Serious work. Fully local.
Artha is a local-first AI workspace that generates documents, indexes your files, and runs agents — all on your hardware. No cloud calls. No accounts. No telemetry.
An AI workspace that earns trust.
Every capability built around a single rule: your files, prompts, embeddings, and model outputs never leave the machine they were generated on.
Native artifacts
Generate Word, Excel, PowerPoint, and PDF files from natural language. Every artifact stays on your machine.
MCP-native
Any Model Context Protocol server becomes a skill your agent can use. Bring your own integrations.
Local RAG
Index folders with Ollama embeddings. Search, cite, and chat with your files — no cloud.
Ollama-first
Auto-detect installed models, pull new ones, and switch between Llama, Mistral, Qwen, and more.
Zero telemetry
No accounts. No tracking. No background phone-home. The binary is auditable.
Sandboxed tools
Optional Docker sandbox for untrusted tools. Run agents without giving them your shell.
Before your first launch.
Three things worth knowing.
- 01
Requires Ollama running locally.
We recommend
llama3.2:3b-instruct-q4_K_Mto start — fits in 8 GB of RAM and is fast on most laptops. - 02
Installers are currently unsigned.
On macOS, right-click the app and choose Open. On Windows, click “More info” → “Run anyway”. Signed builds are on the roadmap.
- 03
The binary is open source and auditable.
Run it as a black box, or build from source — your call.