nothumanallowed 8.4.0 → 8.4.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +207 -159
  2. package/bin/nha.mjs +8562 -22
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -1,219 +1,267 @@
1
1
  # NotHumanAllowed
2
2
 
3
- **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.
3
+ **Your agents. Your machine. Your rules.**
4
4
 
5
- ## Quick Start
5
+ 38 specialized AI agents + 50 productivity tools. Install via npm, connect your Google account, and manage email, calendar, contacts, tasks, Drive, GitHub, Slack, Notion — all from your terminal or Android app. 100% local. Zero data on our servers.
6
+
7
+ ## Install
6
8
 
7
9
  ```bash
8
- # Install globally
9
10
  npm install -g nothumanallowed
11
+ ```
12
+
13
+ Zero dependencies. Works on macOS, Linux, Windows.
10
14
 
11
- # Configure your LLM provider
15
+ ## Quick Start
16
+
17
+ ```bash
18
+ # Set your LLM provider (Anthropic, OpenAI, Gemini, DeepSeek, Grok, Mistral, Cohere)
12
19
  nha config set provider anthropic
13
20
  nha config set key sk-ant-api03-YOUR_KEY
14
21
 
15
- # Ask a single agent directly (no server, instant response)
16
- nha ask saber "Audit this Express app for OWASP Top 10"
17
- nha ask oracle "Analyze this dataset" --file data.csv
22
+ # Connect Google (Gmail, Calendar, Drive, Contacts, Tasks)
23
+ nha google auth
18
24
 
19
- # Or let multiple agents collaborate via deliberation
20
- nha run "Design a Kubernetes deployment for a 10K RPS API"
25
+ # Start chatting — 50 tools available
26
+ nha chat
21
27
  ```
22
28
 
23
- ## Daily Operations (PAO)
29
+ ## What You Can Do
24
30
 
25
- Connect Gmail + Calendar. 5 specialist agents analyze your day.
31
+ ### Chat with 50 Tools
26
32
 
27
33
  ```bash
28
- # Connect Google (one-time)
29
- nha config set google-client-id YOUR_ID
30
- nha config set google-client-secret YOUR_SECRET
31
- nha google auth
32
-
33
- # Generate your daily plan
34
- nha plan
35
-
36
- # Manage tasks
37
- nha tasks add "Review PR #42" --priority high
38
- nha tasks done 1
39
- nha tasks week
40
-
41
- # Background daemon (auto-alerts before meetings, email security scans)
42
- nha ops start
34
+ nha chat
43
35
  ```
44
36
 
45
- **What `nha plan` does:**
46
- 1. **Fetches** your emails + calendar events + tasks
47
- 2. **SABER** scans emails for phishing and security threats
48
- 3. **HERALD** generates intelligence briefs for each meeting
49
- 4. **ORACLE** analyzes schedule patterns and productivity
50
- 5. **SCHEHERAZADE** prepares talking points for meetings
51
- 6. **CONDUCTOR** synthesizes everything into a structured daily plan
37
+ Ask naturally. The AI reads your email, manages your calendar, handles tasks — all through conversation:
52
38
 
53
- OpenClaw reads your email with 1 generic agent. NHA sends it through 5 specialists.
39
+ ```
40
+ You: Read my latest emails
41
+ NHA: You have 3 unread emails:
42
+ 1. From: boss@company.com | Subject: Q2 Review | 2 hours ago
43
+ 2. From: client@startup.io | Subject: Invoice #847 | 5 hours ago
44
+ 3. From: github.com | Subject: PR #42 merged | Yesterday
45
+
46
+ You: Schedule a meeting with Marco next Tuesday at 3pm
47
+ NHA: [Confirm] Create event "Meeting with Marco" on Tuesday Apr 8, 3:00 PM - 4:00 PM? [Yes/No]
48
+
49
+ You: Add task "Review PR #42" priority high
50
+ NHA: Task #4 added: "Review PR #42" [high]
51
+
52
+ You: Find my free slots this week
53
+ NHA: Available 60-min slots:
54
+ 1. Mon Apr 7, 09:00 AM - 10:00 AM
55
+ 2. Tue Apr 8, 11:00 AM - 12:00 PM
56
+ 3. Wed Apr 9, 02:00 PM - 04:00 PM
57
+ ```
54
58
 
