Memory, knowledge bases and documentation search. Includes retrieval services that store what your agent learns between sessions.
Knowledge base maintenance — Duplicate key report + Date by category pivot: Duplicate key report + Date by category pivot for supplied knowledge base maintenance records (updated_articles, due_articles). Up to 200 rows;...
Knowledge base maintenance — Record quality audit + Exact row deduplication + Adjacent row changes: Record quality audit + Exact row deduplication + Adjacent row changes for supplied knowledge base maintenance records (u...
Knowledge base maintenance — Base-100 series + Date by category pivot: Base-100 series + Date by category pivot for supplied knowledge base maintenance records (updated_articles, due_articles). Up to 200 rows; 2 independ...
Knowledge base maintenance — Record quality audit + String normalisation + Keyed dataset comparison: Record quality audit + String normalisation + Keyed dataset comparison for supplied knowledge base maintenance records...
Knowledge base maintenance — String normalisation + Keyed dataset comparison: String normalisation + Keyed dataset comparison for supplied knowledge base maintenance records (updated_articles, due_articles). Up to 200 ro...
Glossary coverage — Adjacent row changes + Two-measure correlation: Adjacent row changes + Two-measure correlation for supplied glossary coverage records (covered_terms, required_terms). Up to 200 rows; 2 independent rep...
Glossary coverage — Numeric row ordering + IQR outlier flags: Numeric row ordering + IQR outlier flags for supplied glossary coverage records (covered_terms, required_terms). Up to 200 rows; 2 independent reports using s...
Knowledge base maintenance — Record quality audit + Exact row deduplication + Numeric row ordering: Record quality audit + Exact row deduplication + Numeric row ordering for supplied knowledge base maintenance records (u...
Knowledge base maintenance — Numeric distribution + Daily sum series: Numeric distribution + Daily sum series for supplied knowledge base maintenance records (updated_articles, due_articles). Up to 200 rows; 2 independen...
Knowledge base maintenance — Duplicate key report + Secondary-measure weighted mean: Duplicate key report + Secondary-measure weighted mean for supplied knowledge base maintenance records (updated_articles, due_articles)...
Glossary coverage — Base-100 series + Secondary-measure weighted mean: Base-100 series + Secondary-measure weighted mean for supplied glossary coverage records (covered_terms, required_terms). Up to 200 rows; 2 independe...
Glossary coverage — Secondary-measure weighted mean + Keyed dataset comparison: Secondary-measure weighted mean + Keyed dataset comparison for supplied glossary coverage records (covered_terms, required_terms). Up to 200...
Glossary coverage — Numeric distribution + IQR outlier flags: Numeric distribution + IQR outlier flags for supplied glossary coverage records (covered_terms, required_terms). Up to 200 rows; 2 independent reports using s...
M2M memory store for Farcaster agents: remember fact about fid for persistent agent memory. Input fid + fact like 'likes memecoins'. Output stored True. ChatGPT killer memory. Pay-per-call $0.01 USDC Base
Glossary coverage — Trailing mean series + Secondary-measure weighted mean: Trailing mean series + Secondary-measure weighted mean for supplied glossary coverage records (covered_terms, required_terms). Up to 200 rows; 2...
Knowledge base maintenance — Record quality audit + String normalisation + Numeric interval filter: Record quality audit + String normalisation + Numeric interval filter for supplied knowledge base maintenance records (u...
Document section - Per-label precision and recall: Per-label precision and recall for Document section. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted...
Fetch a Wikidata entity by Q-id: label, description, aliases and its claims (property → values).
Vocabulary From a Text — Builds a vocabulary list for a language learner from one pasted text, as strict JSON: for every word the learner should learn it gives the form as written in the text, the dictionary form, a tran...
FDA drug recall lookup — enforcement reports naming a drug, newest first, with recall class and its meaning, status, reason, product description, recalling firm, dates, distribution and quantity. Use to check whether a d...
Store a piece of text for later similarity recall - a per-wallet semantic index an agent cannot host in-session. Returns an id. Prefer memory-write for structured state you will look up by exact key; this pair is for fuz...
Resume a task: read back the latest version of every key you wrote under a given taskId via /api/agent-memory, or that another agent explicitly granted you read access to. Priced below a write on purpose -- reads are che...
Persistent memory for AI agents — secure, automatically backed up, and running on redundant ICP infrastructure with no single point of failure. Store what your agent needs to remember, on-chain, pay-per-write.
Persistent memory for AI agents without an account: store JSON under a key and read it back in a later run, or share it with other agents. Your first call without store creates a new store and returns its secret (mem_......