awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
refly-ai avatar

refly-ai/refly

0
View on GitHub↗
7,393 stars·721 forks·TypeScript·18 viewsrefly.ai↗

Refly

Refly is an open-source platform for building, running, and sharing deterministic agent skills. It provides a visual workflow compiler that converts natural language descriptions into executable, versioned agent workflows, and includes a runtime that deploys these compiled skills as APIs, webhooks, Slack bots, or native tools for AI coding platforms like Claude Code and Cursor.

The platform distinguishes itself through a central skill registry with versioning and audit logging, enabling teams to manage agent capabilities as governed corporate assets. It supports human-in-the-loop automation, allowing users to pause, review, and modify agent execution mid-run for transparency and debugging. Workflows can be triggered on configurable schedules or via API, and the platform includes a marketplace monetization layer for publishing workflows as standalone AI apps with per-execution revenue tracking.

Refly also offers prompt-to-workflow assembly, file-based variable injection, and the ability to configure AI providers and select default chat models. Users can register a self-hosted account to access the application.

Features

  • Agentic Workflow Orchestration - Builds and runs multi-step AI workflows that chain prompts, tools, and conditional logic into deterministic agent skills.
  • Agent Skill Generators - Compiles natural-language descriptions of business logic into deterministic, reusable, and versioned agent capabilities.
  • Agent Skill Registries - Stores, versions, and shares agent capabilities as governed assets with audit logs and access control.
  • Governed Skill Registries - Provides a central registry for storing, versioning, sharing, and monetizing agent skills as governed corporate assets.
  • Visual Skill Builders - Provides an open-source platform for building, running, and sharing deterministic agent skills using visual workflows.
  • Human-in-the-Loop Steering - Pauses, reviews, and modifies agent execution mid-run to audit decisions and steer outcomes in real time.
  • Natural Language Workflow Generators - Creates a workflow plan from a natural language description, optionally overwriting an existing canvas.
  • Multi-Platform Skill Runtimes - Deploys compiled agent skills as APIs, webhooks, Slack bots, and native tools for AI coding platforms.
  • Human-in-the-Loop Workflows - Pauses, reviews, and modifies agent execution mid-run for transparent debugging and oversight.
  • Workflow Compilation - Compiles natural-language descriptions into deterministic, versioned agent workflows using a visual canvas.
  • Skill Export Formats - Delivers compiled agent skills as authenticated APIs, Slack webhooks, and native AI coding platform tools.
  • Skill Export Converters - Packages compiled workflows as authenticated APIs, webhooks, or native tools for AI coding platforms.
  • External Tool Integrations - Connects agent workflows to thousands of external APIs and MCP servers for data and logic integration.
  • Workflow Automation Engines - Compiles natural-language descriptions into executable, versioned workflows with visual canvas editing and mid-run intervention.
  • Execution Pausing - Halts workflow progress to allow manual intervention and logic modification mid-execution.
  • Human-in-the-Loop Workflows - Runs workflows as directed acyclic graphs with pause, review, and modify capabilities at each node.
  • AI Agent Deployments - Exports compiled skills as APIs, webhooks, or native tools for platforms like Claude Code and Cursor.
  • Workflow Execution APIs - Triggers a workflow execution by sending variables and returns an execution ID to track progress.
  • Skill Marketplaces - Publishes compiled agent workflows as standalone apps and earns revenue from other users running them.
  • Default Model Selection - Sets a preferred AI model to be used automatically for new conversations and workflows.
  • Model Provider Configurations - Manages external AI model provider credentials and default model selection through account settings.
  • Marketplace Monetization - Shares workflows as standalone AI apps and earns revenue each time another user runs them.
  • Workflow Monetizations - Publishes workflows as standalone AI apps in a marketplace with per-execution revenue tracking.
  • Agent Run Scheduling - Runs agent workflows on configurable schedules using a cron-based scheduler for long-running automations.
  • AI Provider Routing - Configures and selects AI service providers and chat models across all conversations and workflows.

Star history

Star history chart for refly-ai/reflyStar history chart for refly-ai/refly

How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does refly-ai/refly do?

Refly is an open-source platform for building, running, and sharing deterministic agent skills. It provides a visual workflow compiler that converts natural language descriptions into executable, versioned agent workflows, and includes a runtime that deploys these compiled skills as APIs, webhooks, Slack bots, or native tools for AI coding platforms like Claude Code and Cursor.

What are the main features of refly-ai/refly?

The main features of refly-ai/refly are: Agentic Workflow Orchestration, Agent Skill Generators, Agent Skill Registries, Governed Skill Registries, Visual Skill Builders, Human-in-the-Loop Steering, Natural Language Workflow Generators, Multi-Platform Skill Runtimes.

What are some open-source alternatives to refly-ai/refly?

Open-source alternatives to refly-ai/refly include: maiot-io/zenml — ZenML is an extensible machine learning orchestration framework designed to manage the end-to-end lifecycle of data… mastra-ai/mastra — Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and… pyspur-dev/pyspur. inngest/inngest — Inngest is a durable execution framework and event-driven automation engine designed to orchestrate background… langchain-ai/langchainjs — LangChain.js is a framework for building, executing, and monitoring stateful agentic applications. It provides an… breaking-brake/cc-wf-studio — cc-wf-studio is a suite of tools for visually designing, refining, and exporting AI agent workflows. It provides a…

Open-source alternatives to Refly

Similar open-source projects, ranked by how many features they share with Refly.
  • maiot-io/zenmlmaiot-io avatar

    maiot-io/zenml

    5,452View on GitHub↗

    ZenML is an extensible machine learning orchestration framework designed to manage the end-to-end lifecycle of data pipelines and AI agent workflows. It functions as a durable orchestrator that executes machine learning tasks as directed acyclic graphs, ensuring that every step is containerized for consistent performance across local, cloud, and hybrid infrastructure. By decoupling pipeline code from underlying compute and storage backends, the platform allows developers to define infrastructure-agnostic stacks that remain portable across diverse environments. The project distinguishes itself

    Python
    View on GitHub↗5,452
  • mastra-ai/mastramastra-ai avatar

    mastra-ai/mastra

    21,221View on GitHub↗

    Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

    TypeScriptagentsaichatbots
    View on GitHub↗21,221
  • pyspur-dev/pyspurPySpur-Dev avatar

    PySpur-Dev/pyspur

    5,677View on GitHub↗
    TypeScriptagentagentsai
    View on GitHub↗5,677
  • inngest/inngestinngest avatar

    inngest/inngest

    5,499View on GitHub↗

    Inngest is a durable execution framework and event-driven automation engine designed to orchestrate background workflows. It enables developers to build resilient, stateful processes by memoizing function steps, ensuring that long-running tasks can automatically resume from the last successful operation after failures, timeouts, or infrastructure restarts. The platform distinguishes itself through its event-driven architecture, which uses a schema-validated bus to trigger functions and coordinate complex, multi-step logic. It employs an onion-model middleware approach for cross-cutting concer

    Go
    View on GitHub↗5,499
  • See all 30 alternatives to Refly→