Development x402 offerings

Use when you have a likely PyPI project name (or a few tokens) and need to resolve it to live projects: tries the query as-is, PEP 503 normalization (lowercase, [-_.] → -), and hyphen/underscore/dot variants, then returns up to "limit" matching projects with summary, version, requires_python and license. This is name resolution, not full-text discovery — prefer exact package names when known. Author emails are redacted.

Use when you need the public PyPI project card: summary, home_page, project_urls, license, requires_python, a subset of classifiers, requires_dist (capped), current version, and yank status. Author/maintainer emails are omitted or redacted; only display names remain when present.

Use when you need the exact published artifact for an npm version: dependencies, optionalDependencies, peerDependencies, bundledDependencies, engines, os/cpu, dist (tarball URL, integrity, shasum, unpacked size), and the version publish time. Give "latest" as version to resolve the current dist-tag.

Use when you need the published artifacts for a specific PyPI version: each file with filename, packagetype (sdist/bdist_wheel…), size, upload time, yank flags, digests (sha256/blake2b/md5) and download URL. Give "latest" as version to use the project's current version.

Use when you need the public npm registry card for a package (scoped or unscoped): returns description, homepage, bugs URL, repository, license, keywords, maintainers as names only (emails stripped), number of versions, latest dist-tag version, created/modified times, and last-week download count from the official downloads API. Private packages are not supported.

Playwright Test from Manual Steps — Turns manual test steps plus the page facts you have (route, labels, button names, messages) into one Playwright Test file in TypeScript that can really fail. Elements are found by role and accessible name, by label or by text, never by a CSS class, an id or XPath, and a name that is the start of another gets the exact option; every step that observes something gets one awaited, auto-retrying assertion; a step such as wait a couple of seconds becomes an asser…

Open-weight text embeddings at a fixed model and precision: deterministic vectors for RAG and memory pipelines, identical across suppliers. POST /v1/text with {inputs} (a string or array of strings) and get the embedding vectors as one JSON object. Pay per request in USDC; no account, no API key.

Decodes raw EVM transactions and calldata into agent-readable intent: function signature, decoded arguments, and ERC-20 transfers. POST /v1/evm with {tx_hash, chain_id} and get one JSON object back. Fully deterministic: input determines output. Pay per request in USDC; no account, no API key.

Postgres or MySQL SQL to SQLite and D1 — Converts PostgreSQL or MySQL schema statements, migrations and queries into SQLite that Cloudflare D1 and Turso run, so the converted version behaves like the original and not only parses. Knows the conversions that run without an error and then go wrong - a key written as BIGSERIAL or INT AUTO_INCREMENT that SQLite stores as NULL, a custom enum type or an inline enum that stops checking anything, a default now() or gen_random_uuid() that SQLite rejects,…

Line-based diff between two strings using the Myers diff algorithm (via the diff/jsdiff library), returning a list of equal/add/remove operations.

Tests a regular expression pattern against a string, guarded against catastrophic backtracking (ReDoS) by running the match in an isolated worker thread with a hard 500ms timeout that fails closed.

Computes the next N run times for a standard 5-field cron expression, avoiding the mental cron-schedule simulation an LLM often gets subtly wrong.

Compares two semantic version strings and reports which is greater, lesser, or equal, using the standard semver comparison rules.

A Quality Gate For Prompts. Before they break production. Score any AI prompt against 8 dimensions, see what's weak, and get the fixed version in seconds.

A Quality Gate For Prompts. Before they break production. Score any AI prompt against 8 dimensions, see what's weak, and get the fixed version in seconds.

PR Description From a Diff — Writes a pull request title and description from a pasted unified diff, as Markdown only - a title line of at most 72 characters, then four fixed sections - Summary, Changes, Tests and Risks - where every file the diff touches is named once, including renames, deletions, binary files, mode changes, lockfiles and formatting-only edits, and nothing is claimed that the diff does not show. It describes what the hunks change and leaves out a reason, a speed gain, a secur…

$0.01 USDC required (x402 / Base or Solana) Paid 0.01 USDC. Detected plan, price, and billing-period changes for one catalog slug, newest first, with a paging cursor. Empty array means nothing has been recorded yet, not that the vendor’s price has been stable forever. Check free lastChangeAt first. No API key needed. Pay with any x402-compatible wallet that holds USDC on Base or Solana; the challenge lists both and you pay on whichever network your wallet is funded. If your agent does not yet have a funded wallet, set one up via Coinbase Agentic Wallet or Base MCP — then standard x402 clients will pay and retry automatically.

Reviews a single code file for bugs, security issues, syntax errors, and code quality problems with fast LLM turnarounds.

Performs comprehensive senior-engineer code review and security auditing on a single code file using high-precision LLM reasoning.

Retrieves dependency relationships between project tasks for planning and workflow analysis.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

x402 protocol updates as JSON: recently merged changes in the x402 Foundation repository (formerly coinbase/x402), latest tags, and current npm versions of the @x402 packages (core, evm, express, fetch, extensions) and @coinbase/x402. Read live from GitHub and npm, with links.

Latest releases of AI agent frameworks and specs as JSON: OpenClaw, Model Context Protocol specification, LangGraph, CrewAI. Version, date, days since release and link to release notes, read live from GitHub.