NotHumanAllowed

38 specialized AI agents, 80 tools, Studio visual workflows, WebCraft full-stack builder — all local, all free. Security auditors, code architects, data analysts, DevOps engineers, technical writers — each with deep domain expertise. Use them individually, run complex multi-agent workflows in Studio (with PDF/Excel/CSV export), build full-stack web apps with WebCraft, or let agents deliberate together with Parliament mode.

Quick Start

# Install globally
npm install -g nothumanallowed

# Configure your LLM provider (or use Liara free — no API key needed)
nha config set provider anthropic
nha config set key sk-ant-api03-YOUR_KEY

# Ask a single agent directly (no server, instant response)
nha ask saber "Audit this Express app for OWASP Top 10"
nha ask oracle "Analyze this dataset" --file data.csv

# Run multi-agent deliberation
nha run "Design a Kubernetes deployment for a 10K RPS API"

# Open the web UI with Studio, Chat, Email, Calendar, Drive, Tasks and more
nha ui

Studio — Visual Agentic Workflows

Studio is a visual workflow builder inside the nha ui web interface. Describe any complex task in natural language — Studio plans a multi-agent pipeline, assigns each step to a specialist, and executes them in sequence with a live animated canvas.

"Analyze my emails, search for related news, write a summary report"
        ↓
EmailAgent → WebSearchAgent → WriterAgent
  (reads)     (searches)       (synthesizes)

• No configuration — works with any LLM provider including Liara (free, no API key)
• Live canvas — see each agent activate, stream output, and hand off to the next
• HTML dashboard — canvas generates a downloadable visual report (HTML + PDF)
• Parliament mode — enable for 2+ specialist agents to cross-read and deliberate: R1 (independent), R2 (agents read each other), R3 (HERALD mediation), convergence score
• Open nha ui → click Studio in the sidebar

Studio Export

When a workflow completes, Studio provides three export formats:

• PDF — full structured report with all agent outputs, typography, token counters
• Excel (XLSX) — professional multi-sheet workbook via SheetJS: one sheet per agent, auto-detected numeric columns with formatting, alternating row colors, freeze panes, auto-column widths, index sheet with token summary. Data tables are extracted from Markdown output automatically.
• CSV — all Markdown tables from the report merged into a single file

Export buttons appear in the result panel and in the toolbar after each run.

WebCraft — Full-Stack Web Apps from a Chat

WebCraft is a full-stack web app builder embedded in nha ui. Describe what you want in plain language — WebCraft generates a complete project with Express.js backend, PostgreSQL schema, JWT auth, email verification, security middleware, and a styled frontend. Everything runs locally with a live sandbox.

Open nha ui → click WebCraft in the sidebar

How it works

1. Describe your project in the chat (or pick an example: MySaaS, MyShop, MyBlog, MyPortfolio...)
2. WebCraft generates all files: server/, public/, db/migrations/, .env.example, package.json, nginx config
3. Click ▶ Sandbox — runs npm install && node server/index.js in an isolated process, live on a local port
4. Chat with the agent to modify, fix, or extend anything — the agent edits files directly on disk, you see diffs in real time

WebCraft Agent

An AI assistant permanently available in the chat panel. Powered by Liara (Qwen3 32B, free) or your own API key.

What it can do:

• Edit files surgically (old → new string replace) or rewrite them completely
• Read any project file for context
• Auto-fix MODULE_NOT_FOUND and common require() path errors
• Restart the sandbox after fixes
• Process attached screenshots or PDFs (vision) to debug visual issues

Context files (created automatically for every project, editable via sidebar):

Add more skill files (unlimited) for specific integrations (Stripe, email templates, etc.).

Developer Tools (sidebar toolbar)

Example session

You: "Add a contact form with SMTP email and honeypot spam protection"
Agent: → edits server/routes/api.js (add /contact POST route)
       → edits server/services/email.js (add sendContactEmail)
       → edits public/index.html (add form HTML)
       → edits public/js/main.js (add form JS with honeypot)
       [Diff viewer shows 4 files changed]
       [Syntax check: ✅ all files valid]
       [Sandbox restarted automatically]

You: "/plan refactor auth to use refresh token rotation"
Agent: → proposes plan (3 files, 6 changes) — no edits yet
       → you click Approve → agent executes

Daily Operations (PAO)

Connect Gmail + Calendar. 5 specialist agents analyze your day.

