Local-first agentic coding
Voidleap Code is presented as a local harness for agentic coding. The desktop app runs on your machine, supports your own provider keys or a local model, and keeps inference out of Voidleap’s servers.
Voidleap Code
Voidleap Code is a local-first agentic coding IDE for developers who want to run AI-assisted workflows on their own machine, using their own provider keys or a local model. It includes context controls, observability, and configurable execution modes for inspecting and managing agent work.
What Voidleap Code is
Voidleap Code is an agentic coding environment for developers who want to run AI-assisted workflows on their own machine rather than through a hosted wrapper. The site describes it as a harness, not a wrapper: the app runs locally, requests go directly to the provider you choose, and you can also use a local model.
It is designed for people who want more control over how agents operate, what context they see, and how actions are executed. The product emphasizes observability, editable workflows, and provider flexibility, so you can inspect agent steps, adjust orchestration, and keep your projects and keys under your own control.
The pricing page frames Voidleap Code as a per-seat agentic IDE with a Free plan available now and paid tiers described separately. The current app runs on macOS and Windows, and the download flow requires a free account.
Core features
Context control tools
The product exposes a visual context workflow that lets you manage context round by round and drop individual entries to reduce bloat and drift. It also includes slash commands such as /context, /trim, /prune, and /compact.
Observability and telemetry
The site says you can inspect system prompts, context, live telemetry, and thread mechanics instead of treating the agent loop as a black box. It also describes 30+ charts for cost, tokens, latency, cache hit rate, and related activity.
Provider switching
Users can switch models and providers per thread, per agent, or per turn. Supported provider categories include model labs, gateways, cloud platforms, and local inference endpoints.
Controlled execution modes
Execution modes include Default, Read-only, Careful, and Yolo. The site also mentions AST-aware command parsing, sensitive-path protections, and an optional macOS Seatbelt sandbox.
Customizable workflow layers
The product includes editable agents, skills, hooks, slash commands, security rules, and system prompts, with configuration scopes for global, workspace, and project levels.
Where Voidleap Code fits
Compare agent workflows
A developer can bring a task they already solved in another tool, rerun it in Voidleap Code, and inspect each step the agents took to compare workflows and output.
Manage long-running threads
An engineer working on a long coding session can prune context, remove individual messages or tool calls, and keep the thread from drifting without restarting the conversation.
Control command execution
A user who wants tighter control over risk can choose Read-only or Careful execution, review commands before they run, or use Yolo when they want fewer prompts.
Use different models per task
A team can switch between provider accounts or local inference depending on task, cost, or privacy needs, while keeping the same local IDE and workflow structure.
Keep sensitive work local
An organization evaluating a local-first setup can keep code and prompts on its own machine, use its own provider keys, and avoid sending project data through Voidleap servers.
Pros and Cons
Pros
- Runs locally on the user’s machine rather than routing code and prompts through Voidleap servers.
- Supports both provider keys and local models, giving users a choice between cloud inference and on-device inference.
- Provides explicit context controls, live telemetry, and multiple execution modes instead of hiding the agent loop.
- Lets users switch providers per thread, per agent, or per turn, which is useful when different tasks need different models.
- Desktop app is available on macOS and Windows, with a free account required for download and no credit card requested.
Cons
- The pricing page says Pro and Team are in development, so only the Free plan is available now.
- Some items on the pricing page are marked as coming soon, including server installs for Pro and collaboration features for Team.
- The product is opinionated toward local, provider-connected workflows; teams looking for a hosted inference service would need a different setup.
FAQ
How do I install Voidleap Code?
Voidleap Code is installed as a desktop app and runs locally on Mac and Windows. The download flow requires an account, but accounts are free and do not require a credit card.
Which platforms are supported?
The product page says Voidleap Code runs on macOS and Windows.
Is there a free version?
Yes. The pricing page says the Free plan is available now, has no countdown, and does not require a credit card. Paid plans are described on the pricing page, but Pro and Team are marked as not yet available.
Which model providers can I use?
Voidleap Code supports nine providers listed on the site, including Anthropic, OpenAI, Gemini, GitHub Copilot, Ollama, LM Studio, OpenRouter, Azure, and Bedrock. The site also says local models can be used with Ollama or other compatible endpoints through your own inference setup.
Where does my code and prompt data go?
The site says the local architecture is on localhost only, with application data stored in ~/.voidleap/. Inference goes to the provider you choose, or stays on your machine if you run a local model.
Quick Facts
- Category
- Developer Tool
- Product type
- Agentic coding IDE
- Platforms
- macOS, Windows
- Deployment
- Local desktop app
- Pricing
- Free available now; Pro, Team, and Enterprise listed on pricing page
- Source domain
- voidleap.com
Alternativas ao Voidleap Code
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Ghost
Ghost é um assistente de IA para terminal, para conversar, gerar código e executar tarefas no prompt. Traz modelos gratuitos, funciona no Linux, macOS e Windows e é open source.
Vi3ecode
Vi3ecode is a maintained development environment for working with AI coding agents. It keeps project context, terminal, Git, memory, flows, review, and communication connected around the agent you already use.
Lucid Train
Lucid Train is a local-first AI coding harness that turns repository code into architecture diagrams and uses those diagrams as specifications for coding agents. It is available as a desktop app and a lightweight Rust CLI, and it can run with local models or your own API keys.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.