Production ReadyAIv1.0.0
AI

Agent Workbench

A workspace for prompts, tasks, artifacts, and coding-agent runs.

01Run timeline

Agent requests, decisions, artifacts, and human review in one stream.

02Prompt library

Reusable recipes and context bundles for repeatable agent work.

03Artifact review

Generated outputs with approval states and follow-up tasks.

Overview

Agent Workbench is built for the AI coding era: a practical foundation for teams that want to capture prompts, run context, generated files, review notes, and follow-up tasks. It gives agents a predictable domain model while giving humans a clean audit trail.

Next.jsReactTypeScriptLocal-first

Features

  • Agent run timelines
  • Prompt and context libraries
  • Generated artifact review
  • Human approval states
  • Provider-agnostic model boundaries

Make it yours in three steps

1

Download it

One click, one zip, the whole project. Free, MIT licensed, yours to keep.

Download Agent Workbench
2

Run it

Unzip it, then run this in the folder. It works immediately — no database, no accounts, no configuration.

$ npm install
$ npm run dev
3

Hand it to your coding agent

The download ships with CLAUDE.md, AGENTS.md, and Cursor rules, so your agent understands the project the moment it opens the folder.

$ cd agent-workbench
$ claude

Claude Code reads the included CLAUDE.md automatically — it already knows the project.

A good first prompt:

Give me a quick tour of this project, then help me make it mine.

Agent-ready information

The repository is organized around explicit agent concepts and ships with recipes for adding providers, artifacts, and review workflows.

CodexClaude CodeCursor
/agent/START_HERE.md/agent/PROJECT_MAP.md/agent/RULES.md/agent/RECIPES.md/agent/TESTS.md/agent/DEPLOY.md/agent/agent.json

Changelog

v1.0.0Jul 1, 2026
  • Initial release — live demo and downloadable, runnable foundation.

Related foundations

Explore nearby starting points before you commit to a fork.

Browse all
Download foundation