{"slug": "show-hn-clai-context-engineering-for-terminal-powerusers", "title": "Show HN: Clai – Context engineering for terminal powerusers", "summary": "Developer baalimago released Clai, a command-line context feeder for AI tasks that supports multiple LLM vendors and MCP servers. The tool follows Unix philosophy, enabling piped data workflows, conversation management, and customizable profiles for power users.", "body_md": "Test coverage: 68.860% 😌👏\n\n`clai`\n\n(*/klaɪ/*, like \"cli\" in \"**cli** mate\") is a command line context-feeder for any ai task.\n\nInstalling:\n\n```\ncurl -fsSL https://raw.githubusercontent.com/baalimago/clai/main/setup.sh | sh\n```\n\nYou can also install via go:\n\n```\ngo install github.com/baalimago/clai@latest\n```\n\nThen run:\n\n```\nclai help | clai query Please give a concise explanation of clai\n```\n\nEither look at `clai help`\n\nor the [examples](/baalimago/clai/blob/main/EXAMPLES.md) for how to use `clai`\n\n.\nIf 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.\n\nInstall [Glow](https://github.com/charmbracelet/glow) for formatted markdown output when querying text responses.\n\n- Add any MCP server you'd like by simply pasting their configuration.[MCP client support](/baalimago/clai/blob/main/EXAMPLES.md#mcp-tools-external-tool-servers)**Vendor agnosticism**- Use any functionality in Clai with[most LLM vendors](#supported-vendors)interchangeably.- Create, manage and continue conversations.[Conversations](/baalimago/clai/blob/main/EXAMPLES.md#bind-a-previous-conversation-to-the-current-directory)- Pre-prompted profiles enabling customized workflows and agents.[Profiles](/baalimago/clai/blob/main/EXAMPLES.md#profiles--workflow-presets)**Unix-like**- Clai follows the[unix philosophy](https://en.wikipedia.org/wiki/Unix_philosophy)and works seamlessly with data piped in and out.\n\nAll of these features are easily combined and tweaked, empowering users to accomplish very diverse use cases.\nSee [examples](/baalimago/clai/blob/main/EXAMPLES.md) for additional info.\n\n| Vendor | Environment Variable | Models |\n|---|---|---|\n| Berget AI | `BERGET_API_KEY` |\n`berget:` |\n\n`OPENROUTER_API_KEY`\n\n[Text models](https://openrouter.ai/models), use prefix`or:`\n\n`MISTRAL_API_KEY`\n\n[Text models](https://docs.mistral.ai/getting-started/models/)`OPENAI_API_KEY`\n\n[Text models](https://platform.openai.com/docs/models),[photo models](https://platform.openai.com/docs/models/dall-e)`ANTHROPIC_API_KEY`\n\n[Text models](https://platform.claude.com/docs/en/about-claude/models/overview)`GEMINI_API_KEY`\n\n[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)`HF_API_KEY`\n\n[Text models](https://huggingface.co/docs/inference-endpoints/chat-completions), use prefix`hf:`\n\n`XAI_API_KEY`\n\n[Text models](https://docs.x.ai/docs/models)`INCEPTION_API_KEY`\n\n[Text models](https://platform.inceptionlabs.ai/docs#models)`ollama:`\n\n(defaults to llama3), server defaults to localhost:11434Shell completions are also available:\n\n```\n# bash\nmkdir -p ~/.local/share/bash-completion/completions\nclai completion bash > ~/.local/share/bash-completion/completions/clai\n# zsh\nmkdir -p ~/.zsh/completions\nclai completion zsh > ~/.zsh/completions/_clai\n```\n\nFor zsh, ensure your `fpath`\n\nincludes the completions directory before `compinit`\n\n, for example:\n\n```\nfpath=(~/.zsh/completions $fpath)\nautoload -Uz compinit && compinit\n```\n\nThen restart your shell or reload your shell configuration.", "url": "https://wpnews.pro/news/show-hn-clai-context-engineering-for-terminal-powerusers", "canonical_source": "https://github.com/baalimago/clai", "published_at": "2026-06-24 09:32:54+00:00", "updated_at": "2026-06-24 09:44:38.124034+00:00", "lang": "en", "topics": ["developer-tools", "ai-tools", "large-language-models", "ai-infrastructure"], "entities": ["baalimago", "Clai", "OpenAI", "Anthropic", "Google", "Mistral", "Hugging Face", "OpenRouter"], "alternates": {"html": "https://wpnews.pro/news/show-hn-clai-context-engineering-for-terminal-powerusers", "markdown": "https://wpnews.pro/news/show-hn-clai-context-engineering-for-terminal-powerusers.md", "text": "https://wpnews.pro/news/show-hn-clai-context-engineering-for-terminal-powerusers.txt", "jsonld": "https://wpnews.pro/news/show-hn-clai-context-engineering-for-terminal-powerusers.jsonld"}}