| What it does | Multi-model desktop workspace with cost optimization through agent routing
| A desktop IDE for building software with AI agents, built for professional developers and AI engineers
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| SE
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Desktop app: Free and open source (Apache 2.0). Halv Cloud: US$10 per month.
| Free tier with 3 workspaces and 5 projects each, 1 profile for credentials, 7-day dashboard history. Pro at €20/month with unlimited workspaces and projects, one server install, and ticket support. Team at €50/month with unlimited server installs and real-time collaboration for up to 50 seats. Enter
|
|---|
| Key features | - JEV agent routing for automatic model and reasoning selection
- Support for Claude Code, Codex, Kimi, and GLM models
- Synced savings dashboard
- History across machines
- Automatic account rotation
- Code navigation via Crux
- Command output filtering via RTK
- Model context processing via Headroom
- Cross-platform support for macOS, Windows, Linux
| - Multi-provider model support with per-thread, per-agent, and per-turn switching
- Visual context editing with ability to remove messages, tool calls, or files
- Per-turn token count, cost, latency, and cache-hit telemetry
- User-editable agents, skills, hooks, and system prompts at global, workspace, and project scope
- Four execution modes with AST-parsed shell commands and sensitive-path blocking
- Local code index with symbol and reference navigation
- Parallel threads and worker threads in one view with thread forking
- Built-in browser with page annotation for agents
- Full custom grid layout for multiple agents
|
|---|
| What makes it different | - 57.1% lower recorded model costs compared to vanilla Codex on benchmark runs
- Free and open source desktop app under Apache 2.0 license
- Agent routing included with Halv Cloud at no additional fee
- Single workspace for multiple AI coding models
- Matched vanilla Codex pass rates with lower cost
| - Purpose-built agentic IDE from scratch rather than a fork or wrapper
- Complete transparency and control over agent execution with editable context
- Local-first architecture where code and prompts never pass through Voidleap servers
- Professional-grade observability with 30+ charts for cost, tokens, latency, and cache tracking
- Seamless multi-provider mixing allowing provider swaps mid-thread within one task
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 18 ▼ −1 (down) since last check | 4 ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 9 |
|---|
| Citation Flow (Majestic) | 24 | 26 |
|---|
| Referring domains (Majestic) | 57 | 53 |
|---|
Halv
Voidleap Code