yafitzdev/fitz-ai

Intelligent, honest knowledge retrieval in 5 minutes. No infrastructure. No boilerplate.

44
/ 100
Emerging

Implements KRAG (Knowledge Routing Augmented Generation), which parses documents into typed retrieval units (code symbols, sections, tables) and routes queries to specialized search strategies rather than treating all content uniformly. Enforces answer honesty through an ML governance classifier validated against a 2,920-case adversarial benchmark, achieving 86.5% recall at detecting unanswerable questions with only 5.7% false-positive rate. Supports immediate querying via progressive background indexing while handling temporal queries, code symbol extraction, and tabular SQL natively—requiring only Ollama or OpenAI/Cohere API keys, with no framework assembly needed.

20 stars and 1,116 monthly downloads. Available on PyPI.

Maintenance 13 / 25
Adoption 13 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

20

Forks

Language

Python

License

MIT

Last pushed

Mar 12, 2026

Monthly downloads

1,116

Commits (30d)

0

Dependencies

16

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/yafitzdev/fitz-ai"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.