A suite of tools to make working with React Native apps even more fun
Map tile rendering guided by a Mapbox style document
The missing layer between raw LLMs and production AI — personality, safety, sandboxing, containment
High-performance compiler backend for Lamina Intermediate Representation
Anthropic Claude backend for the Laminae AI SDK
OpenAI-compatible backend for the Laminae AI SDK
Process-level execution sandbox for AI agents — command whitelist, network filter, resource watchdog
Voice persona extraction and style enforcement for LLM output — learns how you write and keeps the AI on-voice
Umjunsik Language compiler targeting Lamina IR
Ollama client for local LLM inference — used by Laminae Psyche and Shadow
Adversarial red-teaming engine for AI output — static analysis, LLM review, sandbox execution
Self-improving learning loop for LLM applications — tracks user edits, extracts preferences, builds reusable instructions
Multi-agent cognitive pipeline for AI — Id (creative), Superego (safety), Ego (executor)
Lamina Intermediate Representation — high-level SSA IR for the Lamina compiler
No description provided.
No description provided.