JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution

A Model Context Protocol server that provides task orchestration capabilities for AI assistants

Hyrex is the task framework that makes durable tasks simple. Just wrap your functions and schedule them. The only requirement is Postgres!

A modern Python task runner built for the uv era.

The core of `aipflow` is **task orchestration and execution specifications**. It provides a unified task orchestration framework that supports execution of multiple task types. The core is **pure orchestration** with no LLM dependencies - CrewAI support is optional.

Autonomous task orchestration system that keeps Claude working until a goal is achieved

Production style autonomous agent framework in Python + React that plans multistep tasks, persists state with SQLite, and recovers from failures using exponential backoff retry logic. Includes real time monitoring dashboard, deterministic recovery demo, and API for task orchestration.

Sidekick – Personal Co-Worker is a LangGraph-powered AI assistant built in Python. It uses modular orchestration (sidekick.py) and custom tools (sidekick_tools.py) to act as a personal AI co-worker for automating workflows, brainstorming, and task execution. Dependencies are managed with uv for speed and reproducibility.

Coder (Coder Crew) — A Python-based multi-agent AI template built on CrewAI, empowering developers to orchestrate collaborative AI agents for complex tasks via YAML configuration and a seamless crewai run workflow.

Demo deployment of apflow with rate limiting and quota management.

A robust Python CLI tool for defining, managing, and automating complex workflows. Streamline your data processing, script execution, and task orchestration with powerful, extensible configurations and a declarative approach. Boost productivity and ensure consistent operations across your projects.

EngineeringTeam Crew — A Python-based multi-agent AI template built on CrewAI that enables orchestrated teams of AI agents to collaborate on engineering-style tasks through simple YAML configuration and streamlined execution.

StockPicker Crew — A Python-based multi-agent AI framework using CrewAI, enabling coordinated agents to research, analyze, and generate reports (e.g., on stock-picking strategies). Easy to configure and run with YAML-based agent/task definitions and crewai run.

A Python-based multi-agent system built with CrewAI, enabling AI agents to collaborate, debate, and generate insights through task orchestration.