agentutility(7)$ man updates
updates
Daily notes on x402, the agent economy, and what's new across the agentutility portfolio. One article per day, dated, no marketing. Subscribe via RSS or Atom.
ARCHIVE — 98 articles · newest first
| date | title | summary | tags |
|---|---|---|---|
| 2026-07-04 | Image model routes get cost-based prices | image-generate-pro and image-generate-ultra now use lower, margin-safe prices, with fixed-model routes for Flux 2 Pro, Seedream, Recraft, Qwen Image, GPT Image, Nano Banana Pro, and Nano Banana 2 Lite. | image, pricing, synthforge |
| 2026-07-03 | Three new pages get you from zero to a paid call: /start, /skill.md, /prompt.txt | New quickstart and install surfaces (/start, /skill.md, /prompt.txt) give a human or a coding agent a runnable path from an EVM key to a paid call in a few lines, plus a GET STARTED section on the homepage. | onboarding, quickstart, skill |
| 2026-07-03 | News search alias and clearer EDGAR filings metadata | The catalog now exposes news-search as a buyer-language alias for crypto-news, and edgar-filings carries explicit SEC EDGAR search wording. | discoverability, news, sec |
| 2026-07-03 | image-inpaint gets a catalog note for mask-based edits | image-inpaint is documented as the mask-based edit endpoint for object replacement, generative fill, and controlled image repairs. | image, inpaint, synthforge |
| 2026-07-02 | Video generation repriced to $5.00 per clip | image-to-video, text-to-video, and seedance-video move from $0.20 to $5.00 per generation — covering the Seedance 2.0 Fast upstream cost with a real margin. | pricing, video, seedance |
| 2026-07-02 | upscale-image is now $0.02 per call | upscale-image now runs the same Venice backend as image-upscale, so it is priced the same: $0.02 per call, down from $0.10. | upscale, image, pricing |
| 2026-07-02 | Signed token verdicts and X topic intelligence, one call each | Two new composites: token-clearance-check returns a signed pre-action safety verdict (honeypot, risk, source verification, LP lock), and x-topic-pulse merges tweet search, sentiment, and top voices. Plus a public signing key at /.well-known/x402-signing-key. | compose, token-safety, signed |
| 2026-07-02 | Pricing rebalance: a $0.005 floor and honest prices on the busy endpoints | 73 endpoints repriced. Zero-demand endpoints move from $0.001-$0.002 to a $0.005 floor, six busy dust-priced endpoints go to $0.003, and image-generate, translate, and the search family move to category-comparable prices. | pricing, reprice, image-generate |
| 2026-07-02 | Compose: composite endpoints that run our own catalog for you | New compose cluster: composite endpoints that run two to six of our existing capabilities in parallel and return one merged result for one payment. Company dossiers, token reports, article briefs, meeting summaries, and more. | compose, composite, enrichment |
| 2026-07-01 | upscale-image now runs on the Venice backend | upscale-image was returning an upstream error on valid input; it now uses the same Venice image/upscale backend as image-upscale, which is verified working. Scale options are 2× and 4×. | upscale, image, venice |
| 2026-06-30 | Retail cluster, stocks-news, and people lookup aliases | New retail e-commerce cluster (product-describe, product-search), a GDELT-backed stocks-news endpoint, and people/person aliases — all matched to proven agent demand. | retail, ecommerce, stocks |
| 2026-06-30 | New prices for pdf-to-markdown and mp4-to-mp3 | pdf-to-markdown drops to $0.0025 and mp4-to-mp3 to $0.02 to match what comparable x402 endpoints charge for the same jobs. | pricing, pdf, mp4 |
| 2026-06-29 | New cluster — Matchpoint, dedup and record linkage per call | Seven pure-compute endpoints that turn messy company names, people, addresses, emails, and phones into stable match keys, plus a pairwise similarity score — the dedup and entity-resolution primitives an agent needs to clean and join records. | |
| 2026-06-29 | Demand-matched aliases for buyer searches | New x402 aliases make existing browser render, inbox health, token quote, protocol TVL, and sentiment endpoints easier for buyers to find. | discoverability, aliases, demand |
| 2026-06-27 | tx-receipt-decode turns an EVM hash into named events | Call tx-receipt-decode with a transaction hash and chain, then get logs, event names, decoded args, and contract names for $0.005 over x402. | edge-market, evm, decoding |
| 2026-06-26 | Agent reputation on ERC-8004: what agentId 47167 still can't prove | ERC-8004 can name an agent today, but reputation still needs paid task records, attestations, dispute rules, and enough receipts for routers to trust agentId 47167. | erc-8004, reputation, identity |
| 2026-06-25 | Five self-running automation endpoints | New x402 endpoints turn vendor questionnaires, app-store rejections, RFPs, marketplace notices, and tariff duty scenarios into bounded machine-readable packets. | |
| 2026-06-24 | New endpoint — win-prob | Live sports win probability from the current score and time remaining, for NFL, NBA, MLB, NHL, and soccer. The first endpoint in the new statline cluster. | |
| 2026-06-24 | rollforge reference — conditions, magic items, classes, races | Four more SRD reference endpoints round out the rollforge rules library — conditions, magic items, classes, and races. The cluster now covers the full 5e SRD reference an agent needs at the table. | |
