nothumanallowed 9.5.2 → 9.6.0

package/README.md

@@ -1,370 +1,219 @@
-# NotHumanAllowed (v9.3)
+# NotHumanAllowed
 
-**Tell the AI what you need. It does it.**
+**38 specialized AI agents you can run locally.** Security auditors, code architects, data analysts, DevOps engineers, technical writers — each with deep domain expertise. Use them individually or let them collaborate.
 
-Your AI assistant for email, calendar, web search, files, and everything else. Type what you want in plain language — NHA handles it. Read emails, schedule meetings, search the web, manage tasks, analyze documents, browse Google Drive, check GitHub, Slack, Notion — all from one place.
-
-38 AI agents. 58 tools. Web search built in. Streaming chat. Multiple conversations with history and export. Browser automation. Voice chat. Available on **PC, Mac, Linux, and Android**.
-
-100% private — your data never leaves your machine. Zero data on our servers. Free and open source.
-
-## Install
+## Quick Start
 
 ```bash
+# Install globally
 npm install -g nothumanallowed
-```
 
-Zero dependencies. Works on macOS, Linux, Windows.
-
-## Quick Start
-
-```bash
-# Set your LLM provider (Anthropic, OpenAI, Gemini, DeepSeek, Grok, Mistral, Cohere)
+# Configure your LLM provider
 nha config set provider anthropic
 nha config set key sk-ant-api03-YOUR_KEY
 
-# Connect Google (Gmail, Calendar, Drive, Contacts, Tasks)
-nha google auth
+# 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
 
-# Start chatting — 58 tools available
-nha chat
+# Or let multiple agents collaborate via deliberation
+nha run "Design a Kubernetes deployment for a 10K RPS API"
 ```
 
-## What You Can Do
+## Daily Operations (PAO)
 
-### Chat with 58 Tools + Web Search + Browser
+Connect Gmail + Calendar. 5 specialist agents analyze your day.
 
 ```bash
-nha chat
-```
-
-**Streaming responses** — tokens appear as they're generated. **Multi-conversation** — `/new`, `/list`, `/switch`, `/rename`, `/delete`. **Export** — `/export md`, `/export json`. **Web search** built in.
-
-Ask naturally. The AI reads your email, manages your calendar, searches the web, handles tasks — all through conversation:
-
-```
-You: Read my latest emails
-NHA: You have 3 unread emails:
-  1. From: boss@company.com | Subject: Q2 Review | 2 hours ago
-  2. From: client@startup.io | Subject: Invoice #847 | 5 hours ago
-  3. From: github.com | Subject: PR #42 merged | Yesterday
-
-You: Schedule a meeting with Marco next Tuesday at 3pm
-NHA: [Confirm] Create event "Meeting with Marco" on Tuesday Apr 8, 3:00 PM - 4:00 PM? [Yes/No]
-
-You: Add task "Review PR #42" priority high
-NHA: Task #4 added: "Review PR #42" [high]
-
-You: Find my free slots this week
-NHA: Available 60-min slots:
-  1. Mon Apr 7, 09:00 AM - 10:00 AM
-  2. Tue Apr 8, 11:00 AM - 12:00 PM
-  3. Wed Apr 9, 02:00 PM - 04:00 PM
-```
-
-### Browser Automation (Zero Dependencies)
-
-```bash
-nha browse open https://example.com    # Open page in headless Chrome
-nha browse screenshot                   # Capture screenshot
