Search

A tiny, swappable LLM orchestration core.

Drop-in design-feedback widget. Click → page freezes → drag a rect → engineer pulls the diagnostic envelope. Self-hostable on localhost.

RESTful web service which makes any storage system X available as an S3-compatible REST API

Biomedical Knowledge Mining with co-occurrence modeling and LLMs

A lightweight library for generating short-term bearer tokens for AWS External Anthropic API authentication

Financial infrastructure toolkit: banking connections, market data, credit, cashflows, and brokerage integrations

None

Nginx configuration manager and gateway orchestrator for nanio S3-compatible storage clusters

Local dashboard for tracking Claude Code token usage and costs

Interactive Theorem Prover

EMBeddings and LAtent Space Explorer - Dimensionality reduction service for synchrotron data

A Claude AI skill for asking clarifying questions and resolving ambiguity before starting tasks. Multi-round elicitation, automatic question grouping, and intelligent stopping rules for better first-draft outputs.

Free Claude/Cursor/Codex skill that scores how AI search engines describe your brand vs competitors. Built by GenPicked.

Pre-purchase property due diligence across 87 countries — tax, risks, rental yield, visa, mortgage, and 17 other facets per address. Sourced from primary government data, every claim dated and confidence-labelled.

IA Security Skill — auditoria de segurança defensiva pré-entrega para projetos Claude Code. 24 análises universais · 18 linguagens · 34 frameworks · mobile (MASVS) · desktop · browser extensions · 21 áreas especializadas. Score, attack chains e fixes copy-paste.

Decision-quality pre-commitment analysis for operators who can't afford to be wrong about direction.

Deterministic lexical execution analysis for multi-step LLM workflows.

Agents don’t behave, they swarm. Skills and plugins slot in mid flight, and somehow the whole thing is a mess

A ruthlessly strict algorithmic optimization methodology for AI coding agents. Forces your agent to profile, benchmark, and mathematically prove performance gains before writing code.

Sentence embeddings from any local causal LLM, no fine-tuning.