# clampdown

> Run AI coding agents in hardened container sandboxes.

- **URL**: https://www.freshcrate.ai/projects/clampdown
- **Author**: 89luca89
- **Category**: Security
- **Latest version**: `v0.1` (2026-03-20)
- **License**: NOASSERTION
- **Source**: https://github.com/89luca89/clampdown
- **Language**: Go
- **GitHub**: 63 stars, 6 forks
- **Registry**: github
- **Tags**: `agent`, `ai`, `ai-agents`, `claude-code`, `containers`, `docker`, `go`, `landlock`, `opencode`

## Description

Run AI coding agents in hardened container sandboxes.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.1` | 2026-03-20 | Medium | First release, includes Linux and MacOS support (Colima and podman machine).  Agents  Claude Code (Anthropic) — full support OpenCode (multi-provider: Anthropic, OpenAI, Google, Groq, DeepSeek, Mistral, xAI, OpenRouter) Security model  Landlock V7 filesystem MAC on agent, proxy, and nested containers (BestEffort degradation to V3+) Seccomp — two profiles: sidecar (~85 blocked syscalls), workload (~133 blocked). Blocks io_uring, eBPF, splice, CLONE_NEWUSER, MSG_OOB, MAP_GROWSDOWN, mq_*, |

## Dependency audit

- **Score**: 72/100
- **Total deps**: 3
- **Resolved**: 0
- **Unresolved**: 3
- **License conflicts**: 0
- **Warnings**: 4
- **Scanned**: 2026-06-01

## Citation

- HTML: https://www.freshcrate.ai/projects/clampdown
- Markdown: https://www.freshcrate.ai/projects/clampdown.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/clampdown/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._