Sandcastle screenshot

Sandcastle

AI Coding Agent OrchestrationFree

Sandcastle TypeScript Sandbox Runner for Coding Agents

Last updated Jun 2, 2026

Claim Tool

What is Sandcastle?

Sandcastle is a TypeScript library for running AI coding agents inside controlled sandboxes. Instead of wiring together Git worktrees, containers, prompts, agent CLIs, and merge logic by hand, developers call sandcastle.run() and give the library an agent, sandbox provider, and prompt. Sandcastle then creates the isolated environment, lets the agent work, and reports the branch, commits, and iteration results. The project is built for teams experimenting with AFK coding agents, agent review loops, CI automation, and custom multi-agent orchestration. It is provider-agnostic at the sandbox layer and supports Docker, Podman, Vercel Firecracker microVMs, no-sandbox mode, and custom sandbox providers. On the agent side, the README shows usage with Claude Code and includes API shapes that can be adapted for other coding-agent providers. Sandcastle is most useful when the risk of giving an agent direct access to a repository is too high. A sandbox lets teams isolate file changes, inspect commits, compare outputs from multiple runs, and decide whether to merge. That is a practical fit for codebase maintenance, bug-fix experiments, test-writing runs, pull-request drafting, and internal tooling scripts where agents need to touch real files but should not freely mutate the host environment. The developer experience is intentionally code-first. Installation uses npm, setup starts with npx @ai-hero/sandcastle init, and the main workflow lives in TypeScript. Teams can use the generated .sandcastle folder, set environment variables such as ANTHROPIC_API_KEY, and run scripts with tsx. Advanced users can choose branch strategies, run agents interactively, create sandboxes directly, or build custom providers for their own infrastructure. Pricing depends on how you run it. The repository is MIT licensed and the npm package can be installed into a project, but users still pay for agent APIs, Claude subscriptions, Vercel sandbox usage, or the compute used by Docker and Podman environments. Sandcastle should be treated as orchestration infrastructure: it does not remove agent costs, but it can reduce operational risk when you run many agent attempts in parallel. The most important Sandcastle design choice is that the sandbox is explicit. A team can choose Docker for local bind-mounted development, Podman for rootless container workflows, Vercel for isolated cloud microVMs, or a custom provider when the default options do not fit. That flexibility lets the same orchestration code run in local experiments, CI jobs, and more controlled internal automation. It also makes Sandcastle useful as a foundation for evaluation harnesses where multiple agents attempt the same task and maintainers compare the resulting commits. Sandcastle is not a full no-code agent platform. It expects developers to write TypeScript, understand Git, and choose the right sandbox and agent provider for their risk profile. That is a feature for technical teams: the library keeps the interface small while exposing the pieces that matter for reliable automation. If your team already runs Claude Code, Codex-style tools, or internal coding agents, Sandcastle can provide the isolation and orchestration layer around those agents instead of replacing them.

Sandcastle's Top Features

Key capabilities that make Sandcastle stand out.

sandcastle.run() API for launching coding agents in TypeScript

Built-in sandbox providers for Docker, Podman, Vercel Firecracker microVMs, and no-sandbox mode

Custom sandbox provider support for team-specific infrastructure

Branch and commit reporting for reviewing agent-generated changes

CLI initialization that scaffolds a .sandcastle workspace

Use Cases

Who benefits most from this tool.

AI coding-agent teams

Run multiple coding-agent attempts in isolated environments, then review branches and commits before merging work.

Developer-tool builders

Build custom orchestration around Claude Code or similar agents without manually managing every sandbox lifecycle.

CI automation owners

Use controlled sandboxes for bug-fix experiments, test-writing runs, review agents, and repository maintenance jobs.

Tags

ai-coding-agentstypescriptsandboxclaude-codedockerpodmanverceldeveloper-toolsagent-orchestrationopen-source

Sandcastle's Pricing

Free plan available

User Reviews

Share your thoughts

If you've used this product, share your thoughts with other builders

Recent reviews

Frequently Asked Questions

What is Sandcastle?
Sandcastle is a TypeScript library for orchestrating AI coding agents inside sandboxed environments with a sandcastle.run() workflow.
Which sandbox providers does Sandcastle support?
The README lists Docker, Podman, Vercel Firecracker microVMs, no-sandbox mode, and custom sandbox providers.
Is Sandcastle only for Claude Code?
The examples show Claude Code, but the core value is sandboxed orchestration. Teams can adapt the API around agent providers that fit their stack.
Is Sandcastle free?
The repository is MIT licensed. Users still pay for any coding-agent API, subscription, or sandbox infrastructure they choose to use.