markamo
Joined 8 months ago
Karma
2
Submissions
7
Member since
Mar 6
Recent submissions
Comment · 7 months ago
Comment · 8 months ago
I just reviewed this, this is openclaw for the rest of us. Great work.
Comment · 8 months ago
This is excellent. I do a lot of iot projects, and this can be time saving
Comment · 8 months ago
I kept running AI coding agents with full filesystem and network access,
and no way to review what they did before it hit my system. Docker isolates
but doesn't govern. So I built envpod.
Every agent runs in a pod with a copy-on-write overlay. Your host is never touched until you explicitly commit:
$ sudo envpod init my-agent --preset claude-code $ sudo envpod run my-agent -- claude $ sudo envpod diff my-agent # review every change $ sudo envpod commit my-agent # apply to host, or rollback
Also: encrypted credential vault (agent never sees raw API keys), per-pod DNS filtering (whitelist which domains the agent can reach), action queue (irreversible ops wait for approval), and append-only audit trail.
Single 13 MB static Rust binary. No daemon, no container runtime, no dependencies. Warm start in 32ms. 50 pod clones in 408ms. Tested on 9 Linux distros.
41 example configs for Claude Code, Codex, Aider, SWE-agent, browser-use, and more.
Website: https://envpod.dev Discord: https://discord.gg/envpod
Solo dev. Happy to answer architecture questions.
The adjacent problem I’ve been focused on is what happens after the agent finishes in its isolated environment: how do you review what it actually changed before accepting the result?
I’m interested in diff/commit/rollback at the filesystem level, so you can selectively keep some changes and discard others.
Different problem, but they compose naturally.