Search 264 AI benchmarks by category, with data sources and licences for each.

Audio AI tools: transcription with speakers, stems, noise removal, MIDI, speech, voices and music.

Computer use for Claude Code, Codex, Cursor or any MCP client: your computer + Android phone (beta)

Screenplay and storyboard in your AI assistant: import scripts, edit scenes, build shots.

The context layer for the physical world: filmed spaces as cited context for agents.

Manage your Instagram in chat: stats, comments, DMs, publishing and scheduling after you approve.

Augment your work with Liminal. Stop repeating yourself and build on what’s already solved.

Textile design AI: print-ready upscaling, seamless repeats, colourways, screen separation.

Live listings, sold prices and resale scores from GovAuctions.app, the public surplus-auction site.

Project memory for AI agents: read and keep the user's Listspace boards up to date.

An MCP server that provides access to Agility CMS. See https://mcp.agilitycms.com for more details.

Structural code intelligence for AI agents: real call graphs, blast radius, and change history.

Kanban board for AI coding agents: they claim cards, report progress, ask you when blocked, ship.

Find AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents.

Draft, schedule and publish X (Twitter) and LinkedIn posts in your own voice.

Get a real human to verify, decide, or improve an AI agent's work. Pay per review via x402 on Base.

Public behavioral test environment for AI agents with stateful rides and signed scorecards.

Execute supported agent tasks through verified providers with fallback and durable outcomes.

Create invoices and customers and record payments in BillingEngine from any MCP client.

UK company credit risk for England & Wales: R-Score, CCJs, charges, financials. 5.1M companies.

Checks whether an agent's actions actually happened, against the destination's own records.

Chess opening guides and names, FEN and PGN checks, the daily chess puzzle and Elo estimates.

Citation-health over a CC0 citation graph: what supports, refutes, or cites a paper. Read-only.

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