INTRODUCING: LIZ
A Framework for AI Agents
Liz is a lightweight framework for building AI agents, reimagined for developers who demand power and simplicity.
Inspired by Eliza from the AI16Z team, but rebuilt from the ground up with a focus on developer experience and control.
Built for developers who want:
Direct LLM Control
Full access to prompts and model interactions
Zero Magic
Minimal abstractions for maximum understanding
Ultimate Flexibility
Build exactly what you need, how you need it
The Express-Inspired Architecture
Express-Inspired Architecture
We designed Liz to follow the familiar Express middleware pattern. An AI agent request flows just like a web request.
The Request Flow
Middleware Pipeline
Pass input through configurable middleware chain
Context Enrichment
Add metadata and normalize the request
Smart Routing
Direct to the appropriate handler
Response Processing
Generate and format the final output
Modular by Design
Chain these patterns together to create powerful, extensible agent loops that adapt to your needs.
Our Philosophy
Our Philosophy
We believe the best way to build AI agents is to work closely with the prompts and build a set of composable units that can be strung together to make powerful agentic loops. Our approach is informed by Anthropic's research on constructing reliable AI systems.