9 projects
skillshield
Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install. Zero dependencies.
gov-doc-parser
Parse and extract structured data from UK government documents — GOV.UK, Hansard, ICO, FCA, BAILII, and ATRS. Research and governance analysis toolkit.
synthetic-dataset-gen
Generate synthetic training data for ML pipelines. Q&A pairs, classification examples, tabular data, and instruction-following datasets. Anthropic-powered.
tool-registry-py
Typed tool catalogue for LLM agents. Register, discover, validate, and export tools to Anthropic/OpenAI format. Zero dependencies.
docstring-ai
AI-powered docstring generator for Python codebases. Batch-generates Google, NumPy, or Sphinx docstrings. Preserves existing docs. CI-ready.
llm-agent-bench
Benchmark autonomous AI agents on task completion, tool use, goal adherence, and safety. Works with any agent — just provide a callable.
corpus-quality
Document quality profiler for ML pipelines. Score, deduplicate, and validate your corpus before embedding. Zero mandatory dependencies.
chunk-bench
Benchmark RAG chunking strategies on your own documents. Compare fixed, sliding, paragraph, recursive, and semantic chunking with real retrieval metrics.
llm-response-cache
SQLite-backed LLM response cache. Exact match + fuzzy match. Decorator API. Zero mandatory server dependencies.
