, and detects trading strategies (Arbitrage, Whales, Market Making).

A robust MCP server that eliminates temporal blindness in AI coding agents through intelligent time tracking, persistent memory, and complete session traceability

OpenClaw orchestration and workflow control-plane with subagent-first execution and tmux compatibility.

An SDK for Python AI Agents. Under heavy development.

MCP-one is a central server that connects multiple independent MCP servers and exposes a unified interface to clients (LLMs or applications).

galdr — AI music perception framework. Translates acoustic signal into structures an LLM can encounter. Stateful listener, pattern analysis, harmonic decomposition.

🧜‍♀️Iara is an automated, project-agnostic, and configurable code review tool designed to run in CI/CD pipelines or locally via CLI. It uses the OpenRouter API to access various LLM models (Llama 3, Gemini 2.0, etc.) for free or through paid plans.

Open platform for AI agent networks — semantic discovery, a secure broker, and multidirectional agent-to-agent communication with Google A2A protocol support. Async Python (FastAPI), Postgres, Qdrant, Redis.