@HowToAI_ They missed the chance to call it Nested Learning: A new HOPE π
But seriously, this is great! I hope it makes as big as impact as their first paper on this subject did! Kudos to the research team!
@Dever401 Totally agree! And in my experience, a large part of keeping review quality stable is to have objective, reproducible metrics as part of the review, not just more AI prompting (as this is inherently stochastic) π
@Timur_Yessenov Done, added all your suggestions as issues that will be actively worked on. Thank you for the great discussion, please keep the ideas coming!
Just shipped devcontainer-mcp, an open source MCP server that lets AI coding agents (like Claude, GitHub Copilot and cursor) properly work seamlessly inside real dev containers.
No more messing up your local machine. The agent gets a clean, isolated, reproducible environment.
Get it on Github: https://t.co/sI1GbIa70S
One line install on Mac, Windows and Linux and with zero-setup for Claude Code, GitHub Copilot and Cursor.
Would love some early feedback from the agentic coding community!
@Timur_Yessenov Yes, this is on my list of things to add. I just added hooks to prevent the agent from using host commands and will add destructive command enforcement using this zero configuration method as well! Great suggestion π
https://t.co/uDvKIalIok
Yes, the disposable nature is one of the biggest unlocks. We can let the agent be way more aggressive (experiment, install random stuff, run heavy builds) because we can just have it delete the container/codespace/instance and spin up a fresh one in seconds.
**On secrets:** The agent never sees raw tokens or credentials.
I built a small **Auth Broker** inside devcontainer-mcp that uses opaque handles (e.g. `github-myaccount`). The real secrets stay in the hostβs keyring (via gh CLI, aws cli, etc.). The MCP server only resolves them at call time.
So even if the agent is inside the container, it canβt leak your tokens. Any scenarios you had in mind that wouldn't work with this?
Quick question for everyone using AI coding agents (Claude, Copilot, Cursor, etc.):
Whatβs your biggest frustration right now?
For me it was always:
β Breaking my local environment
β Hardware / memory limits
β Inconsistent setups across machines
Thatβs why I built devcontainer-mcp.
Whatβs YOUR #1 pain point?
https://t.co/sI1GbI9zbk
Nailed it.
Clean sandbox boundaries > βjust trust the repo.β
Thatβs exactly why I built devcontainer-mcp β proper dev containers + MCP makes agents both powerful *and* safe. Reproducible, disposable, and works across local, cloud, and Codespaces.
Appreciate the thoughtful comment!
The real power of devcontainer-mcp: it completely frees your AI agents from your local hardware limits.
Thanks to Devpod, it works not just with GitHub Codespaces, but also on AWS, Azure, GCP, Kubernetes, and any other Devpod-supported remote environment.
Watch Copilot launch a fresh cloud environment and automatically build the entire project inside it, all while my laptop stays completely untouched.
Same tool. Any cloud. Any hardware.
https://t.co/sI1GbI9zbk
Exactly! π
That's precisely why I built devcontainer-mcp, to give agents proper disposable, reproducible sandboxes instead of risking the host machine.
The isolation + multi-backend support (local, DevPod cloud, Codespaces) makes a huge difference.
Have you been running into these issues a lot with agents?