Build better withVoidleap Code
A full coding environment for developers building software with AI agents. A harness, not a wrapper. Every agent in one view. Your machine, your keys or local models. Nothing routes through us.
News
1 post
A control center for agentic engineers
Voidleap Code gives you the ability to inspect, control and adapt your workflow. It’s a foundation you can customize, not an opinionated framework. You get live telemetry and precise mechanics to stop guessing and control the orchestration.
Nothing hidden
Replace the black box with full observability. Audit and improve. Become a better builder.
Full insights into system prompts and context.
Own your toolbox
Your competitive advantage is the way you work. Use any model with any provider. Adapt it per domain or project.
Build workflows that work for you. No one-size fits all. No provider lock-in.
Optimize your output
Your developer experience, knowledge and human taste are the deciding factors for good results. Control your build and scale on your abilities.
Build your context. Manage it in detail. Engineer the output.
Local-first
Runs on your machine. We don't see your prompts or any other data. 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. No data monetization.
Context
Visual context management curation round by round. Drop any entry from context to stop bloat and drift.
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.
FAQ
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 Code 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 Code 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.