Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

AgentRun

AgentRun is an open-source platform designed to enhance AI agents by adding self-improvement, durable execution, and a shared control plane. It works with various agent harnesses like Claude Code, Codex, Pi, and OpenCode, allowing agents to learn from past runs, reuse skills, and recover from interruptions. This platform helps manage agents efficiently and reduce token usage.

Visit Website
Share
AgentRun screenshot
AgentRun screenshot

AgentRun is an open-source platform developed by Parcha Labs that significantly enhances the capabilities of AI agents. It provides a robust control plane, enabling agents to learn from their experiences, execute tasks durably, and manage their operations more efficiently. The platform integrates seamlessly with popular agent harnesses such as Claude Code, Codex, Pi, and OpenCode, offering a unified environment for agent management.

Read More

One of AgentRun's core features is self-learning. Agents become smarter and more cost-effective with each run by identifying repeated steps and converting them into reusable skills and tested workflows. These proposals are validated and graded before acceptance, ensuring that only effective learning is integrated. This process reduces token usage by allowing agents to reuse established methods instead of repeatedly planning and discovering tools, leading to significant cost savings, with some reported cases showing up to a 90% reduction in compliance workloads.

The platform offers a flexible architecture, allowing users to choose their preferred agent harness while AgentRun manages runs, workspaces, recovery, and learning through a single API. It supports various compute environments, from lightweight sandboxes for quick scripts to development environments for building and testing code, and high-resource sandboxes for larger datasets. This separation of the agent loop from the compute environment ensures optimal resource allocation and consistent API interaction across different providers like Docker, Daytona, and Modal.

Durable execution is another critical aspect, ensuring that agent progress is preserved even if a run is interrupted. AgentRun saves conversations, files, and completed tool results, allowing runs to recover from saved states without rebuilding context. This recovery layer is consistent across different harnesses, providing reliable persistence for ongoing tasks. The platform also includes comprehensive agent management features, offering a console and API to monitor agent activities, inspect results, and review learned notes.

AgentRun is available as an Apache-2.0 open-source project, allowing users to self-host it on their own infrastructure with their model API keys, maintaining full control over agents and data. For those preferring a managed solution, AgentRun Cloud provides a hosted deployment managed by the Grep team, eliminating the need for server maintenance. Enterprise options are also available for tailored deployments with dedicated support.

  • CategoryAI Agent Builders
  • Pricing ModelOpen Source
  • DeploymentSelf-Hosted, Cloud
  • PlatformsWeb

  • Self-Learning Agents: Agents learn from runs, creating reusable skills and workflows.

  • Durable Execution: Recovers interrupted runs from saved state, preserving progress.

  • Shared Control Plane: Manages agents, runs, and learning across multiple harnesses.

  • Compute Environment Selection: Choose from lightweight, development, or high-resource sandboxes.

  • Harness Compatibility: Works with Claude Code, Codex, Pi, and OpenCode.

  • Token Usage Reduction: Reuses learned skills to minimize repeated planning and tool discovery.

  • Agent Management Console: Monitor agent activities, inspect results, and review learning notes.

  • Open-Source Platform: Apache-2.0 licensed for self-hosting and full control.

  • Workflow Authoring: Build inspectable and testable workflows combining code, tools, and agents.

  • API Access: Common API for creating agents, starting runs, and inspecting results.

  • Version Control for Agents: Manage agent definitions and revisions.

  • File Management: Each run gets its own files; upload inputs and inspect outputs.

  • Hosted Deployment Option: AgentRun Cloud for managed infrastructure.

  • Enterprise Support: Tailored deployments and support for large organizations.

  1. Install Client: Install the AgentRun client using npm or pip.

  2. Configure Environment: Set AGENTRUN_BASE_URL and AGENTRUN_API_KEY for your deployment.

  3. Define Agent: Create an agent definition, specifying its harness, instructions, and tools.

  4. Enable Learning: Configure agents to enable self-learning for skill and workflow generation.

  5. Choose Compute: Select the appropriate compute provider (Docker, Daytona, Modal) for agent execution.

  6. Start Runs: Initiate agent runs through the common API or console.

  7. Monitor & Inspect: Use the console to monitor progress, inspect results, and review learning notes.

  8. Reuse Skills: Agents automatically reuse accepted skills and workflows in subsequent runs.

  • Automated Compliance Workloads
  • Software Development & Testing
  • Data Processing & Reporting
  • Customer Support Automation
  • Research and Analysis
  • Workflow Automation
  • Agent Experimentation
  • Multi-Agent Orchestration

AgentRun Reviews

Loading...

