ASL AI Hub MCP
Tenant-separated encrypted context and model routing for your AI work; OAuth 2.1 sign-in.
Model inference and embedding endpoints, including routers that front several providers. Context limits and prices change often, so treat the price with its check date.
Tenant-separated encrypted context and model routing for your AI work; OAuth 2.1 sign-in.
Connect your Amazon Seller Central data to Claude, Codex, Cursor, and other AI tools via MCP.
Train a text classifier from your labelled examples in a minute; label texts with probabilities.
Derived & aggregated data: vol surfaces, model-implied prices, forward curves. Index from 2020.
LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.
Pay per request for APIs, compute, browsers, RPC and LLM inference with stablecoins on Celo.
Always-on AI agents: a software factory for Claude Code, or an AI SRE that watches your systems.
Prompt-injection scanner (Bazaar tool #2): flags adversarial system-override strings inside untrusted text. Deterministic heuristics + LLM verdict.
Contract clause risk grader (Bazaar tool #10): flags non-standard liabilities, jurisdiction anomalies, one-sided termination terms. LLM-backed, structured verdict.
OpenAI-compatible chat completion at the standard /v1 base path: send a messages array and get a model reply. Point any OpenAI SDK at https://api.gadgethumans.com/v1 and pay per call with x402.
Single-prompt LLM chat: send one prompt string and get one assistant reply (OpenAI-compatible backend), simple JSON in/out
Validates a JSON document against a JSON Schema (core 2020-12 keywords incl. $ref/$defs, anyOf/oneOf/allOf, formats) and returns every error with instance path, schema path and a plain-language message. Use it as an inde...
LLM inference and AI chat completions billed per token: the 402 quotes your input tokens plus your declared max_tokens, and you pay for what the call actually uses. OpenAI-compatible, no signup, no API key.
Free AI-readiness audit: can ChatGPT, Claude and Perplexity read and cite a site? Fix snippets.
Course completion — Adjacent row changes + Two-measure correlation: Adjacent row changes + Two-measure correlation for supplied course completion records (completions, enrolments). Up to 200 rows; 2 independent reports u...
Course completion — Adjacent row changes + Secondary-measure weighted mean: Adjacent row changes + Secondary-measure weighted mean for supplied course completion records (completions, enrolments). Up to 200 rows; 2 indep...
Course completion — Category frequencies + Trailing mean series: Category frequencies + Trailing mean series for supplied course completion records (completions, enrolments). Up to 200 rows; 2 independent reports using s...
Tutorial completion — Exact row deduplication + Daily sum series: Exact row deduplication + Daily sum series for supplied tutorial completion records (starts, completions). Up to 200 rows; 2 independent reports using sha...
Tutorial completion — String normalisation + Duplicate key report: String normalisation + Duplicate key report for supplied tutorial completion records (starts, completions). Up to 200 rows; 2 independent reports using s...
Course completion — Record quality audit + String normalisation + Grouped numeric summary: Record quality audit + String normalisation + Grouped numeric summary for supplied course completion records (completions, enrolm...
Course completion — Numeric distribution + Date by category pivot: Numeric distribution + Date by category pivot for supplied course completion records (completions, enrolments). Up to 200 rows; 2 independent reports usi...
Tutorial completion — Exact row deduplication + Base-100 series: Exact row deduplication + Base-100 series for supplied tutorial completion records (starts, completions). Up to 200 rows; 2 independent reports using share...
Call AI by role, not by model: tiered AI gateway over REST and MCP.
Read-only project status: strict and weighted completion, each claim held to git.