#workflow

Portable workflow engine, runtime adapters, hooks, and kits that bring evidence-gated process discipline to agent tools.

Autonomous Claude Code orchestration with persistent memory, self-coordinating agent orgs, and a codebase knowledge graph.

One CLI to orchestrate them all. Manage a team of AI agents executing tasks in parallel from your terminal using a command line interface to manage them all. Manage a team of artificial intelligence agents who perform tasks in parallel from your terminal or offline on a local or server

Laravel workflow engine: dry-run, compensation, approval gate, business impact tracker

A hybrid assembly and MAG recovery pipeline (and more!)

AI-powered engineering workflows — Learn from any source, Act through any tool, Report through any channel

A decision engine for Claude Code. MIT licensed.

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

A python workflows library that supports writing Processes with a well defined set of inputs and outputs that can be strung together.

Workflow engine where ops can yield — same async DAG handles batch jobs and event-driven streaming pipelines (pipecat-style callbot, STT → LLM → TTS). Python frontend, drop-in Rust runtime; 2–3× faster on chains, 10–30× on production workloads. LLMs, agents, RAG, native compute as first-class ops.

Simple workflow management engine with an integrated Saga pattern using Laravel Queues.

Mandrel is an orchestration and harness for agentic AI coding. It ships a system prompt, personas, a two-tier skill library, baseline rules, slash-command workflows, and a GitHub-backed orchestration engine — distributed as a Git submodule into your project's .agents/ directory.

A suite of .NET libraries: extension methods, custom types, caching, EF Core, ASP.NET Core response filtering, source generation and .NET Aspire hosting integrations.

✨ 可视化构建 MaaFramework Pipeline 的下一代工作流 审阅&编辑&调试 工具，你的工程师牛牛！ ✨

Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents

Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.

Organize your intent, loop your work and achieve the outcome you want from AI without wasting tokens

Portable application behavior for UI, forms, auth, HTTP, and document head across every JavaScript stack. Your styling system.

Typed async workflows with Result types and automatic error inference

The .NET library to build AI agents with 30+ built-in connectors.

Node-based canvas for AI media workflows - chain 100+ image, video, voice & music models (Seedance, Veo, Kling, Flux, ElevenLabs, Suno) into pipelines that run on schedules, webhooks & Telegram, then publish to 20+ platforms. Self-hostable with your own API keys. MCP server (150+ tools), SDK & CLI.

Professional UI/UX admin panel for Laravel Flow

Durable, replayable multi-step operations.

TypeScript and Python toolkits and project scaffolding for building Unified Namespace applications.

本地多运行时 Agent 工作台：围绕材料研究、生成可编辑报告、独立复核、追溯证据，并从人工反馈持续学习。

Python framework for typed LLM agents with conditional tool chaining.

A durable task substrate for agent systems

An automated job orchestration library to build and execute dynamic workflows.

A starter development kit to CI/CD based on Nuke

Get a saved, cited report from your AI agent