Introduction
Vaner is a local-first preparation engine that turns idle compute into evidence-backed Prepared Work for your AI client.
Vaner is a local-first preparation engine for AI workflows. It runs beside your AI client, watches the project you've scoped to, and uses idle compute to prepare evidence-backed work (review notes, bug hypotheses, docs drift, virtual diffs, research briefs, ready drafts) before you ask. When the real question arrives, your client gets the best fit quickly instead of starting from a cold retrieval pass.
Prepared Work is non-mutating by default. Vaner can prepare a virtual diff but will not apply it or edit your files unless you explicitly export or adopt it.
Install Vaner
Download Vaner Desktop
Recommended for everyone on macOS, Windows, and Linux. Installs the human-facing Vaner app and wires Vaner into your AI clients.
Install the CLI
For power users, CI, and Docker. One-line installer for Linux and macOS. Same engine as the desktop app.
What's next
Get started
Install, init, run.
Prepared Work
What Vaner produces and how to inspect it.
Connect your AI client
Wire Vaner into Claude Code, Cursor, Zed, and 7 other clients.
Configuration
Knob reference for advanced setups.
Why Vaner
Vaner is successful when it improves at least one of:
- Answer quality. Your agent's first reply is grounded in actual evidence, not generic recall.
- Prompt-time latency. Work is prepared in advance; the agent picks it up when you ask.
- Cost per good answer. Local idle compute substitutes for cloud round-trips on routine paths.
Model-agnostic. Local Ollama is the default runtime, including on Apple Silicon Macs. vLLM, llama.cpp-compatible servers, or cloud backends (OpenAI, Anthropic, OpenRouter) also work through the same MCP surface.