Agenta

Agenta is a workspace for teams building and operating AI agents. It's built around a simple idea: you should be able to work with an agent in chat, then turn that same conversation into an automated workflow without rewriting anything.

You start by describing what you want done. The agent works with your files, apps, and integrations to get it done. When you're satisfied, you tell it when to run on its own. That's the whole loop.

Key capabilities:

• Chat-first development – build and test agents conversationally, then schedule them to run without you
• Human-in-the-loop controls – consequential actions pause for your approval before anything is sent or changed
• Full versioning – prompts, skills, and tools are versioned like code, with rollback to any point
• Run tracing – every execution shows each step, its cost in tokens and dollars, and where failures occurred
• Continuous improvement – feedback from real runs becomes test cases, and changes are evaluated before they ship
• Open standards – agents are defined as AGENTS.md files with skills and MCP tools, so you can swap the model, harness, or runtime without rewriting the agent

Agenta ships with templates for common jobs: code review, customer support, sales outreach, knowledge retrieval, and operations. The code review agent template, for instance, reads pull request diffs, flags bugs and security issues inline, and tags code owners when sensitive areas like auth or billing are touched.

For teams concerned about data residency, Agenta is MIT-licensed and fully self-hostable. The self-hosted version runs the same code as Agenta Cloud, with no feature gaps or lock-in. When running locally, you can use your existing Claude or ChatGPT subscription rather than paying for a separate API key.

Agenta fits teams that want to move agents from prototype to production without losing visibility into what's actually happening at runtime.