navada-edge-cli 3.5.9 → 3.5.10

package/README.md

@@ -88,6 +88,16 @@ Developers, system administrators, and infrastructure engineers prefer CLIs beca
 
 NAVADA Edge CLI is an AI-powered operating system layer that runs in your terminal. It is the first interface to the NAVADA Edge Network -- a distributed computing platform built for AI workloads, infrastructure management, and developer tooling.
 
+### Two parts, one CLI
+
+The NAVADA Edge CLI has two distinct modes of operation:
+
+**Part 1: Standalone CLI** -- install from npm, runs on your machine, no account needed. Full AI agent with file operations, shell access, Python execution, code sandbox, and 6 AI providers. The free tier works out of the box. When it runs out, add your own API key. This is a complete, independent developer tool.
+
+**Part 2: Cloud Compute** -- opt-in. Sign up at the Edge Portal, generate an API key, and run tasks 24/7 on AWS or Azure. Your laptop can be closed while jobs run in the cloud. Monitoring, output streaming, and task management built into the same CLI.
+
+Part 1 works without Part 2. Part 2 extends Part 1.
+
 ### What it does
 
 The CLI wraps your terminal in a conversational AI agent. It has tools for file operations, shell execution, Docker management, remote SSH, database queries, cloud services, image generation, and more. You can use slash commands for precision or type naturally and let the agent figure out what to do.
@@ -172,7 +182,7 @@ navada> list files in my home directory
 navada> create a file called test.txt with "Hello from NAVADA"
 ```
 
-The free tier uses GPT-4o-mini via the NAVADA Edge server. No API key required -- install and go.
+The free tier uses Grok via the NAVADA Edge server. No API key required -- install and go. File operations (create, read, edit, delete folders and files) work on the free tier without any AI provider.
 
 To unlock full agent mode with tool use, add your own API key:
 
@@ -195,7 +205,7 @@ The CLI supports 6 AI providers. Each is activated by logging in with the corres
 
 | Provider | Key Prefix | Model | Cost | Tool Use |
 |---|---|---|---|---|
-| **NAVADA Free Tier** | (none needed) | GPT-4o-mini | Free (30 RPM) | No |
+| **NAVADA Free Tier** | (none needed) | Grok (via Edge server) | Free (30 RPM) | File ops only |
 | **Anthropic** | `sk-ant-...` | Claude Sonnet 4 | Paid | Yes (full agent) |
 | **OpenAI** | `sk-...` | GPT-4o | Paid | Yes |
 | **Google Gemini** | `AIza...` | Gemini 2.0 Flash | Free | No |
@@ -259,7 +269,7 @@ navada> /model deepseek-r1   # always use DeepSeek R1
 
 ## Commands
 
-75 commands organised by category. Use `/help` inside the CLI for the full list.
+72 commands (91 with aliases) organised by category. Use `/help` inside the CLI for the full list.
 
 ### AI
 
@@ -355,7 +365,26 @@ navada> /model deepseek-r1   # always use DeepSeek R1
 |---|---|
 | `/db <sql>` | Query PostgreSQL |
 
-### EDGE
+### FILES
+
+| Command | Description |
+|---|---|
+| `/read <path>` | Read a file (with line numbers) |
+| `/write <path> <content>` | Write content to a file |
+| `/edit <path> <search> -> <replace>` | Find and replace in a file |
+| `/delete <path>` | Delete a file or empty directory |
+| `/ls [path]` | List files and directories |
+| `/mkdir <path>` | Create a directory |
+| `/touch <path>` | Create an empty file |
+
+File operations also work via natural language on any tier (no API key needed):
+
+```
+navada> create a folder on my desktop called MyProject
+  Created folder: C:\Users\you\Desktop\MyProject
+```
+
+### EDGE (Part 2 -- Cloud Compute)
 
 | Command | Description |
 |---|---|
@@ -363,7 +392,12 @@ navada> /model deepseek-r1   # always use DeepSeek R1
 | `/edge status` | Check Edge Network connection |
 | `/edge logout` | Disconnect from Edge Network |
 | `/edge tier` | Show current tier and limits |
+| `/edge setup` | Create agent.md and sub-agents directory |
 | `/onboard` | Open Edge Portal to create account |
+| `/offload <command>` | Run a task 24/7 on the cloud |
+| `/sessions` | View your cloud task sessions |
+| `/attach <session-id>` | Stream output from a running task |