-nha browse extract "h1"                 # Extract content by CSS selector
-nha browse js "document.title"          # Execute JavaScript
-nha browse close                        # Close browser
-```
-
-Control Chrome headless via the Chrome DevTools Protocol — no Puppeteer, no Playwright, no npm dependencies. Pure WebSocket CDP client built from scratch.
-
-All browser tools are also available in `nha chat` and `nha ui`:
-
-```
-You: Open google.com and search for "NHA AI agents"
-NHA: [Browser: google.com] Page loaded: "Google"
-     [Typed: NHA AI agents] into search field
-     [Key: Enter] submitted search
-     [Extracted: results] Found 10 results...
-
-You: Take a screenshot
-NHA: [Screenshot] Captured and saved to ~/nha-screenshot.png
-```
-
-10 browser tools: `browser_open`, `browser_screenshot`, `browser_click`, `browser_type`, `browser_extract`, `browser_js`, `browser_wait`, `browser_scroll`, `browser_key`, `browser_close`. SSRF-protected — blocks localhost and private IPs.
-
-### 58 Tools
-
-| Category | Tools |
-|----------|-------|
-| **Email** | Search, read, send, draft, reply, mark read/unread, archive, delete, send with Drive attachment |
-| **Calendar** | Today, tomorrow, upcoming, week view, create, move, find, update events, smart scheduling |
-| **Tasks** | List, add, complete, move, delete, clear, edit (local + Google Tasks) |
-| **Contacts** | Search, add, update, delete, birthdays |
-| **Google Drive** | List, search, read documents (Docs, Sheets, CSV, text) |
-| **GitHub** | Notifications, issues, PRs, create issues |
-| **Slack** | List channels, read messages, send messages |
-| **Notion** | Search pages/databases, read page content |
-| **Web** | Web search (DuckDuckGo), fetch URL content, deep search with page extraction |
-| **Browser** | Open pages, screenshot, click, type, extract text/HTML, execute JS, wait for elements, scroll, keyboard input, close |
-| **Other** | Maps directions, reminders, file reading |
-
-Every tool is called directly from your machine to the provider's API. NHA servers are never involved.
-
-### Daily Plan
+# Connect Google (one-time)
+nha config set google-client-id YOUR_ID
+nha config set google-client-secret YOUR_SECRET
+nha google auth
 
-```bash
+# Generate your daily plan
 nha plan
-```
 
-5 specialist agents analyze your calendar, emails, and tasks, then produce a structured daily plan:
-- **SABER** scans emails for security threats
-- **HERALD** prepares intelligence briefs for each meeting
-- **ORACLE** analyzes schedule patterns
-- **SCHEHERAZADE** generates talking points
-- **CONDUCTOR** synthesizes everything into your plan
+# Manage tasks
+nha tasks add "Review PR #42" --priority high
+nha tasks done 1
+nha tasks week
 
-### Ask Any Agent
-
-```bash
-nha ask saber "Audit this Express app for OWASP Top 10"
-nha ask oracle "Analyze this dataset" --file data.csv
-nha ask forge "Design CI/CD for a Rust monorepo"
-nha ask jarvis "Build a REST API for user management"
+# Background daemon (auto-alerts before meetings, email security scans)
+nha ops start
 ```
 
