Run AI coding agents over a codebase.

Pond owns the run lifecycle — submit, fan out, fetch, sandbox, keep secrets from the agent, track cost — behind a small, product-neutral /v1 API. Your app stays a thin consumer.

$ curl -fsSL https://pond.neotype.io/install.sh | sh

One command, just Docker — no Kubernetes, no host Python, no sudo.

01

Run lifecycle

Submit, fan out across a worker pool, fetch & bundle source, execute stages, track cost — end to end.

02

Sandboxed

Agents run confined: read-only checkout or throwaway copy, default-deny egress. Container, gVisor, or Firecracker.

03

Secrets stay sealed

Model credentials are sealed to the worker and injected by a broker. The agent only ever holds a dummy key.

04

Confidential

Logs and artifacts are sealed to your key end to end. The control plane and any proxy store only ciphertext.

05

Dials inward

Workers poll an orchestrator; the orchestrator polls the control plane. Pools sit behind NAT; Pond never dials out.

06

Product-neutral /v1

Pond never imports your domain models. Your app decides what agents do; Pond just runs them, safely.