Askimo.chat — AI for your workflows

One CLI to Talk, Think, and Automate.

Askimo automating AI workflows — summarizing files, generating commit messages, and integrating seamlessly with Git.

Features

AI Chat

Talk naturally with multiple AI providers — OpenAI, Gemini, Anthropic, Ollama, and X AI — all from one CLI. Control tone and precision with custom system messages and switch models instantly.

Knowledge Management

Give AI full awareness of your work. Askimo’s RAG-enabled projects automatically index documents, code, and notes using PostgreSQL + pgvector, so answers are always contextual and grounded in your data.

Automation & DevOps

Turn your commands into intelligent workflows. Define reusable recipes for repetitive tasks, run Askimo in non-interactive mode for CI/CD, and use AI for log analysis and monitoring — all pipeline-ready.

Platform & Extensibility

A provider-agnostic architecture built for flexibility. Add custom plugins, fine-tune per-provider parameters, and integrate Askimo seamlessly into your toolchain.

Built for Developers

Fast, portable, and secure — powered by GraalVM. Askimo runs anywhere, locally or remotely, giving teams full control and reproducibility over their AI workflows.

How it works

1. Install Askimo

macOS / Linux

Requires: Homebrew

brew tap haiphucnguyen/askimo
brew install askimo

Don’t have Homebrew?

Install it with:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Windows

Requires: Scoop

scoop bucket add askimo https://github.com/haiphucnguyen/scoop-askimo
scoop install askimo

Don’t have Scoop?

Install it with PowerShell:

Set-ExecutionPolicy -Scope CurrentUser RemoteSigned -Force
iwr -useb get.scoop.sh | iex

See all installation methods

2. Configure your AI provider

askimo --set-provider openai --set-param api_key <your-openai-key>

3. Run Askimo

askimo -r summarie <any text file>

Why developers love Askimo

No vendor lock-in: switch OpenAI / Gemini / Anthropic / X AI / Ollama instantly
Works locally or remote; CI/CD-friendly non-interactive mode
RAG projects with pgvector keep responses grounded in your docs & code
Flexible recipes turn repeated steps into one command

Integrations & extensibility

Provider-agnostic: OpenAI, Gemini, Anthropic, X AI, Ollama
Plugin system for custom providers and commands
Per-provider config & parameter tuning
Pipes via stdin/stdout; great for shell scripts and CI/CD