2026TypeLLMopen source
TypeLLM
v0.1.6
TypeLLM is a framework that enables type-safe generation for autoregressive large language models without requiring changes to their architecture or weights. It allows models to retain native thinking and free-form generation capabilities while ensuring outputs strictly adhere to defined JSON schemas.
No out-of-schema hallucinations with JSON Schema enforcement
Dependency-aware execution using DAGs and incremental prefix reuse
Optional thinking mode with per-field budget for complex reasoning
pricingOpen source (Apache-2.0 license)
version0.1.6