A simple Scrabble cheating tool.

Next-generation take on pre/post function hooks

VoltAgent scorers re-export sourced from Viteval's prebuilt scorer set

Deterministic reference scorers as AIP-14 TOOL contracts + one builtin AIP-30 PROVIDER. A scorer IS a tool whose outputSchema is the shared `Score` shape — no new scorer port. Ships exact-match, regex-match, json-schema-valid, and latency-budget. No LLM/m

Trie data structure implementation in TypeScript. Highly performant. No dependencies. Built for a Scrabble Solver.

Lead qualification scorer - weight-profile scoring with per-ICP signal overrides and provenance-scoped multi-product candidacy. Single source of truth shared by the Vega app and the enrichment worker.

The implementation of TC lib for ReactJS projects

ITIL-aligned IT service management for Claude Code (problem, and future incident/change skills)

Parsed Scrabble word lists (CSW21 and NWL2018) with definitions

One-command installer for all Windy Road AI agent plugins and skills

MCP server for ICP Fit Scorer. Scores a company against your ideal customer profile with weighted signals via Apify. Returns a 0 to 100 score, a tier, and a per-signal breakdown. Clay-ready output.

Neural search engine with embedding-based scoring and learning-based pruning

Scrabble is a lightweight module that lets you cheat on a wide range of word games, most notably, the eponymous. Pass your letters into Scrabble as a string and it will return an array of all the possible combinations of those letters that comprise words

Mailwoman neural classifier runtime: SentencePiece tokenizer + ONNX inference + decoder wiring.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Arena escrow SDK for Snak on Celo (cUSD) + Stacks. Match creation, score digest, prize-split math, strike streak counter, rank badge tiers.

Evaluation runner for wasmagent — multi-model multi-axis benchmark harness with paired statistics + Pareto report. Targets the gaps in evomerge-style single-axis evaluation: long-context recall, multi-turn memory, agent trajectory, latency, cost.

Shared, runtime-agnostic core for svelte-vitals (types, rule engine, scorer, reporter).

TypeScript implementation of ROUGE evaluation metrics for text summarization.

An npm package to use the List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words