Runsight — YAML-first workflow engine for AI agents

Runsight — YAML-first workflow engine for AI agents is an AI-powered development platform designed to streamline the creation, management, and deployment of autonomous agent workflows. By treating agent logic as code, it allows developers to define complex operational sequences using YAML files that integrate seamlessly with standard Git version control systems. This approach ensures that every change to an agent's behavior is trackable, reviewable, and reproducible within a team's existing development lifecycle. The platform features a dual-interface system where users can toggle between a visual canvas and a code editor, ensuring that the visual representation and the underlying configuration stay perfectly synchronized. This allows for rapid prototyping of multi-step processes, including loops, conditional gates, and nested sub-workflows. One of its standout capabilities is the granular monitoring system, which provides real-time tracking of execution costs and token usage for every individual block within a run. This is complemented by a robust evaluation framework that uses built-in assertions and transform hooks to validate outputs and maintain high quality across iterations. Built for developers and engineers who prioritize security and control, Runsight is an open-source, self-hosted solution that keeps API keys and model interactions within a local environment. It is particularly well-suited for building research pipelines, automated content generation systems, and complex decision-making agents that require human-in-the-loop oversight. Users can pause or terminate executions mid-flight to prevent resource waste, making it a practical tool for managing production-grade AI agents with precision and transparency.

Key Features

  • YAML-first workflow design - Git-native version control - Per-run cost tracking - Built-in evaluation framework - Pause and kill mid-flight - Open-source self-hosted engine

Use Cases

Use Case 1: Cost-Controlled Agent Development

Problem: Developers fear runaway costs when testing autonomous AI agents.
Solution: Runsight allows setting hard budget caps per run within the YAML config.
Example: An agent automatically kills its own process if the API cost hits $0.20.

Use Case 2: Team Collaboration via Git

Problem: Changes to agent logic are often hidden in messy Python files and hard to review.
Solution: Workflows are defined in YAML and managed via standard Git version control.
Example: A team lead reviews a 'git diff' to see exactly how an agent's logic was updated.

Use Case 3: Quality Assurance and Evals

Problem: It is hard to know if an agent update actually improved performance.
Solution: Built-in assertions and regression testing evaluate every block output.
Example: An assertion checks that a research agent's output is always in valid JSON format.

Target audience: Best for: AI Engineers, DevOps Teams, Software Developers

Pricing: Open Source · Categories: Chatbot Development, Developer Tools, Low-code/No-code

Related tools

  • CrewAI — CrewAI is an innovative orchestration platform designed for developers and businesses looking to build and manage multi-agent AI systems. By…
  • Uplizd — AI Agent Platform — Uplizd — AI Agent Platform is an AI-powered development environment designed for building, connecting, and deploying multi-agent AI systems on…
  • PenguinBot AI — PenguinBot AI is a deployment platform designed for teams looking to launch multi-channel AI assistants within the Microsoft Azure ecosystem.…
  • nao — nao is an open-source analytics agent builder designed to help developers and data teams construct, evaluate, and deploy reliable analytics…
  • LLMStack — LLMStack is a no-code development platform designed to simplify the creation of generative AI applications, intelligent chatbots, and autonomous agents.…
  • EverMind — EverMind is an advanced memory infrastructure designed for software developers and artificial intelligence engineers who build autonomous agents and complex…

Tags: ai agent, developer tools, low-code/no-code, OpenSource, research

Visit Runsight — YAML-first workflow engine for AI agents

What is Runsight?

Runsight is an open-source, self-hosted workflow engine designed for AI agents. It treats agent logic as code by using YAML configuration files that integrate with Git version control. The platform features synchronized code and visual canvas editors, built-in output evaluation hooks, real-time cost tracking per block, and controls to pause or stop runs mid-flight.

Who is Runsight designed for?

Runsight is designed for AI engineers, software developers, and DevOps teams who build and maintain autonomous AI agents. It is suited for technical teams that require version-controlled workflows, transparent cost monitoring, regression testing, and self-hosted environments that keep API keys and model calls under direct control.

How does Runsight track operational costs?

Runsight includes a granular monitoring system that tracks token usage and financial costs for every individual block within a run. Users can define budget caps directly within their YAML configuration, allowing the engine to automatically kill or pause a workflow if an execution reaches a predetermined spending threshold.

How does Runsight validate agent outputs?

Runsight features a built-in evaluation framework that utilizes assertions and transform hooks. Developers can configure tests within their workflows to verify outputs at each step, such as ensuring responses adhere to valid JSON formatting, which facilitates regression testing across different iterations and prompt updates.

Is Runsight free to use?

Yes, Runsight is available as an open-source tool. It is self-hosted, allowing developers to deploy and run the workflow engine on their own infrastructure without paying proprietary platform licensing fees, while retaining complete control over their local execution environment and API configurations.

  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories