AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
An AI coding agent chat interface
Translation pending
Developer toolsTypeScript · HTMLGitHub @jamesmurdzaOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Run AI coding agents in isolated sandboxes connected to your GitHub repositories
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Building blocks for running AI coding agents in isolated Daytona sandboxes. Can be used in your own projects or as a standalone NextJS app:
On npm — use them in your own projects.
Not published — apps and shared internals used only in this repo.
• Node.js 20.9+ (required by Next.js 16)
Set up a local Postgres database and a .env.local file with the variables listed under Development.
Open http://localhost:4000.Read the full README ↗Building blocks for running AI coding agents in isolated Daytona sandboxes. Can be used in your own projects or as a standalone NextJS app:
https://github.com/user-attachments/assets/ee6de7e9-a32e-45bd-acfa-3da1763b80ea
On npm — use them in your own projects.
| Package | Description | Maintainer |
|---|---|---|
agent-configuration | Translation layer between coding agents' configuration formats | |
claude-credentials | Claude Code OAuth credential generation via ccauth and Daytona | |
launcher | npx background-agents launcher that runs the desktop app | |
mcp | MCP provider integrations | |
sandbox-git | Git operations for Daytona sandboxes | |
sandbox-jobs | Run, observe, and reconnect to long-running shell processes in a Daytona sandbox via the filesystem | |
sandbox-skills | Agent skills integration for Daytona sandboxes | |
sandbox-terminal | WebSocket-based PTY terminal for Daytona sandboxes | |
sdk | TypeScript SDK for running AI coding agents in Daytona sandboxes |
Not published — apps and shared internals used only in this repo.
| Package | Description | Maintainer |
|---|---|---|
common | Shared utilities and types | |
desktop | Electron desktop app for Background Agents | |
dev-cron | Local development simulator for Vercel cron jobs | |
docs | Standalone docs site deployed to docs.backgrounder.dev | |
sandbox-image | Custom Daytona sandbox image with pre-installed agent CLIs | |
web | Standalone chat app for AI coding agents |
Set up a local Postgres database and a .env.local file with the variables listed under Development.
npm install
npm run prisma:migrate
npm run dev
Open http://localhost:4000.
The desktop app loads the web app, so it has the same prerequisites as the Web quick start above.
npm install
npm run dev:electron
This starts the local web server and launches the Electron app.
The web package deploys to Vercel. See Deployment for env vars and configuration.