by romanklis · Codex Skill · ★ 26
TaskForge Auditable Agent Orchestration for OpenClaw Disclaimer: This project is not affiliated with or endorsed by the OpenClaw project. TaskForge is an independent orchestration layer that wraps the OpenClaw agent runtime. What It Does 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 | 68.3446458308551/100 |
| 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.