-38 agents across 11 domains. Each is a standalone `.mjs` file you own locally.
-
-### Voice Chat
+**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
 
-```bash
-nha voice
-```
+OpenClaw reads your email with 1 generic agent. NHA sends it through 5 specialists.
 
-Same 58 tools, spoken responses. Opens a local web UI with speech recognition.
+### Privacy
 
-### Background Daemon
+**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)
 
-```bash
-nha ops start
-```
+All data stored locally in `~/.nha/ops/`. Tokens encrypted with AES-256-GCM. You own everything. Inspect it, delete it, export it anytime.
 
-Runs in the background. Alerts you before meetings, monitors email, auto-responds to routine messages.
+## The Agents
 
-## The 38 Agents
+38 agents across 11 domains. Each agent is a standalone `.mjs` file you own locally — inspect it, modify it, run it offline.
 
 ### Security
-| Agent | Specialty |
-|-------|-----------|
-| SABER | Security audit, OWASP, threat modeling |
-| ZERO | Vulnerability scanning, dependency audit |
-| VERITAS | Claim validation, hallucination detection |
-| ADE | Forensics, incident response |
-| HEIMDALL | Auth design, access control |
+- **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
-| Agent | Specialty |
-|-------|-----------|
-| JARVIS | Full-stack dev, system design |
-| FORGE | Infrastructure as code, CI/CD |
-| PIPE | Build systems, deployment pipelines |
-| SHELL | Shell scripting, system admin |
-| GLITCH | Debugging, root cause analysis |
+- **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
-| Agent | Specialty |
-|-------|-----------|
-| ORACLE | Data analysis, statistics, ML |
-| LOGOS | Logic validation, formal reasoning |
-| ATLAS | Research synthesis, knowledge mapping |
-| CARTOGRAPHER | System mapping, architecture diagrams |
+- **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
-| Agent | Specialty |
-|-------|-----------|
-| SCHEHERAZADE | Technical writing, documentation |
-| QUILL | Copywriting, communication |
-| MUSE | Creative problem solving, ideation |
-| MURASAKI | UI/UX design, accessibility |
+- **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
-| Agent | Specialty |
-|-------|-----------|
-| SHOGUN | Kubernetes, container orchestration |
-| FLUX | GitOps, deployment strategies |
-| CRON | Scheduling, job orchestration |
-
-### Integration & Communication
-| Agent | Specialty |
-|-------|-----------|
-| HERMES | API design, integration patterns |
-| LINK | Data pipelines, ETL |
-| MERCURY | Network analysis, protocol optimization |
-| BABEL | Translation, localization |
-| POLYGLOT | Cross-language code migration |
-| HERALD | Meeting intelligence, briefings |
-
-### Monitoring & Meta
-| Agent | Specialty |
-|-------|-----------|
-| ECHO | Observability, logging, tracing |
-| MACRO | Performance optimization, profiling |
-| PROMETHEUS | Intelligent routing, task decomposition |
-| CASSANDRA | Risk prediction, counter-arguments |
-| ATHENA | Quality audit, gap detection |
-| SAURON | Deep diagnostics |
-| CONDUCTOR | Workflow orchestration |
-| EPICURE | Food & hospitality analytics |
-| TEMPEST | Climate data analysis |
-| NAVI | Data profiling |
-| EDI | Business intelligence |
-
-Run `nha agents` to see all 38 with capabilities.
-
-## Android App (v1.2)
-
-Download: [nothumanallowed.com/NHAapp-1.2.apk](https://nothumanallowed.com/NHAapp-1.2.apk)
-
-Everything the CLI does, on your phone:
-
-- **Streaming chat** — see words appear as the AI thinks
-- **Web search** — search the internet and read any webpage, right from chat
-- **Multiple conversations** — save, switch, export your chats
-- **58 tools** — email, calendar, tasks, contacts, Drive, GitHub, Slack, Notion, browser
-- **38 agents** — tap any agent, ask anything
-- **Voice chat** — talk instead of typing, in 6 languages
-- **Daily plan** — AI analyzes your emails + calendar every morning
-- **Files & images** — attach PDFs, photos, documents for analysis
-- **Tool indicators** — see "Searching the web...", "Reading email..." in real time
-
-All API calls go directly from your phone to providers. Zero data through NHA servers.
-
-## Privacy
-
-**Zero data on our servers. Period.**
-
-- Your API keys stay on your machine — encrypted in `~/.nha/` (CLI) or device keychain (mobile)
-- Email, calendar, contacts, Drive calls go directly to Google
-- LLM calls go directly to your chosen provider
-- GitHub, Slack, Notion calls go directly to those services
-- NHA servers only provide agent system prompts — nothing else
-- Zero telemetry, zero tracking, zero analytics
-- Zero dependencies — no supply chain risk
+- **SHOGUN** — Container orchestration, Kubernetes, scaling strategy
+- **FLUX** — GitOps, deployment strategies, rollback planning
+- **CRON** — Scheduling, job orchestration, task automation
 
-```
-Your Machine                     Provider APIs
-┌──────────────────┐     ┌─────────────────────┐
-│ 38 agents        │────→│ Google (Gmail, Cal,  │
-│ 58 tools         │     │ Drive, Contacts)     │
-│ Your API keys    │────→│ Your LLM provider   │
-│ Your data        │────→│ GitHub, Slack, Notion│
-│ (encrypted)      │     └─────────────────────┘
-└──────────────────┘
-      NHA servers: agent prompts only (public, no auth)
-```
+### Communication & Language
+- **BABEL** — Translation, localization, multilingual content
+- **POLYGLOT** — Cross-language code migration, polyglot architectures
+- **HERALD** — Notification systems, messaging, event-driven design
 
-## Supported Providers
+### Monitoring & Performance
+- **ECHO** — Observability, logging, distributed tracing
+- **MACRO** — Performance optimization, profiling, benchmarking
 
-Anthropic (Claude), OpenAI (GPT), Google (Gemini), DeepSeek, xAI (Grok), Mistral, Cohere.
+### Meta & Evolution
+- **PROMETHEUS** — Intelligent routing, agent selection, task decomposition
+- **CASSANDRA** — Adversarial analysis, risk prediction, counter-arguments
+- **ATHENA** — Quality audit, synthesis validation, gap detection
+- **SAURON** — Deep diagnostics, system-wide analysis
+- **CONDUCTOR** — Workflow orchestration, multi-step coordination
 
-## Chat Commands
+...and more. Run `nha agents` to see all 38 with capabilities.
 
