askimo

AI desktop app for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)

What is askimo?

AI desktop app for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)

Overview of askimo

What it is

Askimo is a native desktop application for interacting with multiple AI models. It supports chat, retrieval-augmented generation (RAG) on local files, skills, MCP tools, and autonomous agents. The app is designed to keep all user data—files, RAG index, conversation history, and telemetry—on the local machine. Network calls are only made to the AI providers the user configures.

Key features

  • Multi-provider support: switch between OpenAI, Claude, Gemini, Grok, Ollama, LM Studio, Docker AI, OpenRouter, NVIDIA NIM, Together AI, vLLM Server, or any OpenAI-compatible endpoint per session - Local RAG: index local folders, files, and web URLs using hybrid BM25 + vector retrieval with an AI classifier that skips retrieval when unnecessary; data never leaves the machine - Plans (agentic workflows): chain multi-step AI pipelines from a form UI, with live progress display and export to PDF or Word; plans can be defined in YAML or generated from plain English - MCP tool integration: connect MCP-compatible servers via stdio or HTTP - AI agent CLI integration: delegate goals to Claude Code, OpenAI Codex, or Google Antigravity directly from the app; define reusable skills that materialize into any supported agent's skill-discovery folder - Voice input/output: dictate messages via OpenAI's transcription API or a fully local Whisper engine; have responses read aloud via OpenAI's TTS API or a local Piper endpoint, with optional auto-play for hands-free conversation mode - Persistent sessions and local telemetry: conversations stored in a local SQLite database and restored on restart; token usage, cost estimates, and RAG performance tracked locally and never uploaded

Use cases

  • Chatting with multiple AI models in a single application without switching browser tabs - Searching local files and the web using RAG and multiple web search backends (DuckDuckGo, Brave Search API, Tavily, Serply, SearxNG)
  • Running Python, Bash, and JavaScript scripts directly from chat, with automatic dependency management - Building multi-step AI workflows (Plans) for tasks such as document analysis or report generation - Executing autonomous coding agents (Claude Code, Codex, Antigravity) by delegating goals and monitoring live tool calls - Using voice to dictate messages and hear responses, with fully offline speech-to-text and text-to-speech options

Getting started

Download the app for macOS, Windows, or Linux from the project website. After installation, add a provider by pasting an API key (for OpenAI, Claude, Gemini, etc.) or pointing to a running Ollama instance, then start chatting. To build from source: bash git clone https://github.com/askimo-ai/askimo.git cd askimo # Run the desktop app ./gradlew :desktop:run # Build native installers ./gradlew :desktop:package

License and pricing

The project is licensed under AGPL-3.0 and is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/askimo-aiaskimo.svg)](https://yunodb.com/tools/askimo-aiaskimo?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/askimo-aiaskimo?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/askimo-aiaskimo.svg" alt="Featured on YunoDB" height="20"></a>