25 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
Apify is the largest and most trusted marketplace of tools for web scraping, crawling, data extraction, and automation. Use these tools, called Actors, to extract structured data from social media, e-commerce sites, sear...
Evaluate exact retention of 1-32 caller-labelled evidence spans at exactly five ascending token budgets. Returns five source-linked Context Packs, per-run retention metrics, an evidence frontier, stable hashes, and a det...
Web search that returns READY-TO-USE grounding text, not links: for one query you get the passages an independent search index extracted from the pages it ranked, flattened into chunks with their source URL and title and...
Use when an agent needs base block number. Returns Fetch the current Base mainnet block number from redundant public RPCs and return structured JSON with source and freshness metadata. $0.002.
Compare up to 64 total extracted spans from at most 16 labeled tools against exact code-point slices of supplied source text and declared UTF-8 hashes. Group identical source spans to expose text disagreements. No OCR/PD...
Compare source coverage on exactly the same declared record cohort across two snapshots. Report per-record gained/lost sources, per-source count changes, and global coverage drift. Reject unknown sources or missing/dupli...
Inspect a declared dependency graph of up to 64 nodes and 128 edges: exact cycle membership, source-root reachability, and deterministic graph digest. Duplicate edges and dangling references are rejected. Hash declaratio...
Find an exact 0/1 maximum-declared-value allocation for up to 64 evidence items and a 0–4096 integer token budget. Deterministic ID-based tie handling; items are indivisible. Optimality applies only to the additive calle...
Check exact quotes at declared code-point offsets and enumerate overlapping exact occurrences in supplied text (first 32 offsets, complete count). Unicode/case/whitespace are not normalized. A matching quote does not est...
Convert half-open UTF-8 byte, UTF-16 code-unit, or Unicode code-point spans into all three units for supplied text. Reject offsets inside a code point. No PDF parsing, page inference, or external source lookup.
Check declared citation coverage of up to 64 claims against bounded source and locator inventories. Reject duplicate IDs and dangling references. Coverage is structural, not proof that a source supports a claim.
Compare 2-20 caller-labelled observations of one claim, population and outcome. Returns opposing directions and explicitly excluded observations. No literature search, source inspection, consensus judgment or factual ver...
Choose a context budget before an agent run. Compare five extractive compilation budgets with token estimates and source coverage. Price basis: five compiler runs, the comparison table and the receipt digest. Uses caller...
WhiteMagic hosted recall — agent memory for cross-session continuity: read-only hybrid search (BM25 + vector + associative) over a curated public corpus. Call when an agent needs durable context from prior sessions or th...
Review a structured policy revision before release. Compare up to 40 caller-supplied clauses per version by stable ID, text and scope; report additions, removals and changes. Checks declared chronology, not legal effect,...
Count the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100k for GPT-4/3.5) plus estimates for Claude, Llama and Gemini, with characters per token. Budget LLM calls and split contexts.
Check up to ten declared claim-evidence relationships against a finite, versioned rule set. Reports unsupported frame transfers and missing information. Unknown combinations remain unresolved. No prose interpretation, so...
Compare up to 128 expected passage bindings with up to 128 retained descriptors by passage ID, parent document, version hash and chunk hash. Flags omissions, substitutions, repeats and ordering gaps. Public/synthetic met...
Breached password check: is this password in known data breaches, and how often? Send only the SHA-1 hash (never the password); just the first 5 characters reach Have I Been Pwned (k-anonymity). Up to 50 hashes per call.
Token compression for LLMs
Deduplicate facts and near-duplicate notes to save downstream agent tokens
Report what changed between two agent handoff states so the next agent reads only the delta
Compress long notes or conversation context into compact operational state for agent handoffs
Normalize text, WebVTT, SRT, or timestamped segments into compact, citeable chunks for AI agents.