Compute for everything.
Sandboxes, apps, Postgres and functions on one microVM substrate — live in 49 ms.
$pip install pandastackfrom pandastack import Sandbox
sb = Sandbox.create(template="code-interpreter")
out = sb.exec("echo 'hello from a microVM'")
print(out.stdout)
sb.kill()runs every agent
Not just a codebox. Four primitives.
Sandboxes, app hosting, Postgres and functions — one Firecracker substrate, four ways to use it.
One snapshot restore. Eight steps.
No warm pool. Every create walks the same hot path — scroll to replay it.
source: agent/internal/sandbox/manager.go
How fast is 49 ms?
A full Linux kernel, restored faster than your eyelid.
Pick a base. Ship in minutes.
Production-baked snapshots for every common agent stack. Or bring your own Dockerfile.
Code Interpreter
Python 3.11 + Node 22: pandas, numpy, jupyter, playwright, openai-agents.
Coding Agent
claude, codex, opencode, amp, grok, gemini + copilot CLIs baked in. Pick one via API key.
Claude Managed Agents
Run Anthropic's Claude Managed Agents — the ant worker executes tool calls in your microVMs.
Browser
Headless Chromium + Playwright + crawl4ai. Scrape, automate, extract.
PostgreSQL 16
Managed Postgres 16 + pgvector + pgbouncer on a durable volume.
Custom build
Bring a Dockerfile or build script. We bake the snapshot.
Spin up. Preview. Tear down.
Apps and managed Postgres aren't pets — they're built for the on-the-go, per-PR lifecycle. Open a pull request and PandaStack stands up a preview app and a throwaway database, hands you a live URL, scales to zero when idle, and tears the whole thing down on merge. No leftover infra, no idle bill.
- 01A PR openspush to a branch · or call the API
- 02App spins upbuilt in a fresh microVM, per-PR
- 03A throwaway Postgreson-the-go DB, scoped to this run
- 04Live preview URLisolated environment, real data
- 05Idle → scale-to-zerosnapshot + stop · stops billing
- 06Merge / closeapp + db torn down automatically
Need a Postgres for one preview, one eval, or one agent run? Create it in seconds, connect over TLS, throw it away. Idle DBs scale to zero — the durable volume is preserved, the bill stops.
Every pull request gets its own isolated microVM and a stable URL. Reviewers click a link, not a runbook. It rebuilds on push and disappears on merge.
Teardown is automatic on merge / close. Scale-to-zero handles the in-between. You never pay for an environment nobody is looking at.
Your host is a cache, not a hotel.
Committed memory is a ceiling, not a room held empty in your name. Each microVM's resident set breathes with real use — it grows while code runs, and the reclaim cycle hands the rest back to the host. Billing follows residency, so idle costs almost nothing.
One idle VM's resident set dropped 3258 MB → 897 MB in 12.9 s — zswap compresses the cold tail ~50× on sparse pages.
Under a 17.4 GiB burst, the host recovered 3.9 GB → 21.3 GB available in ~70 s. Zero VMs killed.
A busy VM was billed 160 active CPU-seconds — not the 1240 a committed-basis meter would charge. Its idle neighbor: 2 CPU-seconds across 306 s. RAM bills on working set, never above commitment.
Ship on the millisecond cloud.
Free tier with $5.40/mo usage credit. No card. Apache-2.0.