32 projects
pytagmanager
AI-native analytics implementation platform: crawl -> semantic DOM graph -> rule-based tracking recommendations -> GTM export, plus Tracking Observability & Diagnostics (real-browser runtime verification) and Site-Wide Tagging QA
streamxl
Renamed to pystreamxl. This package is a compatibility shim that re-exports pystreamxl; install pystreamxl directly.
pystreamxl
High-performance .xlsx file reader with formula extraction, comment support, and cross-sheet dependency analysis. Streams large .xlsx files row-by-row without loading the entire file into memory; 3.8-5.6x faster than openpyxl in this repo's own committed benchmarks (see benchmarks/results.md). Rust-powered, Python API.
pytokencalc
Universal token counting for ANY LLM with embedded StatGuardian quality validation: 8 cloud providers, 7 local inference engines, custom/proprietary models, and BYOM (Bring Your Own Model). Pattern-based forward-compatibility, model discovery, platform-aware tracking, 99%+ accuracy.
pyinterviewbot-ai
Local ASR/LLM/TTS + evidence-engine orchestration service for PyInterviewBot
mudfish
Rust-native web crawling and intelligence engine — Python bindings
clusteraudiencekit
Rust-powered customer segmentation: RFM analysis, KMeans/K-Prototypes clustering, churn prediction, customer lifetime value, real-time streaming segmentation, drift detection, lookalike audiences, cohort analytics, lifecycle tracking, and differential privacy / k-anonymity.
pybeamguard
Apache Beam & Dataflow pipeline analysis, reliability validation, and cost optimization platform
pyairflowtester
Unified Airflow + dbt reliability and quality platform
pyapicheck
Discover APIs from an OpenAPI spec, classify sensitive fields, and score risk — with every score traceable to a named reason, not a black-box number.
messagebirds
Python client SDK for MessageBirds, an open-source event-driven Customer Data & Engagement Platform
pyroboframes
High-performance dataloader for robot learning datasets. LeRobot format support, hardware-accelerated video decode via VideoToolbox, MLX array output. Zero-copy data pipeline optimized for Apple Silicon and edge robotics.
pynetworkintel
AI-powered network intelligence and vulnerability discovery platform
statguardian
Fast, declarative data quality framework. Schema validation, data drift detection, anomaly detection, outlier handling. 13x faster than pandera. Supports Pandas, Polars, DuckDB. Automated data contract enforcement for data pipelines.
pyvectorhound
Diagnostic tool for vector search failures in RAG and LLM systems. Evaluate embedding quality, analyze vector search rank correlation, benchmark BM25 vs semantic search, profile reranker performance. Identify root cause of retrieval failures.
pysynthdata
Generate synthetic relational datasets from a schema: real row generation, foreign keys, constraints, and quality scoring.
pyinferencemanager
Intelligent AI workload orchestrator. Multi-provider routing, cost optimization, semantic caching, dynamic routing with budget enforcement. Production observability included.
PyReverseETL
The Open Operational Data Activation Runtime
pydependencycheck
Dependency intelligence and governance platform for Python projects
pyblastradius
Operational Blast Radius Intelligence Platform - Predict cascading failures and quantify business impact
pyweatherenriched
Hyperlocal weather enrichment engine for operational data - street/building-level precision
PyStreamPDF
Intelligence engine for PDFs: selective retrieval, structure analysis, and token-efficient RAG
pystreamai
ML deployment toolkit: canary/A-B deployment routing, cost tracking, request scheduling, hot model reload, and ONNX Runtime inference
PyStreamMCP
Intelligent MCP orchestration hub - Intent understanding, capability matching, tool ranking with cohesive foundation
pyterrainMap
Spatial intelligence platform for multi-robot terrain mapping. Real-time SLAM, traversability analysis, temporal normalization, fleet learning, persistent world knowledge.
pyroboreplay
Forensic debugging platform for autonomous robots: causal analysis, multispectral sensor fusion, invisible object detection, and persistent world knowledge
pyrobovision
Multi-object tracking (Kalman filter + Hungarian association) and trajectory prediction for robotics, with an optional real MiDaS monocular depth backend. Pure Python (NumPy + SciPy) core; PyTorch is optional.
prismnote
Data science notebook with support for 15+ programming languages, SQL execution across 9+ databases, multi-terminal splits, and intelligent code assistance.
openanchor
LLM token-attribution middleware with OTEL observability and semantic caching
pyrobosimulator
AI-native world simulation engine: narratives, robotics, agents, ROS 2
pystreamdocuments
Smart context provider for LLMs - Minimal, most-relevant knowledge based on query anticipation and semantic understanding
pyautollm
AI-Native LLM Training & Infrastructure Abstraction Library
