Move at Hanzo Speed
Build, ship, and iterate faster with the most popular open source coding agent.
npx hanzo-devWhy Hanzo
The all-in-one agentic engineering platform
Stay in your flow
The all-in-one agentic engineering platform
Sync across every interface
Start a task on your mobile device and finish it in VS Code, JetBrains, or the CLI without missing a beat.
Persist your context
Never lose state. Your session history, active agents, and variables follow you automatically across devices and environments.
Open the black box
Hanzo is open source so you can inspect, customize, and integrate to meet your specific needs.
Ship without friction
Move from "commit" to "live" in one motion. Get AI code reviews and deployments without leaving your IDE.
1000x every dev
Multiply your engineering output
Multiply your output
Use Orchestrator Mode and Code Review to plan, build, and audit simultaneously. Be everywhere at once.
Externalize your context
Stop repeating yourself. Use Memory Bank to store architectural decisions and onboard the team automatically.
Code at thought speed
Eliminate boilerplate. Use intelligent Tab Autocomplete to ship PRs faster than you can type them.
Use the best model for the job
With 500+ models, you can control the right tradeoffs between latency, cost, context, and reasoning for each task.
Accelerate AI ROI
Enterprise-grade AI management
Stop AI sprawl
Centralize usage to prevent shadow IT, security risks, and wasted credits before they spiral.
Track and improve velocity
Use the AI Management Dashboard to track adoption rates, measure new hire speed, and prove ROI.
Centralize management
Simplify administration with pooled credits, unified billing, and enterprise-grade data privacy controls.
Duplicate your best devs
Build a managed index to speed up onboarding. Capture individual "superpowers" into custom modes the whole team can use.
Features
Everything you need for agentic development
Cloud Agents
Run AI agents in the cloud without consuming local resources. Execute long-running tasks, complex workflows, and resource-intensive operations while your machine stays free for other work.
View DocumentationCode Reviews
Automated code review agents that analyze pull requests, suggest improvements, catch bugs, and ensure code quality standards. Get instant feedback before merging.
View DocumentationDeploy
One-click deployment. Deploy your applications directly from Hanzo Dev with intelligent configuration detection and automated setup.
View DocumentationParallel Agents (CLI)
Run multiple AI agents simultaneously using git worktrees in the Hanzo Dev CLI. Coordinate complex tasks across different parts of your codebase and review results as pull requests.
View DocumentationApp Builder
Visual app builder that generates production-ready code. Design interfaces, define logic, and let Hanzo Dev create the implementation.
Managed Indexing
Deep semantic understanding of your entire codebase. Navigate, understand, and modify large projects with full context awareness.
Agent Manager
Run multiple AI agents simultaneously directly in your IDE. Coordinate complex tasks across different parts of your codebase.
Sessions
Start a session in one place and continue on another platform. Your AI agents, context, and progress follow you everywhere.
Voice Prompting
Use natural voice commands to interact with AI agents directly in your IDE. Speak your requests instead of typing.
Autocomplete in JetBrains
AI-powered autocomplete and code suggestions directly in your JetBrains IDE with full codebase understanding.
AI Adoption Score
Track and measure your team's AI adoption effectiveness. Understand usage patterns and optimize workflows.
Auto Top Ups
Never run out of credits mid-task. Auto-replenish your balance automatically whenever it drops below $5.
Skills
Extend Hanzo Dev with skills. Sharable packages of domain expertise, new capabilities, and repeatable workflows.
Hanzo Pass
Get up to 50% free credits on your AI subscription. Credits never expire, plus bonus credits on top.
Hanzo for Slack
Ask questions about your codebase, get explanations, or create PRs via cloud agents—all in Slack.
Install where you work
Terminal CLI, VS Code, JetBrains. Hanzo works wherever you do.
Auto failure recovery
Hanzo automatically detects errors, runs test suites and recovers on failure. No more explaining errors to AI.
Hallucination-free code
MCP marketplace with tools that automatically look up library documentation. AI follows best practices.
Context is king
Hanzo searches for the right context automatically. Any context you add is bonus, not required.
Kickstart debugging
Debug mode goes through your codebase with a fine-toothed comb to find bug sources.
Memory bank
Stop re-explaining your app. AI keeps its own records of what it worked on and your preferences.
Tab autocomplete
Fast inline completion including multiline suggestions. Intelligent completions that understand your codebase.
Open Models
Switch between 500+ custom, local, and frontier LLMs.
Hanzo is the best gateway to discover and compare models. Use new models the day they come out and try stealth models for free.
Open Pricing
Run AI where you want and pay as you go
Hanzo Gateway
Open & transparent
- Choose from more than 60 providers
- Use more than 500 models
- Pay the exact list price of Anthropic, OpenAI, and Google
- No commission or hidden fees, we make money on Teams/Enterprise
- Pay as you go, no subscriptions, no waste
- No need to wait for a daily reset, no slow pool, no rate limits!
- Get Hanzo Pass - Get up to 50% bonus free credits
Or use any alternative
For AI inference
- Other Gateways (OpenRouter, Vercel, Requesty)
- Managed Services (AWS Bedrock, Azure OpenAI, Google AI Studio)
- Free, stealth, and budget models (Llama, Mistral, etc.)
- Fallback when you hit a quota limit with our virtual provider
- Bring your own API keys (BYOK) for any provider/subscription
- Run models locally (Ollama, LM Studio)
Open Source
Inspect, control, contribute
The complete plugin is open-source and licensed under Apache-2.0. You can see, control, and modify how Hanzo works. Hanzo does not have an auto model, so you always know exactly what model is being used. No silent context compression or cut-off. You can see the context window size on each request, along with the full prompts.
Join our community on Discord and contribute to help shape Hanzo's future.
Frequently Asked Questions
Looking for something in particular? Don't hesitate to reach out.
We offer generous credits for teams at large enterprises to experiment with the Hanzo Agent before committing. Contact our sales team to get started with a trial.
Ship faster. Keep control.
All coding agents in one workspace. Parallel execution, evidence-driven output, and policies you control.
curl -fsSL hanzo.sh | bash