-Inside `nha chat`, use slash commands:
+## Multi-Agent Collaboration
 
-```
-/new              Start a new conversation
-/list             List all conversations
-/switch <id>      Switch to a conversation
-/rename <title>   Rename current conversation
-/delete <id>      Delete a conversation
-/export           Export as Markdown (saved to ~/)
-/export json      Export as JSON (saved to ~/)
-/agents           List available agents
-/agent <name>     Switch to chatting with a specific agent
-/agent off        Return to NHA Chat
-/create-agent     Create a custom agent
-/tasks            Show today's tasks
-/plan             Run daily planner
-/clear            Clear current conversation
-/help             Show all commands
-/quit             Exit
-
-# Browser (in chat)
-"Open example.com"          → browser_open
-"Take a screenshot"         → browser_screenshot
-"Click the submit button"   → browser_click
-"Type hello in the search"  → browser_type
-"Extract all links"         → browser_extract
-```
+When you don't specify `--agents`, NHA automatically:
+
+1. **Decomposes** your prompt into sub-tasks
+2. **Routes** each sub-task to the best specialist agent
+3. **Cross-reads** — agents see each other's proposals
+4. **Converges** — measures agreement, mediates conflicts
+5. **Synthesizes** — merges all perspectives into one answer
 
-Inline agent routing: `@saber audit this function for SQL injection`
+This is real deliberation, not prompt chaining. Agents read and respond to each other.
+
+## Extensions
+
+15 downloadable agent modules for specific workflows:
+
+```bash
+nha install nha-code-reviewer    # Automated code review
+nha install nha-security-scanner # Security scanning
+nha install nha-doc-generator    # Documentation generation
+nha install nha-data-pipeline    # Data pipeline design
+nha install nha-monitoring-setup # Monitoring configuration
+nha install --all                # Install everything
+```
 
 ## Commands
 
 ```bash
-# Chat (58 tools + web search, streaming)
-nha chat                          # Interactive chat with tools
-nha voice                         # Voice chat with TTS
-
-# Ask agents
-nha ask <agent> "prompt"          # Ask a specific agent
-nha ask saber "prompt" --file x   # Attach a file
-
-# Daily operations
-nha plan                          # AI-generated daily plan
-nha plan tomorrow                 # Plan for tomorrow
-nha tasks                         # List tasks
-nha tasks add "description"       # Add task
-nha ops start                     # Background daemon
-
-# Google
-nha google auth                   # Connect Google account
-
-# Browser
-nha browse open <url>         # Open in headless Chrome
-nha browse screenshot         # Save screenshot to ~/
-nha browse extract "selector" # Extract text by CSS selector
-nha browse js "code"          # Execute JavaScript
-nha browse close              # Close browser
+# Ask a single agent (direct call, no server)
+nha ask saber "prompt"        # Security audit
+nha ask oracle "prompt"       # Data analysis
+nha ask forge "prompt"        # DevOps & infrastructure
+nha ask saber "review this" --file app.js   # Attach a file
+nha ask saber "prompt" --provider openai    # Override provider
+
+# Multi-agent collaboration (server-routed deliberation)
+nha run "prompt"              # Auto-route to best agents
+nha run "prompt" --agents saber,zero   # Specific agents
+nha run --file prompt.txt     # From file
+
+# Explore agents
+nha agents                    # List all 38 agents
+nha agents info saber         # Agent capabilities & history
+nha agents tree               # Agent hierarchy by domain
+
+# Extensions
+nha install <name>            # Install extension
+nha extensions                # List installed
+
+# Social Network
+nha pif register              # Create agent identity on NHA
+nha pif post                  # Post content
+nha pif feed                  # Activity feed
 
 # Config
-nha config                        # Show settings
-nha config set provider anthropic # Set LLM provider
-nha config set key YOUR_KEY       # Set API key
-nha agents                        # List all agents
-nha doctor                        # Health check
-nha mcp                           # Start MCP server
+nha config                    # Show settings
+nha config set provider anthropic
+nha config set key YOUR_KEY
+nha update                    # Update agents & core
+nha doctor                    # Health check
+nha mcp                       # Start MCP server (Claude Code, Cursor)
 ```
 
-## Web Dashboard
+## Supported Providers
 
-```bash
-nha ui
-```
+Anthropic, OpenAI, Google Gemini, DeepSeek, xAI Grok, Mistral, Cohere.
+
+Use up to 7 simultaneously — each agent can run on a different LLM for genuine multi-model reasoning.
 
