Highcharts Stock fork with performanceChart, budget compare, and ranked tooltips.

Client for the DBC Ranked Recommendation service

Find the best Ollama model for your hardware, ranked by real benchmarks

Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsurf a ranked, token-budgeted query surface — agents query structure (symbols, imports, call edges

Codebase index and ranked static guidance for AI coding agents

Categorized, deterministically-ranked SKILL.md catalog AND MCP server for Claude Code (and any agent that speaks MCP). 1128 curated skills across 17 categories — frontend, backend, video editing, AI video generation, UI design, motion graphics, 3D, devops

Social-as-a-service backend — communities, posts, ranked feeds, stories, direct conversations, notifications, moderation, flags via ProductCraft Social. Generated from the production OpenAPI spec.

A Pi /cd command with ranked directory suggestions, persistent history, and aliases.

Feature location by coverage diff for vitest — where does feature X live? These lines, ranked, with the tests that prove it.

Live Task Manager for the React Native JS thread — see which timers, Promises, and callbacks are eating your JS FPS, ranked in real time. Part of Buoy devtools.

Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬

Drag and drop behaviors, specific to ranked-choice voting

MCP server for local markdown notes — ranked search, tags, todos, and a wiki-link knowledge graph, from any MCP client.

EXPLAIN for Docker builds and images — collects build/image facts, runs a deterministic rule engine, emits ranked findings for Claude to reason over.

A read-only Stripe billing audit & lint CLI — scans a Stripe account and reports revenue-losing misconfigurations as severity-ranked findings.

Structural code index with PageRank-ranked repo maps, symbol search, call-graph queries, and dependency analysis. Built on tree-sitter and graphology.

Batch web search for the pi coding agent -- ranked, readable results ready to fetch. Requires pi-smart-fetch.

MCP server that shows what is consuming your agent's context window before the conversation starts — skill descriptions, memory files and their imports, and configured MCP servers — ranked, with duplicates called out.

Tunable signal-ranking pipeline — turns a pile of agent-gathered candidates into a ranked list of the most prominent signals for any dashboard.

Facilitate ranked-choice voting using an instant-runoff algorithm