Build better withVoidleap Code

A harness, not a wrapper. An IDE, not a black box. Every agent in one view.

Local-first

Voidleap Code is a desktop app that runs on your machine. When you use a cloud model, your prompts go directly to the provider. We don't see them or store them. Run a local model to skip providers entirely.

Bring your own keys. Swap providers. Nothing about your work flows through our servers.

Core features

Privacy

Local harness. Bring your own provider keys, or run a local model via Ollama.

Context

Visual context management curation round by round. Drop any entry from context.

Performance

Custom virtualizer with predictive height measurement. Built for long streaming threads.

Observability

30 charts: Cost, tokens, latency, cache hit, etc. Control center for live feed across every running thread.

Frequently asked questions

Where does my code go?

Decoupled inference. The architecture is locked local - on localhost only, all application data in ~/.voidleap/. The inference is your choice: a cloud provider for raw capability, or a local model for full provider privacy. Voidleap doesn't see your code either way.

Can I work without a constant internet connection?

Yes, for agent execution. With local models, your prompts and code stay on your machine - no provider in the loop. Voidleap itself only requires periodic license validation; once validated, you can stay offline for 24h.

Can I see what I'm spending?

Yes, 30+ charts cover cost trend, per-model, per-agent, per-thread, per-tool, and cache hit rate - exportable.

What happens when my conversation gets long?

You stay in control. The visual context lets you click any message, tool call, or file and tell the agent to forget it - no thread restart. AI Prune in suggest mode so you review before anything is removed. Four slash commands: /context, /trim, /prune, /compact.

Which models can I use?

Nine providers: Anthropic, OpenAI, Gemini, GitHub Copilot, Ollama, LMStudio, OpenRouter, Azure, Bedrock. Switch per thread, per agent, or per turn. Local models get full tool-call parity.

What can the agent run on my machine?

You decide. Four execution modes: Default, Read-only, Careful (approve every action), Yolo. AST-aware command parsing understands paths, redirects, pipes, subshells, and heredocs. Sensitive-path defaults block .ssh, .env*, .aws, .gnupg out of the box. Optional macOS Seatbelt sandbox.

How customizable is it?

Every agent, skill, hook, slash command, security rule, and system prompt is editable through the library or markdown. Three scopes: Global, workspace, project lets you configure once and override anywhere. Override or replace, not just append.

How do I install it?

Desktop app for Mac and Windows. No bun, no npm, no build step. Auto-updates with signed releases.

© 2026 VOIDLEAP ABPRIVACY