| What it does | Multi-agent AI code review that reads your repo as a graph, not just the diff
| Multi-model desktop workspace with cost optimization through agent routing
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2025
| Not given
|
|---|
| Based in | IN
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free Trial: 14 days, full feature access, no credit card required. Pro: $6 / ₹499 per active developer per month (bring your own LLM key). Enterprise: Custom pricing, contact sales.
| Desktop app: Free and open source (Apache 2.0). Halv Cloud: US$10 per month.
|
|---|
| Key features | - Multi-agent code review analyzing bugs, security, performance, and architecture on every PR
- Whole-codebase graph analysis across monorepos and multi-repo setups
- Inline PR comments with severity, rationale, and suggested fixes
- CLI for local and CI review with pre-push hooks
- IDE extension supporting Cursor, Copilot, Claude and Windsurf rule sync
- Support for GitHub, GitLab, Bitbucket, and Azure Repos
- Bring Your Own Key (BYOK) with zero markup on LLM costs
- Code never stored or used for model training
| - 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
|
|---|
| What makes it different | - Architectural understanding of the entire codebase instead of just reviewing isolated diffs
- Multi-agent parallel analysis running specialized agents for different review categories simultaneously
- Consistent review rules enforced across IDE, CLI, and cloud reviewer
| - 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
|
|---|
| 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) | 1 ● no change since last check | 19 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 3 |
|---|
| Citation Flow (Majestic) | 22 | 24 |
|---|
| Referring domains (Majestic) | 22 | 57 |
|---|
Mesrai
Halv