by romanklis · Codex Skill · ★ 26
TaskForge runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) through a human-in-the-loop approval process. Every approval triggers a container image rebuild, and every LLM interaction is logged for audit.
| Stars | 26 |
| Forks | 7 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 37.45/100 |
| Open Issues | 3 |
| Last Updated | 2026-04-11 |
| Created | 2026-02-08 |
| Platforms | docker, python |
| Est. Tokens | ~296k |
Explore other popular codex skill tools:
openclaw-contained is TaskForge runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) throug. It is categorized as a Codex Skill with 26 GitHub stars.
openclaw-contained is primarily written in Python. It covers topics such as audit, llm, openclaw.
You can find installation instructions and usage details in the openclaw-contained GitHub repository at github.com/romanklis/openclaw-contained. The project has 26 stars and 7 forks, indicating an active community.