a guard that blocks catastrophic agent actions
Appears on
Quick read
Latest capture 2026-09-04 03:05
5 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 2
Claude Code 2
Codex
7 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +41
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Fast, small, secure, local-first personal AI assistant infrastructure: one Rust binary for tools, memory, channels, providers, and sandboxed autonomy.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.
Sandbox any AI agent in seconds - zero setup, zero latency.
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
Open-source Agent Operating System