+| `/kill <session-id>` | Stop a running cloud task |
 
 ### TASKS
 
@@ -427,6 +461,7 @@ navada> /model deepseek-r1   # always use DeepSeek R1
 | `/activity` | Recent activity log |
 | `/version` | Version and tier info |
 | `/upgrade` | Check for CLI updates |
+| `/audit` | Security and compliance audit (30 checks) |
 | `/exit` | Exit CLI |
 
 ---
@@ -469,12 +504,15 @@ The agent (Anthropic and OpenAI providers) supports tool use. The AI model decid
 | `shell` | Local | Run any shell command on your machine |
 | `read_file` | Local | Read files from your filesystem |
 | `write_file` | Local | Create or modify files |
+| `edit_file` | Local | Find and replace text in a file |
+| `delete_file` | Local | Delete a file or empty directory |
 | `list_files` | Local | Browse directories |
 | `system_info` | Local | CPU, RAM, disk, hostname, OS |
 | `python_exec` | Local | Execute Python code |
 | `python_pip` | Local | Install Python packages |
 | `python_script` | Local | Run a Python script file |
 | `sandbox_run` | Local | Run code with syntax highlighting |
+| `founder_info` | Local | Accurate answers about the NAVADA founder (CV-grounded) |
 | `network_status` | Network | Ping all NAVADA Edge nodes |
 | `lucas_exec` | Remote | Run bash on EC2 via Lucas CTO |
 | `lucas_ssh` | Remote | SSH to any network node |
@@ -483,7 +521,6 @@ The agent (Anthropic and OpenAI providers) supports tool use. The AI model decid
 | `docker_registry` | Remote | Query the private Docker registry |
 | `send_email` | Remote | Send email via SMTP or MCP |
 | `generate_image` | Remote | Generate images (Flux or DALL-E) |
-| `founder_info` | Local | Information about the NAVADA founder |
 
 The execution loop works like this:
 
@@ -537,11 +574,12 @@ navada> /doctor
 
 ### API key tiers
 
-| Tier | Requests/day | Tokens/day | Edge tasks | Max runtime |
-|---|---|---|---|---|
-| **Free** | 100 | 50K | 10 | 5 minutes |
-| **Pro** | Coming soon | -- | -- | -- |
-| **Enterprise** | Coming soon | -- | -- | -- |
+| Tier | Cloud Compute | Pricing |
+|---|---|---|
+| **Free** | 3 sessions, 1 concurrent, 5 min max | Free |
+| **Starter** | 10 sessions, 3 concurrent, 15 min max | TBC |
+| **Pro** | 50 sessions, 5 concurrent, 1 hour max | TBC |
+| **Enterprise** | 500 sessions, 10 concurrent, 4 hour max | TBC |
 
 ### Portal
 
@@ -555,17 +593,25 @@ This is the early stage of an AI-powered operating system.
 
 Today, the CLI is a terminal agent -- you install it, type naturally, and it executes tasks on your machine using AI. But the terminal is just the first interface layer. The architecture is designed for what comes next.
 
-### Where this is going
+### What is built today
 
-**Local LLM execution.** The CLI currently routes to cloud AI providers. The next step is running models locally on NVIDIA GPUs via Docker containers. Instead of paying per token to a cloud API, your home server runs Llama, Mistral, or DeepSeek locally. The CLI routes to whichever is fastest -- local GPU or cloud API -- transparently.
+**Part 1: Standalone CLI.** Install from npm and go. Full local tools (file CRUD, shell, Python, sandbox), 6 AI providers, conversation history, agent.md customisation, sub-agents, learning modes, code sandbox. Works completely independently with no account or sign-up required. Free tier included, or bring your own API key.
 
-**Edge compute offloading.** Today, `/lucas exec` sends a command to one remote node. In the future, you will be able to offload long-running tasks (ML training, batch processing, video encoding) to any node in the Edge Network. The CLI submits a task, the network schedules it on an available node, and you get notified when it completes.
+**Part 2: Cloud Compute.** Sign up at the Edge Portal, generate an API key, and offload tasks to AWS (EC2) for 24/7 execution. Tasks run when your laptop is closed. Monitor sessions, stream output, kill tasks -- all from the CLI. Authenticated via `nv_edge_` API keys with tier-based limits.
 