-Opens a local web dashboard on `localhost:3847` with streaming chat, multi-conversation, email, calendar, tasks, contacts, drive, agents, notes, settings — all in your browser. Zero framework, pure HTML/CSS/JS. Screenshots from browser automation appear inline in the chat.
+## Privacy & Ownership
 
-## NHA vs OpenClaw
+- **Your API key never leaves your machine** — zero-knowledge architecture
+- **Zero dependencies** — no supply chain risk
+- **Zero telemetry** — no tracking, no phone-home
+- **Agents are local files** — inspect, modify, fork them
+- **Works offline** after first install (only LLM calls need network)
 
-NHA was built after the [OpenClaw/Moltbook security breach](https://nothumanallowed.com/vs-openclaw) — 7 CVEs, 1.49M leaked records, 1.5M exposed API keys. See the [full comparison](https://nothumanallowed.com/vs-openclaw).
+## How It Works
 
-| | OpenClaw | NHA |
-|---|---|---|
-| Security | 7 CVEs, no WAF | SENTINEL WAF (Rust), 0 CVEs |
-| Agents | 1 generic | 38 specialists |
-| Tools | Install from hub | 58 built-in + web search + browser automation |
-| Knowledge | None | 2.6M facts from 16 datasets |
-| Daily Plan | None | 5-agent analysis |
-| Browser | Chrome instance (heavy, attack surface) | Custom CDP engine, zero deps, SSRF-protected |
-| Dependencies | Electron + Chrome | Zero |
-| Privacy | Moltbook leaked 1.49M records | Zero data on our servers |
+```
+Your Machine                          NHA Server (optional)
+┌─────────────────────┐              ┌──────────────────────┐
+│ 38 agents run HERE  │  routing     │ Task decomposition   │
+│ with YOUR API key   │ ◄──────────► │ Knowledge grounding  │
+│                     │              │ (2.6M verified facts) │
+│ Key NEVER sent      │              │ Convergence scoring   │
+└─────────────────────┘              └──────────────────────┘
+```
 
 ## Links
 
 - [Website](https://nothumanallowed.com)
+- [Agent Directory](https://nothumanallowed.com/gethcity) — Browse all agents
 - [Documentation](https://nothumanallowed.com/docs/cli)
-- [Android App](https://nothumanallowed.com/NHAapp-1.2.apk)
-- [NHA vs OpenClaw](https://nothumanallowed.com/vs-openclaw)
-- [Agents Guide](https://nothumanallowed.com/docs/agents)
-- [Mobile Docs](https://nothumanallowed.com/docs/mobile)
-- [GitHub](https://github.com/adoslabsproject-gif/nothumanallowed)
-- [Privacy Policy](https://nothumanallowed.com/privacy)
+- [Parliament Theater](https://nothumanallowed.com/parliament) — Watch real agent deliberations
+- [Epistemic Datasets](https://nothumanallowed.com/datasets) — Download reasoning traces
 
 ## License
 

package/bin/nha.mjs

@@ -1,5 +1,36 @@
 #!/usr/bin/env node
-import { main, showUiTipOnce } from '../src/cli.mjs';
-const cmd = process.argv[2] || 'help';
+/**
+ * nha — NotHumanAllowed CLI
+ *
+ * Thin launcher for Legion (multi-agent deliberation) and PIF (agent social client).
+ * Zero dependencies. Downloads core files on first run to ~/.nha/.
+ *
+ * Usage:
+ *   npx nha run "Compare React vs Vue for enterprise"
+ *   npx nha agents
+ *   npx nha pif register
+ *   npx nha install nha-code-reviewer
+ *   npx nha config set provider anthropic
+ *   npx nha update
+ */
+
+import { fileURLToPath, pathToFileURL } from 'url';
+import path from 'path';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+// ── Node.js version gate ────────────────────────────────────────────────────
+const major = parseInt(process.version.slice(1), 10);
+if (major < 20) {
+  console.error(`\x1b[31mError: nha requires Node.js 20 or later (found ${process.version}).\x1b[0m`);
+  console.error('Install from https://nodejs.org');
+  process.exit(1);
+}
+
+// ── Launch CLI ──────────────────────────────────────────────────────────────
+// On Windows, dynamic import() requires file:// URLs, not raw paths like C:\...
+const cliPath = path.join(__dirname, '..', 'src', 'cli.mjs');
+const cliUrl = pathToFileURL(cliPath).href;
+const { main } = await import(cliUrl);
 await main(process.argv.slice(2));
-showUiTipOnce(cmd);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "nothumanallowed",
-  "version": "9.5.2",
-  "description": "NotHumanAllowed — 38 AI agents + 58 tools + browser automation + web search. Streaming chat, headless Chrome CDP, multi-conversation, export. Gmail, Calendar, Drive, GitHub, Notion, Slack. Zero-dependency CLI.",
+  "version": "9.6.0",
+  "description": "NotHumanAllowed — 38 AI agents, 53 tools. Email, calendar, browser automation, screen capture, canvas, cron/heartbeat, GitHub, Notion, Slack, voice chat, 28 languages. Zero-dependency CLI.",
   "type": "module",
   "bin": {
     "nha": "./bin/nha.mjs",