Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation
LabLoop™: a research automation environment for empirical work
Hypotheses, designed experiments, evidence and conclusions as durable state — built for researchers, applications and AI agents across any empirical domain.
Two projects, side by side. Each folder is self-contained and usable on its own.
Ports are defined in ports.env (38050/38060/38070/38080/38090).
Requires KVM/libvirt on a Linux host. From ml-labloop/:
A locally built VM boots with login lab / password lab — change it after first login.
create-lab-template finds the sibling ../ml-scientist checkout automatically (override with MLSCIENTIST=). See ml-labloop/README.md for the full workflow including publishing VM images.
Released VM images live in the public Hugging Face bucket: https://huggingface.co/buckets/cloudcell/LabLoop
Download an image plus its checksum, verify it, then import it with the script in ml-labloop/release-package/:
Published images are sealed — unlike a local build, the lab/exp passwords are locked and the import generates a one-time password for first login. See ml-labloop/release-package/import-lab-vm.sh for details.
Beyond the build/clone pipeline (00/01/02), the numbered scripts cover the day-to-day operations on a running lab VM. All data movement is host-initiated over the qemu guest agent — no SSH, no virtiofs, no guest→host sockets.
Seals a template for publication (locks lab/exp passwords, sysprep, snapshot), flattens + compresses the qcow2, checksums it, and uploads the pair to the private trials bucket (hf://buckets/LabLoopCommunity/lab-trials). Asks before publishing.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/cloudcell--labloop.html)
Local credential control for AI coding agents.
1105216375-alt/resimindNeuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
Shalimov04/mcp-airlockStateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing
surendranb/writing-skillsProcedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in openc
Vuk97/codex-remote-proChatGPT <-> Codex bridge: local coding agents ask ChatGPT for advice, and ChatGPT can inspect or steer your running Codex sessions. No API key.
bestdeejay-design/agent-skillsAgent Skills - 29 skills for AI agents (Sisyphus, opencode): frontend-perfection (Lighthouse audit), secret-scanner, security-review, version-bumper, commit-lint, coverage-analyzer, api-contract-testi
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.