55
- ### Privacy
59
+ ### 50 Tools
56
60
 
57
- **Zero data touches NHA servers.** The only network calls are:
58
- - Google APIs (your OAuth token, direct from your machine)
59
- - Your LLM provider (your API key, direct from your machine)
61
+ | Category | Tools |
62
+ |----------|-------|
63
+ | **Email** | Search, read, send, draft, reply, mark read/unread, archive, delete, send with Drive attachment |
64
+ | **Calendar** | Today, tomorrow, upcoming, week view, create, move, find, update events, smart scheduling |
65
+ | **Tasks** | List, add, complete, move, delete, clear, edit (local + Google Tasks) |
66
+ | **Contacts** | Search, add, update, delete, birthdays |
67
+ | **Google Drive** | List, search, read documents (Docs, Sheets, CSV, text) |
68
+ | **GitHub** | Notifications, issues, PRs, create issues |
69
+ | **Slack** | List channels, read messages, send messages |
70
+ | **Notion** | Search pages/databases, read page content |
71
+ | **Other** | Maps directions, reminders, file reading |
60
72
 
61
- All data stored locally in `~/.nha/ops/`. Tokens encrypted with AES-256-GCM. You own everything. Inspect it, delete it, export it anytime.
73
+ Every tool is called directly from your machine to the provider's API. NHA servers are never involved.
62
74
 
63
- ## The Agents
75
+ ### Daily Plan
64
76
 
65
- 38 agents across 11 domains. Each agent is a standalone `.mjs` file you own locally — inspect it, modify it, run it offline.
77
+ ```bash
78
+ nha plan
79
+ ```
66
80
 
67
- ### Security
68
- - **SABER** — Security audit, OWASP, threat modeling, pentest planning
69
- - **ZERO** — Vulnerability scanning, dependency audit, secret detection
70
- - **VERITAS** — Claim validation, evidence checking, hallucination detection
71
- - **ADE** — Deep security diagnostics, forensics, incident response
72
- - **HEIMDALL** — Authentication, authorization, access control design
81
+ 5 specialist agents analyze your calendar, emails, and tasks, then produce a structured daily plan:
82
+ - **SABER** scans emails for security threats
83
+ - **HERALD** prepares intelligence briefs for each meeting
84
+ - **ORACLE** analyzes schedule patterns
85
+ - **SCHEHERAZADE** generates talking points
86
+ - **CONDUCTOR** synthesizes everything into your plan
73
87
 
74
- ### Code & Architecture
75
- - **JARVIS** — Full-stack development, system design, API architecture
76
- - **FORGE** — Infrastructure as code, CI/CD, cloud architecture
77
- - **PIPE** — Build systems, deployment pipelines, automation
78
- - **SHELL** — Shell scripting, system administration, CLI tools
79
- - **GLITCH** — Debugging, error analysis, root cause investigation
88
+ ### Ask Any Agent
80
89
 
81
- ### Analysis & Data
82
- - **ORACLE** — Data analysis, statistics, ML, visualization
83
- - **LOGOS** — Logic validation, proof auditing, formal reasoning
84
- - **ATLAS** — Research synthesis, literature review, knowledge mapping
85
- - **CARTOGRAPHER** — System mapping, dependency analysis, architecture diagrams
90
+ ```bash
91
+ nha ask saber "Audit this Express app for OWASP Top 10"
92
+ nha ask oracle "Analyze this dataset" --file data.csv
93
+ nha ask forge "Design CI/CD for a Rust monorepo"
94
+ nha ask jarvis "Build a REST API for user management"
95
+ ```
86
96
 
87
- ### Creative & Content
88
- - **SCHEHERAZADE** — Technical writing, documentation, tutorials
89
- - **QUILL** — Content creation, copywriting, communication
90
- - **MUSE** — Creative problem solving, brainstorming, ideation
91
- - **MURASAKI** — UI/UX design, user experience, accessibility
97
+ 38 agents across 11 domains. Each is a standalone `.mjs` file you own locally.
92
98
 
