Local-first AI agent platform for desktop and CLI. Chat, RAG search, multi-step Plans workflows, MCP tools, and script runner. Supports OpenAI, Claude, Gemini, Grok, Ollama, LM Studio and more
You shouldn't have to choose between the best AI model, your privacy, and getting real work done.
One app, every model. Stop juggling browser tabs. Chat with OpenAI, Claude, Gemini, Grok, or a local Ollama model, switch in seconds, no copy-pasting.
Built as a native desktop app. Not a web wrapper. Starts fast, runs lean, and stays responsive even after hours of use and thousands of messages in a single conversation.
Long conversations that actually work. No crashes, no tab reloads, no lost context. Askimo handles deep, extended sessions the way a real desktop app should.
Your files stay on your machine. Search and chat with your own documents using local RAG. Nothing is uploaded. Nothing leaves your device.
More than just chat. Run Python/Bash scripts, chain multi-step AI workflows, and connect MCP tools, all from the same app.
See It in Action
Multi-step AI Plans - fill in a form, get a finished deliverable:
RAG - search and chat with your local files:
Script runner - execute Python, Bash, and JavaScript from chat:
| | |
|---|---|
| OS | macOS 11+, Windows 10+, Linux (Ubuntu 20.04+, Debian 11+, Fedora 35+) |
| Memory | 50–300 MB (AI models require additional memory depending on provider) |
| Disk | 250 MB |
Features
Multi-provider - Switch between OpenAI, Claude, Gemini, Grok, Ollama, LM Studio, LocalAI, Docker AI, or any OpenAI-compatible endpoint per session
Local RAG - Index local folders, files, and web URLs. Hybrid BM25 + vector retrieval with an AI classifier that skips retrieval when the query doesn't need it. Your data never leaves your machine.
Plans (agentic workflows) - Chain multi-step AI pipelines from a form UI. Each step builds on the previous; progress shown live. Export as PDF or Word. Define your own plans in YAML or generate them by describing your workflow in plain English.
Script runner - Execute Python, Bash, and JavaScript from chat. Python runs in an auto-managed virtualenv with automatic dependency installation.
MCP tool integration - Connect MCP-compatible servers via stdio or HTTP, scoped globally or per project
Persistent sessions - Conversations stored in a local SQLite database, restored on restart
Vision - Attach images to conversations; works with any multimodal model
A single prompt cannot reason properly across multiple stages. Ask one prompt to research, analyse, and conclude simultaneously and the AI skips the dependencies between those stages.
Plans mirror how experts actually think: each step has one focused job and one persona - researcher, analyst, strategist, writer. The output of each step feeds into the next as grounded context. No copy-pasting. No re-prompting.
Built-in plans:
| Plan | What it does |
|---|---|
| 💼 Job Application Writer | Analyses a job description, matches your CV, writes a tailored cover letter and ATS-optimised resume |
| ✍️ Blog Post Writer | Generates an outline, writes the full draft, adds SEO metadata, outputs the polished post |
| 🏆 Competitor Analysis | Profiles a competitor, compares against your product, produces a strategic opportunities report |
| 📋 Meeting Notes Processor | Structures raw notes, extracts action items with owners, produces shareable minutes |
| 📝 Research Report | Researches a topic and writes a structured report with executive summary and key findings |
| 📧 Email Writer | Drafts and self-refines a professional email from a one-line description |
Create your own: describe your workflow in plain English - the AI generates valid plan YAML instantly. Fine-tune in the built-in editor or duplicate any built-in plan as a starting point.
Supported Providers
Cloud: OpenAI · Anthropic Claude · Google Gemini · xAI Grok Local: Ollama · LM Studio · LocalAI · Docker AI Custom: Any OpenAI-compatible endpoint via custom base URL
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