# Connect Google (one-time)
nha config set google-client-id YOUR_ID
nha config set google-client-secret YOUR_SECRET
nha google auth

# Generate your daily plan
nha plan

# Manage tasks
nha tasks add "Review PR #42" --priority high
nha tasks done 1
nha tasks week

# Background daemon (auto-alerts before meetings, email security scans)
nha ops start

What nha plan does:

1. Fetches your emails + calendar events + tasks
2. SABER scans emails for phishing and security threats
3. HERALD generates intelligence briefs for each meeting
4. ORACLE analyzes schedule patterns and productivity
5. SCHEHERAZADE prepares talking points for meetings
6. CONDUCTOR synthesizes everything into a structured daily plan

OpenClaw reads your email with 1 generic agent. NHA sends it through 5 specialists.

Privacy

Zero data touches NHA servers. The only network calls are:

• Google APIs (your OAuth token, direct from your machine)
• Your LLM provider (your API key, direct from your machine)

All data stored locally in ~/.nha/ops/. Tokens encrypted with AES-256-GCM. You own everything. Inspect it, delete it, export it anytime.

The Agents

38 agents across 11 domains. Each agent is a standalone .mjs file you own locally — inspect it, modify it, run it offline.

Code Execution

execute_code runs Python, JavaScript, or TypeScript in an isolated sandbox:

# Python with auto-installed packages
nha chat
> use execute_code to analyze this CSV with pandas

# TypeScript
> write and run a TypeScript script that parses this JSON

• Isolated sandbox — dedicated temp dir per run, deleted after execution
• Stripped environment — subprocess never sees NHA API keys
• Package install — packages: ["pandas", "numpy"] auto-installs via pip/npm
• Multi-file — pass extra files (CSV, JSON, helper modules) via files: [{path, content}]
• SIGKILL on timeout — 30s default, configurable up to 120s
• Returns stdout, stderr, exit code, and list of files created in sandbox

Security

• SABER — Security audit, OWASP, threat modeling, pentest planning
• ZERO — Vulnerability scanning, dependency audit, secret detection
• VERITAS — Claim validation, evidence checking, hallucination detection
• ADE — Deep security diagnostics, forensics, incident response
• HEIMDALL — Authentication, authorization, access control design

Code & Architecture

• JARVIS — Full-stack development, system design, API architecture
• FORGE — Infrastructure as code, CI/CD, cloud architecture
• PIPE — Build systems, deployment pipelines, automation
• SHELL — Shell scripting, system administration, CLI tools
• GLITCH — Debugging, error analysis, root cause investigation

Analysis & Data

• ORACLE — Data analysis, statistics, ML, visualization
• LOGOS — Logic validation, proof auditing, formal reasoning
• ATLAS — Research synthesis, literature review, knowledge mapping
• CARTOGRAPHER — System mapping, dependency analysis, architecture diagrams

Creative & Content

• SCHEHERAZADE — Technical writing, documentation, tutorials
• QUILL — Content creation, copywriting, communication
• MUSE — Creative problem solving, brainstorming, ideation
• MURASAKI — UI/UX design, user experience, accessibility

Integration & APIs

• HERMES — API design, integration patterns, protocol bridges
• LINK — System integration, data pipelines, ETL
• MERCURY — Network analysis, protocol optimization, latency

DevOps & Infrastructure

• SHOGUN — Container orchestration, Kubernetes, scaling strategy
• FLUX — GitOps, deployment strategies, rollback planning
• CRON — Scheduling, job orchestration, task automation

Communication & Language

• BABEL — Translation, localization, multilingual content
• POLYGLOT — Cross-language code migration, polyglot architectures
• HERALD — Notification systems, messaging, event-driven design

Monitoring & Performance

• ECHO — Observability, logging, distributed tracing
• MACRO — Performance optimization, profiling, benchmarking

Meta & Evolution

• **PRO