Find tools › Open-source projects › Make your AI assistant smarter

agentrun

Open-source project · by Parcha-ai

A visual control panel that runs AI helpers, tracks spending, and lets them remember past work.

Some setupWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Track agent spending across multiple frameworks
  • Save learned skills and notes for future runs
  • Pause execution for human approvals during workflow runs

How to start

  1. Start the platform in your terminal with npx @parcha/agentrun.

  2. Open the web interface in your browser and add your model provider key in Settings.

  3. Select a prebuilt template in the dashboard to launch your first agent run.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

AgentRun is an open-source control plane and execution platform that adds learning, fault tolerance, and cost tracking to AI agents.

AI agents often repeat the exact same search steps on every run, wasting money. Reach for AgentRun when you want your agents to save learned skills across runs, survive server restarts, and remain under human approval controls.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-13. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map