aerovato/container — Safely run OpenCode, Codex, Claude Code with full permissions.

Description and use

**Brief Summary (2‑3 sentences)**
Aerovato/container is an open‑source TypeScript toolkit that lets developers run AI models such as OpenCode, Codex, and Claude with full permissions, enabling rapid prototyping of RAG, agent‑based, or other AI‑driven features without building a model stack from scratch. With 280 ★, recent commits, and a clear API/SDK/CLI surface, it is positioned as a production‑ready component for AI‑enhanced applications.

**Value**

• **Accelerated AI integration** – provides ready‑made wrappers and execution environments, so teams can add sophisticated model capabilities (code generation, reasoning, retrieval‑augmented generation) without the overhead of infrastructure setup or custom model training.
• **Full permission model** – unlike sandboxed offerings, it grants unrestricted access to model APIs, making it suitable for complex workflows that need fine‑grained control (e.g., custom prompts, tool use, or multi‑step agent loops).
• **Developer‑friendly** – the TypeScript codebase, well‑documented CLI, and SDK let engineers stay within their existing stack, reducing context switching and onboarding time.

**Practical Adoption Path**

1. **Evaluation** – clone the repo, run the provided CLI against a test model key, and verify the API contracts (metadata, language support, topic focus).
2. **Prototype** – integrate the SDK into a sandbox service to build a small RAG or code‑assist feature, leveraging the built‑in permission handling.
3. **Pilot** – containerize the component (Docker/K8s), connect it to production model endpoints, and run performance/latency tests while monitoring security logs.
4. **Scale** – embed the container in CI/CD pipelines, expose its API to downstream services, and apply standard DevOps observability (metrics, tracing).

**Production Readiness**
The project scores high on readiness: recent activity (last commit 2026‑06‑23), solid community signals (280 ★, 30 forks, 20 topics), and a clear TypeScript implementation with API/CLI exposure. These factors indicate a stable codebase and active maintainers, making it suitable for a serious pilot. The remaining diligence items are a final license review, a security audit of the container runtime, and confirmation of long‑term maintainer commitment before full production deployment.

Problem

aerovato/container helps add AI capability without starting from a blank model stack.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• prototype AI features
• build RAG or agent workflows
• evaluate model tooling

Evidence

Safely run OpenCode, Codex, Claude Code with full permissions.

Source