Popular AI Tools Like AgentRun

Willder

AI Apps

Willder provides a unified memory solution for AI agents, ensuring better context, tighter control, and smoother coordination across teams. It allows agents to share knowledge,…

AI Agent Builders

Ranked #195 in AI Knowledge Management

View Tool

AI Apps

Provides a unified memory solution for AI agents, ensuring better context, tighter control, and smoother coordination across teams. It allows agents to share knowledge,…Willder provides a unified memory solution for AI agents, ensuring better context, tighter control, and smoother coordination across teams. It allows agents to share knowledge,…

AI Agent Builders
Ranked #195 in AI Knowledge Management

OpenAI Agents SDK

AI Frameworks

The OpenAI Agents SDK allows developers to create agentic AI applications with minimal complexity. It features a set of primitives for building agents, managing tasks, and…

AI Agent Builders
View Tool

AI Frameworks

The OpenAI Agents SDK allows developers to create agentic AI applications with minimal complexity. It features a set of primitives for building agents, managing tasks, and…

FeaturedAI Agent Builders
See the Top 50 AI Frameworks

Conclave

AI Apps

Conclave is a self-hosted agent harness and hub that allows coding agents to run on your own computers using various AI models like Claude Code, Codex, Gemini CLI, and OpenCode.…

AI Agent Builders
View Tool

AI Apps

Self-hosted agent harness and hub that allows coding agents to run on your own computers using various AI models like Claude Code, Codex, Gemini CLI, and OpenCode.…Conclave is a self-hosted agent harness and hub that allows coding agents to run on your own computers using various AI models like Claude Code, Codex, Gemini CLI, and OpenCode.…

AI Agent Builders
See the Top 250 AI Apps

AGNT

AI Apps

AGNT is a local-first agent operating system that allows users to bring their AI subscriptions, models, and coding agents into a single workspace. It coordinates research, code,…

AI Agent Builders

Ranked #143 in AI DevOps & Cloud Tools

View Tool

AI Apps

Local-first agent operating system that allows users to bring their AI subscriptions, models, and coding agents into a single workspace. It coordinates research, code,…AGNT is a local-first agent operating system that allows users to bring their AI subscriptions, models, and coding agents into a single workspace. It coordinates research, code,…

AI Agent Builders
Ranked #143 in AI DevOps & Cloud Tools

Omnara

AI Apps

Omnara is an open-source, model-agnostic platform for building durable, secure production AI agents, and a command center for running and steering Claude Code and Codex from…

AI Agent Builders

Ranked #59 for Prompt Engineers

View Tool

AI Apps

Open-source, model-agnostic platform for building durable, secure production AI agents, and a command center for running and steering Claude Code and Codex from…Omnara is an open-source, model-agnostic platform for building durable, secure production AI agents, and a command center for running and steering Claude Code and Codex from…

AI Agent Builders
Ranked #59 for Prompt Engineers

ERNIE Agent Platform by Baidu is an AI platform based on the ERNIE large model. It enables developers to create AI agents tailored to their industry and application needs using…

AI Agent Builders

Ranked #79 in AI Agent Builders

View Tool

ERNIE Agent Platform by Baidu is an AI platform based on the ERNIE large model. It enables developers to create AI agents tailored to their industry and application needs using…

AI Agent Builders
Ranked #79 in AI Agent Builders

AgentScope is an open-source multi-agent platform designed for building LLM-powered agent applications. It features drag-and-drop workflows, runtime management, and a…

AI Agent Builders

Ranked #26 in AI Frameworks

View Tool

Open-source multi-agent platform designed for building LLM-powered agent applications. It features drag-and-drop workflows, runtime management, and a…AgentScope is an open-source multi-agent platform designed for building LLM-powered agent applications. It features drag-and-drop workflows, runtime management, and a…

FeaturedAI Agent Builders
Ranked #26 in AI Frameworks

Agent Desktop

AI GitHub Repos

Agent Desktop is a command-line interface (CLI) tool designed for AI agents to interact with and control a computer. It enables AI agents to perform various tasks by providing a…

AI Agent Builders
View Tool

AI GitHub Repos

Command-line interface (CLI) tool designed for AI agents to interact with and control a computer. It enables AI agents to perform various tasks by providing a…Agent Desktop is a command-line interface (CLI) tool designed for AI agents to interact with and control a computer. It enables AI agents to perform various tasks by providing a…

AI Agent Builders
See the Top 250 AI GitHub Repos
1 of 8