-**Sub-agents.** Lucas CTO is the first sub-agent -- an autonomous infrastructure manager. More are planned: a security agent for vulnerability scanning, a data agent for ETL pipelines, a monitoring agent for alerting. Each runs in its own container and communicates via MCP.
+**agent.md customisation.** Every user can define their own `agent.md` file at `~/.navada/agent.md` -- a plain-text configuration that shapes the AI's personality, tools, and behaviour. Your agent becomes uniquely yours. Sub-agents live in `~/.navada/agents/` and can be switched mid-session with `/agent use <name>`.
 
-**agent.md customisation.** Every user will be able to define their own `agent.md` file -- a plain-text configuration that shapes the AI's personality, tools, and behaviour. Your agent becomes uniquely yours: different system prompts, different tool sets, different priorities. This is the NAVADA moat -- an AI operating system that adapts to each user, not a one-size-fits-all chatbot.
+**Knowledge skills.** The CLI uses Python-based knowledge skills for grounded, accurate responses. Instead of the AI hallucinating, factual data is baked into Python scripts that the agent calls as tools. No RAG infrastructure needed -- just a Python file and a prompt.
 
-**Multi-device.** The CLI already supports mobile access via `/serve`. The vision is a unified agent layer across terminal, web, and mobile -- same context, same tools, same conversation -- wherever you are.
+### Where this is going
+
+**Azure compute node.** A second cloud region for redundancy and lower latency. The CLI will route tasks to the nearest available node.
+
+**Local LLM execution.** Running models locally on NVIDIA GPUs via Docker containers. Instead of paying per token to a cloud API, your home server runs Llama, Mistral, or DeepSeek locally. The CLI routes to whichever is fastest -- local GPU or cloud API -- transparently.
+
+**More sub-agents.** Lucas CTO is the first sub-agent -- an autonomous infrastructure manager. More are planned: a security agent for vulnerability scanning, a data agent for ETL pipelines, a monitoring agent for alerting. Each runs in its own container and communicates via MCP.
+
+**Multi-device.** The CLI supports mobile access via `/serve`. The vision is a unified agent layer across terminal, web, and mobile -- same context, same tools, same conversation -- wherever you are.
 
 ### The operating system analogy
 
@@ -609,11 +655,34 @@ NAVADA_LUCAS=http://100.x.x.x:8820
 
 | Package | Install | Purpose |
 |---|---|---|
-| **navada-edge-sdk** | `npm i navada-edge-sdk` | SDK for Node.js applications |
+| **navada-edge-sdk** | `npm i navada-edge-sdk` | SDK for Node.js applications -- build on top of the Edge Network |
 | **navada-edge-cli** | `npm i -g navada-edge-cli` | AI agent in your terminal |
-| **Edge Portal** | [portal.navada-edge-server.uk](https://portal.navada-edge-server.uk) | Account management and API keys |
+| **Edge Portal** | [portal.navada-edge-server.uk](https://portal.navada-edge-server.uk) | Account management, API keys, usage dashboard |
+| **Edge Compute** | via CLI `/offload` | 24/7 task execution on AWS/Azure |
 | **MCP Server** | `POST /mcp` | JSON-RPC tool server (18 tools) |
 
+### SDK usage
+
+The CLI ships with the NAVADA Edge SDK as a dependency. You can also install it independently to build your own applications:
+
+```bash
+npm install navada-edge-sdk
+```
+
+```javascript
+const navada = require('navada-edge-sdk');
+
+// Configure
+navada.init({ mcpApiKey: 'nv_edge_your_key' });
+
+// Use
+const status = await navada.network.ping();
+const result = await navada.mcp.call('server_status');
+const image = await navada.cloudflare.flux.generate('a sunset over mountains');
+```
+
+The SDK provides programmatic access to the same services the CLI uses: network nodes, MCP tools, Cloudflare (R2, Flux, Stream, DNS), AI providers, Docker registry, and PostgreSQL.
+
 ---
 
 ## Telemetry

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "navada-edge-cli",
-  "version": "3.5.9",
+  "version": "3.5.10",
   "description": "Interactive CLI for the NAVADA Edge Network — explore nodes, agents, Cloudflare, AI, Docker, and MCP from your terminal",
   "main": "lib/cli.js",
   "bin": {