This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
runspace
Disposable cloud sandboxes for humans and AI agents
runspace runs dependencies, build scripts and AI agents' commands on a disposable GitHub codespace rather than on your machine. For devs who want builds and tests off their laptop. For people who run coding agents and want every agent command in a sandbox. Has a CLI and an MCP server with the same commands, returns the work as a patch you can check before applying, and requires only a single binary and a GitHub token.
I built runspace because I wanted to have coding agents be able to access the shell without running anything on my own machine, and without having to set up VMs or a daemon to do that. My GitHub account could already create codespaces, so runspace uses them as disposable sandboxes and brings the work back as a patch I review before it lands. The most useful feedback right now is whether it works with your setup: token types other than a gh OAuth token with the codespace and repo scopes, repositories with their own devcontainer config (it needs an SSH server), and MCP clients other than Claude Code. I'd also like to hear whether the recommended agent setup feels like too much work, and about any command that suddenly breaks, because runspace depends on GitHub's undocumented codespace protocol.
No comment highlights available yet. Please check back later!
About runspace on Product Hunt
“Disposable cloud sandboxes for humans and AI agents”
runspace was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #291 on the daily leaderboard. runspace runs dependencies, build scripts and AI agents' commands on a disposable GitHub codespace rather than on your machine. For devs who want builds and tests off their laptop. For people who run coding agents and want every agent command in a sandbox. Has a CLI and an MCP server with the same commands, returns the work as a patch you can check before applying, and requires only a single binary and a GitHub token.
runspace was featured in Productivity (664.8k followers), Developer Tools (522.5k followers), Artificial Intelligence (482.9k followers) and GitHub (41.5k followers) on Product Hunt. Together, these topics include over 435.8k products, making this a competitive space to launch in.
Who hunted runspace?
runspace was hunted by Dwi Siswanto. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how runspace stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Dwi Siswanto
I built runspace because I wanted to have coding agents be able to access the shell without running anything on my own machine, and without having to set up VMs or a daemon to do that. My GitHub account could already create codespaces, so runspace uses them as disposable sandboxes and brings the work back as a patch I review before it lands. The most useful feedback right now is whether it works with your setup: token types other than a gh OAuth token with the codespace and repo scopes, repositories with their own devcontainer config (it needs an SSH server), and MCP clients other than Claude Code. I'd also like to hear whether the recommended agent setup feels like too much work, and about any command that suddenly breaks, because runspace depends on GitHub's undocumented codespace protocol.