KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #ai-agents #dsh-plugin #codex #developer-tools #claude-code #windows #desktop-app #typescript #rust #ai-agent #cli

clai

★ 146 Open GitHub ↗

Command line artificial intelligence - Context engineering for terminal powerusers

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Command Line Artificial Intelligence

![Wakatime](https://wakatime.com/badge/user/018cc8d2-3fd9-47ef-81dc-e4ad645d5f34/project/018e07e1-bd22-4077-a213-c16290d3db52.svg)

Test coverage: 71.795% 😌👏

<hr>
<div align="center">
  <p><code>clai</code> (<i>/klaɪ/</i>, like "cli" in "<b>cli</b>mate") is a command line context-feeder for any ai task.</p>
</div>

## Get started

Installing:

```bash
curl -fsSL https://raw.githubusercontent.com/baalimago/clai/main/setup.sh | sh
```

You can also install via go:

```bash
go install github.com/baalimago/clai@latest
```

Then run:

```bash
clai help | clai query Please give a concise explanation of clai
```

Either look at `clai help` or the [examples](./EXAMPLES.md) for how to use `clai`.
If you have time, you can also check out [this blogpost](https://lorentz.app/blog-item.html?id=clai) for a slightly more structured introduction on how to use Clai efficiently.

Install [Glow](https://github.com/charmbracelet/glow) for formatted markdown output when querying text responses.

## Features

- **[Shell context injection](./architecture/shell-context.md)** - Inject shell context into the system prompt via configurable templates.
- **[Seamless conversation import](./architecture/continue-from-claudex.md)** - Ran out of session? Continue in clai!
- **[Agent Skills](./architecture/skills.md)** - Import skills from custom global directories, or project-level `.agents/skills`.
- **[Profiles](./EXAMPLES.md#profiles--workflow-presets)** - Pre-prompted profiles enabling customized workflows and agents.
- **[MCP client support](./EXAMPLES.md#mcp-tools-external-tool-servers)** - Add any MCP server you'd like by simply pasting their configuration.
- **Unix-like** - Clai follows the [unix philosophy](https://en.wikipedia.org/wiki/Unix_philosophy) and works seamlessly with data piped in and out.

All of these features are easily combined and tweaked, empowering users to accomplish very diverse use cases.
See [examples](./EXAMPLES.md) for additional info.

## Supported vendors

| Vendor      | Environment Variable | Models                                                                                                                                                             |
| ----------- | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Berget AI   | `BERGET_API_KEY`     | [Text models](https://berget.ai/models), use prefix `berget:`                                                                                                      |
| OpenRouter  | `OPENROUTER_API_KEY` | [Text models](https://openrouter.ai/models), use prefix `or:`                                                                                                      |
| Mistral     | `MISTRAL_API_KEY`    | [Text models](https://docs.mistral.ai/getting-started/models/)                                                                                                     |
| OpenAI      | `OPENAI_API_KEY`     | [Text models](https://platform.openai.com/docs/models), [photo models](https://platform.openai.com/docs/models/dall-e)                                             |
| Anthropic   | `ANTHROPIC_API_KEY`  | [Text models](https://platform.claude.com/docs/en/about-claude/models/overview)                                                                                    |
| Gemini      | `GEMINI_API_KEY`     | [Text models](https://ai.google.dev/gemini-api/docs/models), [photo models](https://ai.google.dev/gemini-api/docs/image-generation#image_generation_text-to-image) |
| HuggingFace | `HF_API_KEY`         | [Text models](https://huggingface.co/docs/inference-endpoints/chat-completions), use prefix `hf:`                                                                  |
| xAi         | `XAI_API_KEY`        | [Text models](https://docs.x.ai/docs/models)                                                                                                                       |
| Inception   | `INCEPTION_API_KEY`  | [Text models](https://platform.inceptionlabs.ai/docs#models)                                                                                                       |
| Ollama      | N/A                  | Use format `ollama:` (defaults to llama3), server defaults to localhost:11434                                                                                      |

---

Shell completions are also available:

```bash
# bash
mkdir -p ~/.local/share/bash-completion/completions
clai completion bash > ~/.local/share/bash-completion/completions/clai
```

```bash
# zsh
mkdir -p ~/.zsh/completions
clai completion zsh > ~/.zsh/completions/_clai
```

For zsh, ensure your `fpath` includes the completions directory before `compinit`, for example:

```bash
fpath=(~/.zsh/completions $fpath)
autoload -Uz compinit && compinit
```

Then restart your shell or reload your shell configuration.

clai

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README