A tool to grab the latest Corpora Project data locally and access it.
AWS DynamoDB implementation for LangGraph Memory Store and Checkpoint Saver in TypeScript
Just testing another path
Naive Bayes Text Classifier
Constraints are container elements with a configurable constraint size, like width or height.
Another test
DiskANN/Vamana — SSD-friendly billion-scale approximate nearest neighbor search with product quantization
There data is still too hard to find and access. We need to make it accessible so we can start doing natural language processing and machine learning at a faster rate.
Domain-adaptive lossless compression for LLM conversation streams
AI-powered QA testing CLI — spawns cheap AI agents to test web apps with headless browsers
node.js interface to the Google word2vec tool
Unified memory-layer plugin for Claude Code. One MCP server, multiple typed corpora (vault, code, plans, docs, research, project-map), unified cross-corpus knowledge graph, conditional tool registration, in-process drift detection, and human↔code translat
StarTrekCorpora client
Pythia - corpus list.
Deny list dictionaries and config data for @stll/anonymize
Standalone TypeScript project service wrapper for linting.
Registry of DraCor corpora
Compile article voice profiles into reusable LLM writing context, evidence-first briefs, and deterministic draft review notes.
Another test
Self-hosted, open-source documentation framework. Drop-in compatible with Mintlify projects — render existing docs.json/MDX corpora unmodified, with Astro under the hood. Includes a CLI (init, dev, build, migrate), pluggable themes, and full MDX component
MCP server for Aztec development - clones and searches Aztec documentation and examples
Comprehensive security guards for LLM-powered and agentic AI applications - 34 guards covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards accessible via unified TrustGuard facade. Features prompt injection (PAP/per
An offline document-to-agent-context compiler. Transform unstructured files (PDFs, CSVs, Markdown) into token-efficient, semantic context packs for LLM agents.
Lexes CommonJS modules, returning their named exports metadata