Launching today
ssg - AI Agent Guardrails
CONTROL your AI Agents before they control YOU
1 follower
CONTROL your AI Agents before they control YOU
1 follower
SigmaShake is a sub-millisecond governance engine for AI agents. Enforce deterministic rules, prevent destructive commands, and audit tool calls. Check it out at https://sigmashake.com Free for 2000 tool evaluations per day. Pro subscription is 50% off for unlimited tool evaluations and more.
What inspired me to build this?
AI coding agents have exploded in popularity. but there's a terrifying pattern: we’re handing AI Agents access to our production code, databases, and AWS/GCP/Azure accounts, crossing our fingers the system prompt and permissions is enough to prevent a catastrophe.
That risk that is getting worse. LLMs contribute outdated and unsafe code because it was train on year old data. It circumvent controls to get access, it gets context overload bugs and ignores instructions, and not all commands are defined by the developer to be denied. LLMs get confused by complex git repos, and simply don't understand the blast radius of running 'rm -rf' or 'git push --force'. Keeping all the permissions, system prompts, skills, and AGENT markdown files synced with several projects just made me go insane.
I wanted the massive productivity boost of AI agents without the constant hand-holding. Human's are the bottleneck and we are tired. A rogue command nuking my workspace or leaking credentials while using Claude Code, Codex, Antigravity, and Cursor in "YOLO" mode. This is risky if I worked for a company that let me use Claude Code with no restrictions... What's the worst that could happen? Anthropic leaking source code from one config change, AWS junior engineers pushing changes that take down production, and users nuking their backups during a migration.
What problem was I trying to solve?
It started when I was running Claude Code with zero token restrictions and reaching 'AI Psychosis'. If an IT team rolled out access with absolutely zero guardrails, it was basically Darwin's law. I quickly realized there are several "footguns" that completely destroy productivity that would make a computer useless until repaired. I was also spending hours of my time battling the AI Agent, because without other tools, it would use outdated and unsafe implementations of code and outdated versions of software, and it would make my tools/app become vulnerable to really dangerous exploits. As a Security Engineer, this was unacceptable. Even with a massive CLAUDE.md file and specific SKILL files, simply didn't work because of context fatigue.
Worse, Claude kept inadvertently creating fork-bombs and causing massive CPU contention with EDR software like CrowdStrike and SentinelOne, particularly when touching eBPF implementations. Traditional sandboxing, Docker limitations, and VMs weren't solving the core behavioral issue. The AI Agent still kept making the mistake of outdated versions of packages and unsafe functions, or used the wrong tool.
With a 10-year background in Security Engineering, Incident Response, and Detection & Response experience, I realized that if I was facing this, everyone using Claude Code was facing this too. No one was building the right solution that could be easily adopted and existing attempts required tons of setup to get a mediocre solution.
SigmaShake solves the probabilistic vs. deterministic mismatch. Instead of begging an LLM to behave via text prompts, SigmaShake operates entirely in local user space to intercept tool calls via hooks or MCP before execution, evaluating them against deterministic rules. The results?
Nanosecond performance: Faster and lighter than CrowdStrike or SentinelOne could ever achieve, even with eBPF.
AI Agent Harness Agnostic: Supports Claude Code, VsCode + Github Copilot, Cursor, Antigravity, Codex, Gemini CLI, Pi Agent
Massive scale: Easily supports 100,000+ rules.
Zero friction: No sandboxes, no Docker, no virtual machines. Just download, initialize in your git repo and you are protected!
Developer control: Users control and manage their own rules, we have a community hub to get you started.
How did my approach evolve while building for launch?
Initially, I just wanted a simple local blocker—a wrapper script doing regex matches on bash commands. But as I built it, I realized that security is deeply contextual.
That realization shifted everything. Instead of just a local CLI, I ended up building an entire ecosystem:
Declarative Rule Syntax (.sigmashake/rules): Allowing teams to write and enforce their own granular policies.
The SigmaShake Hub (hub.sigmashake.com): A community platform to share rulesets for specific frameworks (like rules-nginx, rules-aws, or rules-swift).
Interactive Approval Dashboard: Developers aren't just hard-blocked; they can review the agent's intent and click "Approve" when a sensitive action is genuinely required.
Daemon that is resilient to crashes using techniques form Elixir OTP/Rust Safety/Zig performance with built-in self-healing, Telemetry & Observability for users to monitor
What started as a tool to save my own sanity evolved into a comprehensive governance platform. For AI agents to truly scale into enterprise environments, the guardrails need to be lightning-fast, shareable, auditable, and seamlessly integrated into the developer workflow.