AI Agent in Your Terminal

Write, edit, debug, and ship code with AI — powered by local models (Ollama) or cloud APIs. Zero telemetry. Your code stays yours.

Download Roncon Code

Detecting your OS...

Download

v0.3.0 — standalone binary, no Python required

macOS: After download, open Terminal and run: xattr -cr ~/Downloads/roncon-code*

Other Platforms

macOS (Apple Silicon) macOS (Intel) Linux (x64) Windows (x64)
roncon-code — ~/project
$ roncon-code --model ollama:qwen2.5:7b [AdaptiveProfile] Level: LIGHT (7 tools, Metal GPU, 8.7GB free) [ModelFallback] Chain: ollama:qwen2.5:7b [PrivacyGuard] Active — all telemetry DISABLED Ready to code. What would you like to build? > Fix the bug in auth.py and add tests Reading auth.py... Found issue: missing null check on line 42 Editing auth.py: replaced 1 occurrence Creating test_auth.py (234 chars, 12 lines) Running: pytest test_auth.py All tests passing. Bug fixed. > /cost Session: 0 tokens | $0.00 (local model — free)

Features

🔍

Adaptive Profiles

Auto-detects GPU, RAM, and model size. Adjusts tool complexity to match your hardware — from MINIMAL (3 tools) to FULL (all tools).

🔄

Model Fallback

Cloud API hits rate limit? Auto-switches to local Ollama. Re-adapts tool descriptions for the new model. Zero downtime.

🔒

Privacy Guard

Zero telemetry by default. All LangSmith tracing blocked at code level. Your data never leaves your machine.

💰

Cost Tracking

Real-time token usage and cost per provider. Free with Ollama, from $0.14/M tokens with cloud APIs.

🛡

Permission System

Blocks dangerous operations: rm -rf, git push --force, DROP TABLE. Configurable patterns and sensitive paths.

📡

Live Model Registry

Polls Ollama every 30s. New model pulled? Auto-discovered. Model removed? Auto-disposed. All in real-time.

⌘

53 CLI Commands

/model, /adaptive, /fallback, /registry, /privacy, /providers, /doctor, /benchmark, and 45 more.

🧪

694 Tests

100% coverage on all custom middleware. 29 eval scenarios across 4 categories. Battle-tested.

🌐

Multi-Provider

Ollama, Groq, DeepInfra, Together, OpenRouter, Anthropic, OpenAI — switch with one flag.

Cost Comparison

Setup Monthly Cost Quality Privacy
Roncon Code + Ollama $0 (free) Good (7B local) 100% local
Roncon Code + DeepInfra ~$22/mo Very Good (72B) API only
Roncon Code + Groq ~$37/mo Good (70B, fast) API only
Claude Code (Anthropic) $100-200/mo Excellent Cloud
GitHub Copilot $19/mo Good Cloud