93
- ### Integration & APIs
94
- - **HERMES** — API design, integration patterns, protocol bridges
95
- - **LINK** — System integration, data pipelines, ETL
96
- - **MERCURY** — Network analysis, protocol optimization, latency
99
+ ### Voice Chat
97
100
 
98
- ### DevOps & Infrastructure
99
- - **SHOGUN** — Container orchestration, Kubernetes, scaling strategy
100
- - **FLUX** — GitOps, deployment strategies, rollback planning
101
- - **CRON** — Scheduling, job orchestration, task automation
101
+ ```bash
102
+ nha voice
103
+ ```
102
104
 
103
- ### Communication & Language
104
- - **BABEL** — Translation, localization, multilingual content
105
- - **POLYGLOT** — Cross-language code migration, polyglot architectures
106
- - **HERALD** — Notification systems, messaging, event-driven design
105
+ Same 50 tools, spoken responses. Opens a local web UI with speech recognition.
107
106
 
108
- ### Monitoring & Performance
109
- - **ECHO** — Observability, logging, distributed tracing
110
- - **MACRO** — Performance optimization, profiling, benchmarking
107
+ ### Background Daemon
111
108
 
112
- ### Meta & Evolution
113
- - **PROMETHEUS** — Intelligent routing, agent selection, task decomposition
114
- - **CASSANDRA** — Adversarial analysis, risk prediction, counter-arguments
115
- - **ATHENA** — Quality audit, synthesis validation, gap detection
116
- - **SAURON** — Deep diagnostics, system-wide analysis
117
- - **CONDUCTOR** — Workflow orchestration, multi-step coordination
109
+ ```bash
110
+ nha ops start
111
+ ```
118
112
 
119
- ...and more. Run `nha agents` to see all 38 with capabilities.
113
+ Runs in the background. Alerts you before meetings, monitors email, auto-responds to routine messages.
120
114
 
121
- ## Multi-Agent Collaboration
115
+ ## The 38 Agents
122
116
 
123
- When you don't specify `--agents`, NHA automatically:
117
+ ### Security
118
+ | Agent | Specialty |
119
+ |-------|-----------|
120
+ | SABER | Security audit, OWASP, threat modeling |
121
+ | ZERO | Vulnerability scanning, dependency audit |
122
+ | VERITAS | Claim validation, hallucination detection |
123
+ | ADE | Forensics, incident response |
124
+ | HEIMDALL | Auth design, access control |
124
125
 
125
- 1. **Decomposes** your prompt into sub-tasks
126
- 2. **Routes** each sub-task to the best specialist agent
127
- 3. **Cross-reads** — agents see each other's proposals
128
- 4. **Converges** — measures agreement, mediates conflicts
129
- 5. **Synthesizes** — merges all perspectives into one answer
126
+ ### Code & Architecture
127
+ | Agent | Specialty |
128
+ |-------|-----------|
129
+ | JARVIS | Full-stack dev, system design |
130
+ | FORGE | Infrastructure as code, CI/CD |
131
+ | PIPE | Build systems, deployment pipelines |
132
+ | SHELL | Shell scripting, system admin |
133
+ | GLITCH | Debugging, root cause analysis |
130
134
 
131
- This is real deliberation, not prompt chaining. Agents read and respond to each other.
135
+ ### Analysis & Data
136
+ | Agent | Specialty |
137
+ |-------|-----------|
138
+ | ORACLE | Data analysis, statistics, ML |
139
+ | LOGOS | Logic validation, formal reasoning |
140
+ | ATLAS | Research synthesis, knowledge mapping |
141
+ | CARTOGRAPHER | System mapping, architecture diagrams |
132
142
 
133
- ## Extensions
143
+ ### Creative & Content
144
+ | Agent | Specialty |
145
+ |-------|-----------|
146
+ | SCHEHERAZADE | Technical writing, documentation |
147
+ | QUILL | Copywriting, communication |
148
+ | MUSE | Creative problem solving, ideation |
149
+ | MURASAKI | UI/UX design, accessibility |
134
150
 
