An experimental Generative AI Playground for UC Santa Cruz
BayLeaf Chat and BayLeaf API form an experimental Generative AI Playground designed to serve the entire UC Santa Cruz campus community (students, faculty, and staff). The system is operated by Adam Smith (faculty from the Department of Computational Media), as a living prototype of a possible future university-managed service.
LLM inference for the Playground is based on a portfolio of zero-data-retention providers accessed via OpenRouter.
Our Chat service provides access, by default, to one model called "Basic" that is powered by a strong, open-weight LLM (which one varies from month to month). Basic uses a system prompt that customizes it for the campus community (e.g. some basic self-knowledge of BayLeaf and the Chat user interface).
The "Help" model also available in the chat interface can accept "invite-..." style invite codes, allowing users access to specialized groups that might, for example, offer course/department/role-specific models or toolkits.
The Web Search and Web Page Content toolkits are available to everyone and allow some level of autonomy in agentic research processes.
The Code Sandbox toolkit gives models access to a persistent, sandboxed Linux environment, making it possible to run command-line tools directly from the browser. This enables tasks like file processing, scripting, and interacting with external services through CLI tools without leaving the chat interface.
Most chat models are subject to a rate limit mechanism that ensures fair and cost-efficient access for all.
Tip: Chat message replies from models are limited in length based on the number of turns in the conversation so far. Users should prefer many short conversations on distinct topics rather than one long one that meanders through unrelated topics.
Our API service provides key-less access to users connecting from the campus network (e.g. 169.233.x.x), and it allows authenticated users to grant themselves an API key for off-campus access.
This API injects a short system prompt prefix to all proxied requests to lightly customize downstream agents for use with the Playground.
To allow for experimentation, API requests are not closely rate limited, but individual keys are subject to a reasonable total daily spending limit.
For a list of models and per-token prices, visit https://openrouter.ai/models (note that only models available from ZDR providers can be accessed via BayLeaf API).
The API also provides sandboxed Linux environments (backed by
Daytona) for code execution and file
management. Keyed users get a persistent sandbox that retains files
across sessions, while campus-pass users get ephemeral sandboxes
that are created and destroyed per request. The same sk-bayleaf- API key
authenticates both LLM inference and sandbox access.
The API dashboard distributes setup instructions and credentials for CLI tools that extend what coding agents can do on behalf of authenticated users:
Nearly 100% of the code, documentation, and other project data in the BayLeaf repository was created using generative AI in agentic coding tools. This is an intentional choice: it demonstrates that sufficient technical capacity exists within the university to build and operate a service like this, without ceding control or responsibility to external parties. If you are a critic, ally, or other human who wants a direct human connection, please contact Adam Smith directly.
BayLeaf is open source and designed to be replicable. The architecture (Open WebUI, OpenRouter, OIDC authentication, zero-data-retention inference) is not UCSC-specific. Any institution with SSO and a domain can run the same stack.
If you're evaluating AI tools for your campus, read the case for universities owning their own AI infrastructure, or explore the source.