HazelJSBuild Your AI Backend and Ship It This Week.
HazelJS gives you one TypeScript backend for agents, RAG, tools, and memory so you can move from prototype to production without rewriting your stack.
Start Building in Seconds
Perfect for adding HCEL orchestration to your existing codebase. Minimal footprint, high impact.
npm install @hazeljs/core @hazeljs/aiUltra-Light Core
- • Use HCEL in Any Framework
- • Direct API Orchestration
- • Zero External Dependencies
- • Perfect for: Backend logic additions.
Standard Stack
- • Production Agent Runtime
- • Pre-configured RAG & Vectors
- • Built-in Auth & Observability
- • Perfect for: Starting from scratch.
Elegance Meets Intelligence.
Stop wrestling with manual integration. HazelJS brings enterprise-grade structure to the age of AI.
// 1. Setup DI
// 2. Configure OpenAI Adapter
// 3. Setup LangChain Chain
// 4. Manually pipe input to RAG
// 5. Manually pipe RAG output to Agent
// 6. Handle tool failures manually
// 7. Write 50 lines of boilerplate...
async execute(input) {
const docs = await this.rag.search(input);
const prompt = this.template.fill(input, docs);
const agent = new AgentExecutor({ ... });
return agent.call({ prompt });
}// 1. Just call the chain.
// Context flows implicitly.
async execute(input) {
return await this.ai.hazel
.prompt(template)
.rag('docs')
.agent('specialist')
.execute(input);
}Compose AI Pipelines Like Fluent TypeScript
HCEL gives you a chainable DSL to orchestrate prompts, RAG, agents, and ML in one typed flow. Less glue code, better observability, and production-ready orchestration by default.
Fluent Chaining
Build multi-step AI workflows with a readable chain API instead of nested async glue code.
Implicit Context Flow
Output from one operation automatically becomes input to the next, keeping pipelines concise and clear.
Built-In Observability
Trace each step with context and timing hooks so debugging and production monitoring are straightforward.
import { HazelAI } from '@hazeljs/ai';
const ai = HazelAI.create({ defaultProvider: 'openai', model: 'gpt-4o' });
const result = await ai.hazel
.prompt('Summarize this issue: {{input}}')
.rag('engineering-docs')
.agent('support-specialist')
.ml('sentiment')
.observe((event) => console.log(event.type, event.timestamp))
.execute(userTicket);What can you build with HazelJS?
Skip the boilerplate. From simple chatbots to enterprise-grade AI agents, build it in a weekend.
Customer Support Agent
A stateful agent that uses RAG to browse your docs and Tools to check order status directly in your database.
Knowledge Intelligence
Upload PDFs, CSVs, or web links and query them with semantic search and GraphRAG for complex reasoning.
Automated Content Pipeline
Build durable workflows that generate, review, and publish content based on real-time data triggers.
The Enterprise AI Stack
One stack. 44+ packages. AI-native from day one.
AI-Native Architecture
Built from the ground up for AI applications. Not a framework with AI bolted on—AI is at the core of every design decision.
Production Agent Runtime
Stateful execution engine for AI agents. Unlike stateless handlers, agents maintain context, execute tools safely, and support pause/resume workflows.
Agentic RAG
Self-improving retrieval system that plans queries, reflects on results, and adapts strategies. Build intelligent search that learns and improves over time.
HCEL Orchestration
Compose prompts, RAG, agents, and ML in one fluent TypeScript chain with implicit context and built-in observability.
Production-Ready Security
HazelJS includes enterprise-grade security middleware out of the box. No configuration needed—secure by default.
Security Headers
X-Content-Type-Options, X-Frame-Options, X-XSS-Protection, and HSTS headers automatically applied.
Rate Limiting
Protect your APIs from abuse with configurable rate limiting middleware. In-memory or Redis-backed.
CSRF Protection
Built-in CSRF token generation and validation to protect against cross-site request forgery attacks.
Input Sanitization
Automatic XSS prevention with HTML and string sanitization utilities. Protect against injection attacks.
Latest Blog Posts
Stay up to date with the latest news, tutorials, and updates from the HazelJS team.
Introducing @hazeljs/pubsub: Google Cloud Messaging, HazelJS Style
Introducing @hazeljs/pubsub for HazelJS: decorator-based Google Cloud Pub/Sub consumers, typed publishing, ack/nack controls, and module-first integration.
Introducing HCEL: The Most Fluent Way to Build AI Pipelines in TypeScript
A deep dive into HCEL (HazelJS Composable Expression Language), a fluent DSL for orchestrating prompts, RAG, and AI agents with minimal boilerplate and maximum type safety.
HazelJS v0.4.0: Distributed Sagas, Locking, and Zero-Config Documentation
Major update with distributed sagas, distributed locking, zero-config documentation, performance monitoring, and enhanced error handling. Enterprise-grade distributed systems capabilities now available.
Join the HazelJS Community
Connect with developers from universities around the world. Share knowledge, collaborate on projects, and build amazing applications together in our invite-only community platform.
University Groups
Join groups from your university. Connect with fellow students, researchers, and faculty members.
Discussions
Share knowledge, ask questions, and engage in meaningful discussions with the community.
Secure & Private
Invite-only access ensures a safe, focused environment for academic and professional collaboration.
Ready to Get Started?
Join the growing community of HazelJS developers and start building amazing applications today.
Deploy in Seconds, Not Hours
The fastest way to deploy your HazelJS applications. Push to GitHub or Bitbucket and watch your app go live instantly—zero configuration, zero hassle.
Lightning Fast
Deploy in under 30 seconds with optimized build pipelines
Zero Config
No setup required—just connect your repo and deploy
Global Edge
Deployed to edge locations worldwide for ultra-low latency
Auto Previews
Preview every PR automatically before merging
Seamless Git Integration
Connect your GitHub or Bitbucket repository and deploy automatically on every push. It's that simple.
GitHub
BitbucketJoin 9+ developers for early access to HazelJS.Cloud
HumanBee
Need help shipping AI agents, RAG, or production backends on HazelJS? HumanBee is the official consulting partner for architecture, implementation, and team enablement.
Visit HumanBeeSponsors & Partners
We're grateful to our sponsors and partners who support the HazelJS ecosystem.
Interested in becoming a sponsor or partner?
Get in Touch