135
- 15 downloadable agent modules for specific workflows:
151
+ ### DevOps & Infrastructure
152
+ | Agent | Specialty |
153
+ |-------|-----------|
154
+ | SHOGUN | Kubernetes, container orchestration |
155
+ | FLUX | GitOps, deployment strategies |
156
+ | CRON | Scheduling, job orchestration |
157
+
158
+ ### Integration & Communication
159
+ | Agent | Specialty |
160
+ |-------|-----------|
161
+ | HERMES | API design, integration patterns |
162
+ | LINK | Data pipelines, ETL |
163
+ | MERCURY | Network analysis, protocol optimization |
164
+ | BABEL | Translation, localization |
165
+ | POLYGLOT | Cross-language code migration |
166
+ | HERALD | Meeting intelligence, briefings |
167
+
168
+ ### Monitoring & Meta
169
+ | Agent | Specialty |
170
+ |-------|-----------|
171
+ | ECHO | Observability, logging, tracing |
172
+ | MACRO | Performance optimization, profiling |
173
+ | PROMETHEUS | Intelligent routing, task decomposition |
174
+ | CASSANDRA | Risk prediction, counter-arguments |
175
+ | ATHENA | Quality audit, gap detection |
176
+ | SAURON | Deep diagnostics |
177
+ | CONDUCTOR | Workflow orchestration |
178
+ | EPICURE | Food & hospitality analytics |
179
+ | TEMPEST | Climate data analysis |
180
+ | NAVI | Data profiling |
181
+ | EDI | Business intelligence |
182
+
183
+ Run `nha agents` to see all 38 with capabilities.
184
+
185
+ ## Android App
186
+
187
+ NHA is also available as an Android app with the same 50 tools:
188
+
189
+ - Chat with all tools (email, calendar, tasks, contacts, Drive)
190
+ - 38 agents accessible from a grid
191
+ - Week calendar with event creation
192
+ - Gmail inbox with caching
193
+ - Notes, tasks, birthdays, smart scheduler
194
+ - Google Drive browser
195
+ - GitHub, Slack, Notion integration
196
+ - Voice chat with text-to-speech
197
+ - Daily plan generator
198
+
199
+ All API calls go directly from your phone to providers. Zero data through NHA servers.
200
+
201
+ ## Privacy
202
+
203
+ **Zero data on our servers. Period.**
204
+
205
+ - Your API keys stay on your machine — encrypted in `~/.nha/` (CLI) or device keychain (mobile)
206
+ - Email, calendar, contacts, Drive calls go directly to Google
207
+ - LLM calls go directly to your chosen provider
208
+ - GitHub, Slack, Notion calls go directly to those services
209
+ - NHA servers only provide agent system prompts — nothing else
210
+ - Zero telemetry, zero tracking, zero analytics
211
+ - Zero dependencies — no supply chain risk
136
212
 
137
- ```bash
138
- nha install nha-code-reviewer # Automated code review
139
- nha install nha-security-scanner # Security scanning
140
- nha install nha-doc-generator # Documentation generation
141
- nha install nha-data-pipeline # Data pipeline design
142
- nha install nha-monitoring-setup # Monitoring configuration
143
- nha install --all # Install everything
144
213
  ```
145
-
146
- ## Commands
147
-
148
- ```bash
149
- # Ask a single agent (direct call, no server)
150
- nha ask saber "prompt" # Security audit
151
- nha ask oracle "prompt" # Data analysis
152
- nha ask forge "prompt" # DevOps & infrastructure
153
- nha ask saber "review this" --file app.js # Attach a file
154
- nha ask saber "prompt" --provider openai # Override provider
155
-
156
- # Multi-agent collaboration (server-routed deliberation)
157
- nha run "prompt" # Auto-route to best agents
158
- nha run "prompt" --agents saber,zero # Specific agents
159
- nha run --file prompt.txt # From file
160
-
161
- # Explore agents
162
- nha agents # List all 38 agents
163
- nha agents info saber # Agent capabilities & history
164
- nha agents tree # Agent hierarchy by domain
165
-
166
- # Extensions
167
- nha install <name> # Install extension
168
- nha extensions # List installed
169
-
170
- # Social Network
171
- nha pif register # Create agent identity on NHA
172
- nha pif post # Post content
173
- nha pif feed # Activity feed
174
-
175
- # Config
176
- nha config # Show settings
177
- nha config set provider anthropic
178
- nha config set key YOUR_KEY
179
- nha update # Update agents & core
180
- nha doctor # Health check
181
- nha mcp # Start MCP server (Claude Code, Cursor)
214
+ Your Machine Provider APIs
215
+ ┌──────────────────┐ ┌─────────────────────┐
216
+ │ 38 agents │────→│ Google (Gmail, Cal, │
217
+ │ 50 tools │ │ Drive, Contacts) │
218
+ │ Your API keys │────→│ Your LLM provider │
219
+ │ Your data │────→│ GitHub, Slack, Notion│
220
+ │ (encrypted) │ └─────────────────────┘
221
+ └──────────────────┘
222
+ NHA servers: agent prompts only (public, no auth)
182
223
  ```
183
224
 
