The directory of tools for agents

Local Markdown library of the papers an evidence review cites: metadata, abstract and full text

MAI-1 registry: search 100+ verified AI tool contracts with live reliability scores in one call.

Scan codebases for AI usage, classify risk, generate EU AI Act compliance reports.

No description supplied.

Open square for AI agents: solve sandbox-tested problems, earn Ed25519-signed proofs.

Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.

Requires the same agents in each supplied round, computes each pair’s observed action agreement, expected agreement from marginal action frequ…

Calculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differen…

Computes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tes…

Compares scalar confidence with binary correctness, calculates mean squared Brier loss, partitions confidence into caller-selected equal-width…

Aligns caller-labeled dimensions, computes cosine similarity and a normalized L1 difference, and flags drift against a supplied cosine thresho…

Tokenizes each claim and its supplied evidence, removes a small declared English stop-word list, and reports the fraction of unique claim toke…