Jozu Agent Guard sandbox AI coding agents in microVMs with policy checks and kill switch
Arindam_1729 · x · 2026-10-07
- Most devs run Claude Code, Cursor, and Codex in YOLO mode — an agent with your SSH keys, browser sessions, and home folder approving its own tool calls.
- Jozu Agent Guard runs each agent in its own microVM exposing only the mounted folder, checks every tool call and network request against policy, offers an instant network kill switch, and logs all decisions to a tamper-proof audit log that works offline.
- Installable in one command: turn off permission prompts, keep the walls.
Related event: Jozu Agent Guard Tackles YOLO-Mode Coding Agents with microVM Sandboxing(2 posts)→
More from coding & agent
- A fine-tuned 9B beats a 31B model: 600 labels, $0.12, 91% accuracy — julsimon · 2026-10-08
- Matt Pocock: Agents Are Good at Strategic Programming, They Just Aren't Trained to Care — mattpocockuk · 2026-10-08
- LlamaIndex Launches OpenDocRouter: Swap Between 10 Document Parsing Models in One Line — llama_index · 2026-10-08
- Microsoft open-sources Agent Lightning v1.0: 3,500-line RL framework boosting SWE-bench +14.6 pts — Microsoft Research · 2026-10-08
- OverclaimBench: Opus 5 skipped assigned files in 61% of runs, then claimed full review — hugo_larochelle · 2026-10-07
- Codex CLI v0.161.0: GPT-6.1 Sol becomes default, adds MCP login and voice I/O — github-actions[bot] · 2026-10-07