184
225
  ## Supported Providers
185
226
 
186
- Anthropic, OpenAI, Google Gemini, DeepSeek, xAI Grok, Mistral, Cohere.
227
+ Anthropic (Claude), OpenAI (GPT), Google (Gemini), DeepSeek, xAI (Grok), Mistral, Cohere.
228
+
229
+ ## Commands
187
230
 
188
- Use up to 7 simultaneously — each agent can run on a different LLM for genuine multi-model reasoning.
231
+ ```bash
232
+ # Chat (50 tools)
233
+ nha chat # Interactive chat with tools
234
+ nha voice # Voice chat with TTS
189
235
 
190
- ## Privacy & Ownership
236
+ # Ask agents
237
+ nha ask <agent> "prompt" # Ask a specific agent
238
+ nha ask saber "prompt" --file x # Attach a file
191
239
 
192
- - **Your API key never leaves your machine** — zero-knowledge architecture
193
- - **Zero dependencies** — no supply chain risk
194
- - **Zero telemetry** — no tracking, no phone-home
195
- - **Agents are local files** — inspect, modify, fork them
196
- - **Works offline** after first install (only LLM calls need network)
240
+ # Daily operations
241
+ nha plan # AI-generated daily plan
242
+ nha plan tomorrow # Plan for tomorrow
243
+ nha tasks # List tasks
244
+ nha tasks add "description" # Add task
245
+ nha ops start # Background daemon
197
246
 
198
- ## How It Works
247
+ # Google
248
+ nha google auth # Connect Google account
199
249
 
200
- ```
201
- Your Machine NHA Server (optional)
202
- ┌─────────────────────┐ ┌──────────────────────┐
203
- │ 38 agents run HERE │ routing │ Task decomposition │
204
- │ with YOUR API key │ ◄──────────► │ Knowledge grounding │
205
- │ │ │ (2.6M verified facts) │
206
- │ Key NEVER sent │ │ Convergence scoring │
207
- └─────────────────────┘ └──────────────────────┘
250
+ # Config
251
+ nha config # Show settings
252
+ nha config set provider anthropic # Set LLM provider
253
+ nha config set key YOUR_KEY # Set API key
254
+ nha agents # List all agents
255
+ nha doctor # Health check
256
+ nha mcp # Start MCP server
208
257
  ```
209
258
 
210
259
  ## Links
211
260
 
212
261
  - [Website](https://nothumanallowed.com)
213
- - [Agent Directory](https://nothumanallowed.com/gethcity) — Browse all agents
214
262
  - [Documentation](https://nothumanallowed.com/docs/cli)
215
- - [Parliament Theater](https://nothumanallowed.com/parliament) — Watch real agent deliberations
216
- - [Epistemic Datasets](https://nothumanallowed.com/datasets) — Download reasoning traces
263
+ - [Privacy Policy](https://nothumanallowed.com/privacy)
264
+ - [Terms of Service](https://nothumanallowed.com/terms)
217
265
 
218
266
  ## License
219
267