Classify LLM provider error responses (rate-limit, auth, server, context-window, content-policy, malformed). Anthropic, OpenAI, Google, AWS Bedrock. Zero deps.
SQL shell with LLM-powered UDFs (fold, unfold, map)
LLM orchestration for DiffSift — Anthropic/OpenAI providers, prompt templates, pre-check filter
Classify code changes by semantic impact — CI-native code review triage
Classification engine for semantic code change analysis — 231 rules, 15 languages, Tree-sitter AST
VCS integration for DiffSift — GitHub/GitLab PR comment posting, CI detection
A3S workflow engine — JSON DAG execution for agentic workflows (Dify/n8n style)
ML and pattern-based classifiers for toxicity, PII, and prompt injection detection
Slot pool orchestration library for Claude CLI
Super YARA — extends YARA-compatible rules with semantic, classifier, and LLM-based matching
Developer productivity analytics — git commit collection, classification, and reporting
HS code prediction for chemical products — Akinator-style interactive classification with rule-based and LLM hybrid engine