10 projects
crit-core
crit Core's Python side: model inspection, tokenizers and chat templates, machine locks, native engines
crit
crit: inference runtime, reusable techniques, kernel discovery, evaluation and an OpenAI-compatible serving API
crit-eval
crit-eval: one speed, quality and exactness suite that every inference engine runs the same way
fitz-sage
Intelligent, honest knowledge retrieval in 5 minutes. No infrastructure. No boilerplate.
fitz-forge
Agentic coding-planning harness for local LLMs
fitz-tec
Temporal Expert Caching (TEC) for MoE inference — run MoE models that overflow GPU VRAM up to 6x faster on consumer hardware.
fitz-ai
Intelligent, honest knowledge retrieval in 5 minutes. No infrastructure. No boilerplate.
fitz-graveyard
MCP server for local-first AI architectural planning using local LLMs
fitz-gov
fitz-gov: Comprehensive RAG Governance Benchmark
fitz-pgserver
Fork of pgserver with Windows crash recovery fix - self-contained PostgreSQL for Python apps
