Summary
This server brings ISG Agent 1's security scanning into Claude's context. It exposes operations for running AI security scans with stack-specific threat models, generating trust scores based on the platform's constitution and governance engine, and analyzing code for autonomous agent risks. You'd reach for this when auditing AI systems or agent codebases before deployment, especially if you need more than generic linting and want checks against adversarial prompts, skill quarantine violations, or missing governance gates. The free local scan runs entirely on your machine. Think of it as a security-first lens for evaluating whether an AI agent or LLM integration has the guardrails it claims to have.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
ISG Agent 1
Governance from Day 1. A security-hardened, governance-first autonomous AI agent platform.
ISG Agent 1 proves that autonomous AI agents can be both powerful and safe. While other agent platforms bolt on security as an afterthought, ISG Agent 1 bakes governance into every layer from the start.
7 Innovations No Other Agent Has
| Innovation | What It Does |
|---|---|
| Agent Constitution | Machine-enforced behavioral contract -- not guidelines, a verified contract |
| Adversarial Self-Testing | The agent red-teams itself in production on a schedule |
| Time-Locked Actions | Mandatory cooling period before dangerous operations (30-60s) |
| Trust Ledger | Transparent, cryptographic reputation tracking for every action |
| Explain Mode | Cryptographic proof of why every decision was made |
| Skill Reputation | Community-verified trust scores for agent skills |
| Separation of Powers | Critical actions require approval from independent agent or human |
Security Comparison
ISG Agent 1 was built as a direct response to the security failures in existing agent platforms. Where others have exposed instances, malicious skills, and no audit trails, ISG Agent 1 has localhost-only defaults, skill quarantine, and hash-chained audit logs.
Quickstart
git clone https://github.com/InnovativeSystemsGlobal/isg-agent-1.git
cd isg-agent-1
cd gateway
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp ../.env.example ../.env
cp ../config/agent.example.yaml ../config/agent.yaml
python -m isg_agent
The gateway starts on http://localhost:8900 by default (localhost-only).
Architecture
User (Discord/Telegram/Web)
-> Bridge (TypeScript, normalizes messages)
-> Gateway (Python/FastAPI, governance engine)
-> Constitution check
-> Governance gate (PROCEED/REVIEW/HALT)
-> Audit trail (SHA-256 hash chain)
-> Brain (LLM + convergence guarantees)
-> Skills (sandboxed, quarantined, reputation-scored)
-> Response (governed, explained, audited)
See ARCHITECTURE.md for the full architecture overview.
Documentation
- Quickstart Guide
- Architecture Overview
- Security Model
- The 7 Innovations
- Constitution Guide
- Skill Development
- Deployment Guide
- API Reference
Contributing
See CONTRIBUTING.md for contribution guidelines.
Security
See SECURITY.md for our responsible disclosure policy.
License
MIT License. See LICENSE for details.
Innovative Systems Global. The name is not aspirational. It is a statement of fact.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Configuration
DINGDAWG_API_KEYsecretAPI key for paid tier access — get free at dingdawg.com
Categories
Registryactive
Packagedingdawg-shield
TransportSTDIO
AuthRequired
UpdatedApr 9, 2026
