I built an open source background agent inspired by Ramp Inspect
Self-hosted coding agent runner when GitHub Copilot already does this in cloud.
Background agent runner. Kick off coding agents in cloud sandboxes, preview changes, access hosted VS Code, and get PRs back.
E2B sandbox isolation prevents agent chaos while streaming realtime previews before PR creation.
Developers wanting automated code generation with sandboxed execution
Ramp Inspect · GitHub Copilot Workspace · Replit Agent
I've been quietly working on a background agent runner inspired by Ramp Inspect.
I'm working on closing the loop between prompting, testing, and deploying:
1) You prompt agents to make changes to your projects in a web interface
2) Agents pull your code and make changes in a sandbox
3) Instantly test your changes with preview environments
4) Get a PR back
Every star on GH is motivation to keep going. Appreciate any comments or input!
jv
Self-hosted coding agent runner when GitHub Copilot already does this in cloud.
Self-hosted alternative to Stripe Minions for teams avoiding cloud-only agents.
Kanban-driven multi-agent fleet orchestration beats single-chat-per-agent tools.
Kill switch fires mid-loop at dollar ceiling before the bill lands.
Deterministic Go governor halts runaway agents at budget with HTTP 402.
Stepwise refinement teaching agentic patterns, but backlog generation is already solved by Cursor and Copilot.