14 posts
Askimo's new built-in Local LLM provider downloads a platform-matching llama-server binary and lets you browse, search, and download GGUF chat and embedding models straight from Hugging Face. One toggle, one model picker, zero extra installs: Ollama and LM Studio become optional, not required.
Read Full Article
Askimo 1.5.4 brings local LLM engine support and full voice capabilities powered by Whisper - live transcription, text-to-speech, and cancellable downloads - plus smarter inline suggestions and a round of desktop reliability fixes.
Read Full Article
Askimo 1.5 adds Agents: a single interface for running Claude Code, Antigravity CLI, or Codex CLI directly against your local project files - reading, writing, and executing with your review. Reusable Skills, GitHub and ZIP imports, and autonomous skill selection mean you describe a goal once and Askimo figures out which capability applies. Here is how it works and how it fits alongside Askimo Plans.
Read Full Article
Askimo 1.4.8 gives you direct control over AI reasoning quality with configurable Reasoning Effort levels and per-model support. Anthropic prompt caching speeds up repeated queries, while drag-and-drop file attachments make it easier to share context. New font settings, accent color palettes, and spacing improvements create a more polished and personalized interface. Token usage tracking and a system diagnostics dialog improve visibility into how Askimo is running.
Read Full Article
Askimo App provides an Ollama GUI for running local AI models like Llama 3.3, DeepSeek R1, Mistral, Gemma 3, Qwen 2.5, and Phi-4. Features persistent history, in-chat search, starred conversations, and export options. Project-aware RAG enables chatting with your codebase or documents using local models with complete privacy. Switch seamlessly between Ollama and cloud providers. Includes lazy loading, custom directives, and automatic endpoint detection.
Read Full Article
Askimo's Script Runner makes AI-generated code actually useful. Run Python, Bash, or Node.js scripts directly inside the app, view real stdout output instantly, and iterate faster without copy-pasting into a terminal. Great for data processing, log analysis, small automations, and reproducible workflows - all local, all private.
Read Full Article
New in Askimo: built-in terminal emulator, Model Context Protocol (MCP) integration, a RAG sources tree to inspect exactly what the assistant used, image-model support for multimodal workflows, and major desktop improvements across performance, reliability, and UX.
Read Full Article
Askimo App provides a powerful GUI client for Docker Model Runner, Docker's official feature for running AI models locally with OpenAI-compatible endpoints. Features persistent history, in-chat search, starred conversations, and export options. Project-aware RAG enables chatting with your codebase using local Docker AI models with complete privacy. Switch seamlessly between Docker Model Runner and cloud providers.
Read Full Article
Askimo 1.2.0 introduces project-based RAG for answering questions using your documents with jvector and Apache Lucene search. Attach PDFs, spreadsheets, images, or code directly in conversations. Docker AI support joins OpenAI, Claude, Gemini, and Ollama. Enhanced project sessions organize knowledge-based chats. Responsive design works across all screen sizes. macOS installer now fully notarized for secure installation.
Read Full Article
Major Askimo App update adds multilingual support for 10+ languages including English, Vietnamese, Chinese, Japanese, Korean, French, German, Spanish, Portuguese, and Italian. Introduces 18 themes with light, dark, and system-adaptive options. New developer tools include real-time resource monitoring, enhanced debugging, and granular log controls. Significant performance improvements especially on Windows, plus better error handling across all platforms.
Read Full Article
Askimo protects data through AES-256-GCM encryption, local-only storage, and zero cloud dependency. API keys are encrypted before disk storage, never in plain text. macOS uses system Keychain; other platforms use secure local encryption with strict permissions. No files uploaded to external servers or background analytics. Communication only happens with AI services you configure. Conversations, keys, and preferences stay on your machine.
Read Full Article
Askimo v1.0 launches the Desktop app with intelligent lazy loading for responsive long conversations, full-text search across entire chat history, and custom directives for consistent AI behavior. Features include theme customization, keyboard shortcuts, folder organization, and starred discussions. Supports OpenAI, Claude, Gemini, and Ollama. Open-source and built for productivity-focused users needing multiple AI models chat without browser limitations.
Read Full Article
Askimo App complements the CLI for interactive AI work. Switch between OpenAI, Claude, Gemini, and Ollama in one session without separate browser tabs. The app maintains your workspace and conversation context when switching providers. Start with OpenAI, jump to Gemini, or use local Ollama models seamlessly. Features offline support, secure storage, and native cross-platform performance for unified AI workflows.
Read Full Article
Askimo originated from developer frustration with fragmented AI tools. Created as a unified CLI for OpenAI, Ollama, and other providers, it became a daily-use command-line assistant for summarizing documents, writing drafts, and development tasks. Works everywhere via Homebrew, binaries, or Docker. Supports local context for project questions and seamless provider switching. Emphasizes reusable prompts and command recipes for DevOps automation.
Read Full Article
