kunji (कुंजी)

Name: kunji
Author: testwithsuraj

Every AI model in one terminal, with your own keys. See what every answer costs.

pip install kunji

Website · Documentation · Install · Commands · Kunji (कुंजी) means "key" in Hindi.

Kunji is a terminal app for chatting with any AI model using your own API keys.
You pay each provider directly. Kunji never sees your bill, your keys or your prompts.

Why kunji

One tool, every provider. OpenAI, Anthropic, Google Gemini, Groq, OpenRouter,
DeepSeek, Mistral, xAI, Together, Ollama (local), plus any OpenAI-compatible server.
Switch models mid-conversation with /model — the conversation carries over.
Live cost meter. Every reply shows tokens and cost. /cost and kunji usage
show totals, in your currency.
Daily budgets. Warns at 80%, blocks at 100%, per provider or overall.
Compare mode. One prompt, several models, side by side — fastest and cheapest highlighted.
Automatic fallback. Rate-limited or down? Kunji retries on your next model.
Keys in your OS keychain (Windows Credential Manager, macOS Keychain, Secret Service),
never in a plain-text file.
Pipes. npm test 2>&1 | kunji ask "why is this failing?"
Saved prompts. kunji @commit writes a commit message from your staged changes;
@explain, @review, @fix, @summarize, @translate, @tests — or make your own.
Chat history. Every chat is saved on your computer. Continue with kunji chat -c,
search with kunji history search.
Attach files. /file app.py in chat, or kunji ask -f app.py "what does this do?".
Menu or commands. Run kunji for an arrow-key menu that stays open until you exit;
every action is also a command for scripts.
Looks professional. Minimal monochrome design, responsive to any terminal size.

Install

Requires Python 3.11+.

pip install kunji

If pip isn't found or shows an error, run it through Python instead:

System	Command
Windows	`python -m pip install kunji` (or `py -m pip install kunji`)
macOS	`python3 -m pip install kunji`
Linux	`python3 -m pip install --user kunji` (if it says "externally managed", use `pipx install kunji`)

No Python on Windows? Download kunji-windows-x64.exe from the
latest release and run it from a terminal.
Linux: kunji-linux-x64.

Update later with pip install -U kunji. If the kunji command isn't found after installing,
python -m kunji always works.

winget, Scoop and Homebrew packages are on the roadmap.

Quick start

kunji                     # opens the menu: add a provider, then start a chat

Prefer commands? kunji keys add, then kunji chat.

Free and local? Install Ollama, then kunji keys add ollama.

Commands

Command	What it does
`kunji`	Interactive menu (stays open until you choose Exit)
`kunji chat`	Chat (`-m provider:model`, `-s "system prompt"`, `-c` continue last, `--resume <id>`)
`kunji ask "…"`	One-shot answer. Reads piped input. `-f file` to attach, `--raw` for scripts
`kunji @name "…"`	Run a saved prompt, e.g. `kunji @commit`, `git diff \| kunji @review`
`kunji prompts`	List prompts; `add`, `edit`, `show`, `remove` your own
`kunji history`	Saved chats; `search`, `show`, `export`, `delete`
`kunji compare "…" -m a -m b`	Same prompt to several models, side by side
`kunji keys add [provider]`	Add or replace a key (verified, then saved to the keychain)
`kunji keys list` / `test` / `remove`	Manage keys (always masked)
`kunji models [provider]`	Live model list with prices
`kunji use provider:model`	Set your default model
`kunji providers`	Supported providers; `providers add` for custom servers
`kunji usage`	Tokens and cost per model (stored locally only)
`kunji budget set <provider\|all> <amount>`	Daily spending limit
`kunji config show` / `set` / `path`	Settings
`kunji doctor`	Check Python, config, keychain and providers

In chat

Input	Action
`/help`	Show commands and shortcuts
`/model provider:model`	Switch model (tab completes)
`/models [filter]`	List models of the current provider
`/cost`	Session and today's cost
`/file path`	Attach a text file to your next message (tab completes paths)
`@name text`	Use a saved prompt, e.g. `@explain this error`
`/prompts` · `/history`	List saved prompts · recent chats
`/system …`	Set the system prompt
`/retry` · `/new` / `/clear` · `/save [file]`	Regenerate · new conversation · export markdown
`/copy`	Copy the latest assistant response to the clipboard
`/exit` · `/quit` · `/q`	Leave the chat
`enter` · `alt+enter` / `ctrl+j`	Send · new line
`ctrl+c` · `ctrl+d`	Stop the reply · quit

Providers

ID	Provider	Key env variable
`openai`	OpenAI	`OPENAI_API_KEY`
`anthropic`	Anthropic	`ANTHROPIC_API_KEY`
`gemini`	Google Gemini	`GEMINI_API_KEY` / `GOOGLE_API_KEY`
`groq`	Groq	`GROQ_API_KEY`
`openrouter`	OpenRouter	`OPENROUTER_API_KEY`
`deepseek`	DeepSeek	`DEEPSEEK_API_KEY`
`mistral`	Mistral	`MISTRAL_API_KEY`
`xai`	xAI	`XAI_API_KEY`
`together`	Together AI	`TOGETHER_API_KEY`
`ollama`	Ollama (local)	none

Any OpenAI-compatible server (LM Studio, vLLM, LiteLLM proxy…):

kunji providers add lmstudio --base-url http://localhost:1234/v1 --no-key

Security and privacy

API keys are stored only in your operating system's credential store, or read from
environment variables. They are sent only to the provider they belong to.
Kunji's config file never contains keys. Errors are scrubbed so keys never appear on screen.
Usage and cost history stay on your machine (kunji config path).
Network calls kunji makes on its own: the public model price list (OpenRouter, plus this
repo's catalog/pricing.json) and the PyPI version check. Neither sends anything about you.
Turn them off with kunji config set network.catalog false and
kunji config set updates.check false.
Found a vulnerability? Please follow SECURITY.md.

Details: docs/PRIVACY.md.

Configuration

kunji config set display.currency INR
kunji config set display.usd_rate 84          # your conversion rate
kunji budget set all 200                      # ₹200/day across every provider
kunji config set fallback '["groq:llama-3.3-70b-versatile", "ollama:qwen2.5"]'

All options: docs/CONFIG.md. Every command with examples: docs/COMMANDS.md. Full documentation: testwithsuraj.github.io/kunji/docs.

Free and Pro

Everything that runs on your machine is free and open source, forever — chat,
switching, keys, cost meter, budgets, compare, fallback, pipes. A future optional
Pro plan will add cloud features that need a server (sync across devices, shared team
keys with per-person budgets, a smart router). See ROADMAP.md.