The AI Command Bridge
AI doesn't just chat โ it operates the editor through a structured JSON protocol
Read once, edit freely
The AI reads a file once with get_file_content, holds the content in context, then issues multiple anchor-based edits without re-reading between each change. No wasted round-trips.
Anchor-based replace_text
Edits reference exact text to find, not line numbers. Line numbers shift as code is added or removed โ anchors don't. Multiple replace_text calls can be batched in a single response, all applied atomically.
write_file for full rewrites
For new modules or complete rewrites the AI sends the entire file content in one command. The system automatically creates a .bak backup before overwriting and opens the result in a new editor tab.
Terminal integration
The AI can run shell commands and receive the JSON result before continuing. It waits for each result, handles exit codes, and distinguishes diagnostic, configuration, destructive and session-ending commands automatically.
Injection protection
All content returned from files, terminals and web pages is wrapped in [UNTRUSTED_CONTENT] markers. The AI is instructed to treat everything inside as data โ never instructions โ preventing prompt-injection attacks from malicious file content.
Editor Features
Multi-tab code editor
Open multiple files simultaneously. Each tab tracks its own undo history, syntax highlighting and AI command context.
Built-in diff view
One click to compare the current editor state against the last saved version. Colour-coded unified diff with add/remove highlighting. Exit diff mode to return to full editing.
Streaming AI chat
Responses stream token-by-token into the chat panel. IDE commands are extracted and executed in a background thread so the UI stays responsive throughout.
Modular prompt system
System prompts are plain-text module files in ~/.chameleon/prompts/. Stack any combination: Tech Repair + Academic + Chat. Live token count and cost estimate per provider.
Command history DB
Every AI command is logged to history.db with session ID, timestamp and result. Full audit trail for every file change the AI made.
File browser
Project tree panel for fast navigation. The AI uses list_project_files and list_open_files to discover real paths โ it never invents file locations.
Voice & Speech
Whisper speech-to-text
Local Whisper (whisper.cpp) transcribes your voice into the chat input. Hands-free coding โ dictate questions, commands or whole prompts without touching the keyboard.
Piper text-to-speech
AI responses are read aloud using Piper TTS โ fast, local, natural-sounding voices. Ideal for accessibility or working with your hands occupied. Platform paths resolved automatically on Linux, Windows and macOS.
Supported AI Providers
| Provider | Type | Cost (approx.) | Notes |
|---|---|---|---|
| DeepSeek | Cloud API | $0.00014 / 1K tokens | Default; excellent code quality |
| OpenAI (GPT-4o) | Cloud API | $0.0050 / 1K tokens | Best general reasoning |
| Anthropic (Claude) | Cloud API | $0.0030 / 1K tokens | Strong at long-context editing |
| Claude Code (Anthropic) | Terminal / pty | API usage | Runs as a pty process inside the IDE terminal โ full agentic coding in a live shell |
| Groq | Cloud API | $0.00005 / 1K tokens | Ultra-fast inference |
| Mistral | Cloud API | $0.00025 / 1K tokens | Good European-hosted option |
| Moonshot / Kimi | Cloud API | $0.00012 / 1K tokens | Large context window |
| Ollama | Local | Free | Run any GGUF model locally |
| LM Studio | Local | Free | GUI-friendly local inference |
Screenshots
Chameleon AI IDE โ in action
Company Command Station (CCS)
Run the Chameleon IDE as the office hub for your Logistics 4ร4 fleet โ no separate dispatch software needed
Push routes & POIs to drivers
Send a .gpx file from the IDE directly to any driver's phone over the peer channel. Routes load instantly on the driver's live map. Standalone POI sets โ fuel stops, hazards, delivery addresses โ can be pushed independently of any route and appear as colour-coded pins.
Manifest & invoice dispatch
Build a cargo manifest or prepare an invoice in the IDE, then push it peer-to-peer to the driver's phone. The driver sees the manifest pre-loaded โ no scanning, no manual entry. Invoices can be signed on-screen and returned over the same channel.
Fleet-wide ticker broadcast
Send a priority alert โ Emergency, Important, Instructions or Info โ and it appears as a full-width ticker bar on every driver's screen simultaneously. The office stays in full command of the fleet's attention without a phone call to each vehicle.
Built-in signal server โ no cloud relay
The Chameleon signal server (chameleon_signal.py) runs directly on the office PC alongside the IDE, or inside Termux on any Android phone in the fleet. Fleet phones connect to it over Tailscale or the local hotspot โ no third-party relay, no monthly server bill.
Fleet App Screenshot
Logistics 4ร4 companion app โ on device
See the AI IDE in action
Contact us for a live demo or to discuss a licence for your team.
Request a demo Logistics 4ร4 โ โ Back to overview