klyro 1.0.4

Klyro is AI pair programming in your terminal

 ██╗  ██╗██╗  ██╗   ██╗██████╗  ██████╗
 ██║ ██╔╝██║  ╚██╗ ██╔╝██╔══██╗██╔═══██╗
 █████╔╝ ██║   ╚████╔╝ ██████╔╝██║   ██║
 ██╔═██╗ ██║    ╚██╔╝  ██╔══██╗██║   ██║
 ██║  ██╗███████╗██║   ██║  ██║╚██████╔╝
 ╚═╝  ╚═╝╚══════╝╚═╝   ╚═╝  ╚═╝ ╚═════╝

AI pair programming in your terminal.

Klyro talks to your code. You talk to Klyro.
Works with GPT-4o, Claude, Gemini, DeepSeek, Ollama, Grok, Groq, Mistral — and 100+ more.

Quick Start · Features · Models · Commands · Config · Changelog

---

⚡ Quick Start

pip install klyro

# Run with your API key set
klyro

# Or specify a model directly
klyro --model gpt-4o
klyro --model ollama/llama3.2
klyro --model gemini/gemini-2.5-flash

Windows: If klyro is not recognized, either run python -m klyro or add your Scripts folder to PATH:

python -c "import sysconfig; print(sysconfig.get_path('scripts', 'nt_user'))"

Install from source:

git clone https://github.com/RavindraTirlangi/Klyro.git
cd Klyro
pip install -e .

---

✨ Features

🤖 Smart Model Detection Auto-detects your environment at startup: Local Ollama running? Uses it instantly — no API key needed Cloud keys set? Picks the best available model Nothing configured? Guides you through OpenRouter setup (free tier available)	🗺️ Repository Intelligence Understands your entire codebase: Builds a repo map using tree-sitter AST analysis Identifies relevant files automatically Manages context to stay within token limits
✏️ Precise Code Editing Applies changes surgically: Whole-file and diff-based editing modes Auto-lints after every edit and feeds errors back Built-in git integration with descriptive auto-commits	🔀 Model Switching On-the-Fly Switch any time without restarting: /model flash → Gemini 2.5 Flash /model r1 → DeepSeek R1 /model groq-llama → Groq (ultra-fast) /model list → see all options

---

🧠 Supported Models

Switch models inside Klyro using /model <alias>:

Provider	Alias	Model
Anthropic	claude / sonnet	claude-sonnet-4-6 ⭐ latest
	opus	claude-opus-4-7 — most capable
	haiku	claude-haiku-4-5 — fastest
OpenAI	4o	gpt-4o ⭐ recommended
	4o-mini	gpt-4o-mini — cheapest
	o1 / o3-mini	reasoning models
Google	gemini	gemini-2.5-pro ⭐ recommended
	flash	gemini-2.5-flash — fast & cheap
	flash-lite	gemini-2.5-flash-lite
DeepSeek	deepseek	deepseek-chat (v3)
	r1	deepseek-reasoner — best reasoning
Mistral	mistral	mistral-large-latest
	codestral	codestral-latest — code specialist
	pixtral	pixtral-large — vision
Ollama (local)	llama / llama3.2	ollama/llama3.2 — no API key
	qwen	ollama/qwen2.5-coder
	phi4	ollama/phi4
	devstral	ollama/devstral — code expert
xAI	grok / grok3	xai/grok-3-beta
	grok3-mini	xai/grok-3-mini-beta
Groq	groq-llama	llama-3.3-70b-versatile — ultra-fast
	groq-mixtral	mixtral-8x7b-32768
	groq-gemma	gemma2-9b-it
OpenRouter (free)	llama-free	llama-3.1-8b-instruct:free
	deepseek-free	deepseek-r1-0528:free
	gemma-free	gemma-3-27b-it:free
	qwen-free	qwen3-235b-a22b:free
AWS Bedrock	bedrock-claude	anthropic.claude-3-5-sonnet-v2
Azure OpenAI	azure-gpt4o	azure/gpt-4o
Cohere	command	cohere/command-r-plus

Run /model list inside Klyro to see all 90+ aliases.

---

💬 Slash Commands

Command	Description
/model [name]	Switch model mid-session — /model list to browse all providers
/stats	Show current model, last message cost, and total session cost
/web <url>	Scrape a webpage and add its content to the chat
/export [file]	Export full chat history to a Markdown file
/add <file>	Add a file to the chat context
/drop <file>	Remove a file from the chat context
/diff	Show the diff of changes made in this session
/undo	Undo the last AI commit
/tokens	Report token usage for current context
/git <cmd>	Run any git command
/run <cmd>	Run a shell command and add output to chat
/clear	Clear the chat history
/help	Show all available commands

---

⚙️ Configuration

Create .klyro.conf.yml in your project root:

model: ollama/llama3.2   # default model
dark-mode: true
auto-commits: true

Or use environment variables:

# Cloud providers
export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...
export GEMINI_API_KEY=...
export DEEPSEEK_API_KEY=...
export MISTRAL_API_KEY=...
export XAI_API_KEY=...
export GROQ_API_KEY=...
export OPENROUTER_API_KEY=sk-or-...

# Local
export OLLAMA_API_BASE=http://localhost:11434

---

📦 Release

Tagged releases automatically publish to PyPI via GitHub Actions:

git tag v1.0.3
git push origin v1.0.3

See CHANGELOG.md for full version history.

---

📄 License

Apache License 2.0 — see LICENSE for details.

---

Made with ❤️ · PyPI · GitHub · Changelog