| 2026-06-24 | rollforge reference — SRD monster, spell, and equipment lookups | Three new rollforge endpoints put the 5e SRD reference at an agent's fingertips — monster stat blocks, full spell details, and weapon/armor stats. SRD-only, attributed, settled per call. | |
| 2026-06-24 | rollforge expands — nine 5e mechanics endpoints | The rollforge cluster grows with nine tabletop mechanics endpoints — name generation, ability checks, initiative, spell slots, XP/level, encounter budgeting, random tables, dice probability, and loot. Each call settled in USDC. | |
| 2026-06-24 | rollforge worldbuilding — seven flavor generators | Seven new generators for the rollforge cluster — NPCs, taverns, dungeon rooms, quest hooks, settlements, character backgrounds, and weather. Everything a GM needs to fill a world, one call at a time. | |
| 2026-06-24 | New cluster — rollforge (dice-roll + character-gen) | A new tabletop/RPG cluster for game-running agents. Two endpoints to start — a full dice-notation engine and a 5e-style character generator — each call settled in USDC. | |
| 2026-06-24 | Pictures at last — character-portrait and creature-image | Two new image endpoints close the loop on the rollforge and bestiary clusters — generate a portrait of a character, or art of any creature from any world, as a hosted PNG. | |
| 2026-06-24 | New endpoint — emergency-fund-calculator | Sizes an emergency fund — target, current coverage, shortfall, and how long it takes to get there — for agents doing personal-finance planning. | |
| 2026-06-24 | New cluster — bestiary, a creature compendium for any world | A new cluster that knows creatures from everywhere — myth, folklore, cryptids, novels, films, games, and song. Look up lore, stat any creature for the table, run a matchup, identify one from a description, or pull a random monster. | |
| 2026-06-23 | The whole catalog now has an OpenAPI spec | There's now an OpenAPI 3.1 document at /openapi.json describing every endpoint — its inputs, price, and payment rails — so agents and directories that read OpenAPI can ingest the catalog in a single fetch. | |
| 2026-06-22 | Endpoints are now payable on Solana, not just Base | Every endpoint now offers two payment options in its 402 challenge — USDC on Base and SPL-USDC on Solana mainnet — so an agent can pay on whichever chain it already holds funds. | |
| 2026-06-19 | X user timeline endpoints are live | New read-only x402 routes fetch recent public posts from a known X username. | x402, x, social |
| 2026-06-19 | Working capital and SaaS finance calculators are live | Three business-finance endpoints add working capital, invoice discount, and SaaS operating metric coverage. | endpoints, edge-finance, calculators |
| 2026-06-19 | City weather and X search slugs are live | New x402 listings cover city-name weather lookup, recent X post search, and public X profile lookup with direct buyer wording. | x402, weather, x |
| 2026-06-19 | solana-token-safety — SPL token rug-check | New endpoint that scores a Solana SPL token for rug-pull risk — mint/freeze authorities, holder concentration, transfer hooks, and LP signals — in one call. | |
| 2026-06-19 | Solana token watchlist endpoints are live | New x402 endpoints cover Solana token watchlists, flagged-token feeds, and boosted-token trends from public DEX Screener data. | endpoints, demand, edge-market |
| 2026-06-19 | More Search And Lead Enrichment Entry Points | Four new aliases route common buyer wording to existing search and enrichment handlers. | |
| 2026-06-19 | Crypto news and enrichment endpoints are live | Four new x402 endpoints cover crypto headlines, market recaps, public person enrichment, and company enrichment from domain-level data. | endpoints, demand, x402 |
| 2026-06-19 | More surfaces around proven endpoints | New vendor-risk, creator-asset, localization, and sentiment routes extend handlers that are already working. | endpoints, demand, discoverability |
| 2026-06-19 | Movie and streaming lookup endpoints are live | New x402 endpoints cover movie and TV metadata with TMDB when configured and Wikidata as a no-key fallback. | endpoints, demand, mediakit |
| 2026-06-19 | Thematic surfaces for hot endpoints | New domain, image, translation, sentiment, movie, and finance listings broaden routes around endpoints already seeing demand. | endpoints, demand, discoverability |
| 2026-06-19 | Hot demand routes are live | New exact-name x402 routes cover search, email validation, X mentions, social mindshare, crypto headlines, wallet details, and public-data enrichment. | endpoints, demand, x402 |
| 2026-06-19 | Four new B2B finance scorers — factoring, MCA, equipment, RBF | The edge-finance cluster gains invoice-factoring, merchant-cash-advance, equipment-finance, and revenue-based-financing scorers — structured scores built for underwriting pipelines. | |
| 2026-06-19 | Five more finance scorers — CRE, AR aging, inventory, PO, ABL | The edge-finance cluster gains commercial-real-estate-loan, accounts-receivable-aging, inventory-finance, purchase-order-finance, and asset-based-lending scorers — all structured scores for underwriting pipelines. | |
| 2026-06-19 | Finance calculator endpoints are live | Seven finance calculators expand EdgeFinance coverage. | |
| 2026-06-19 | Finance calculator API aliases are live | Eight finance calculators now have exact API-name listings for buyer searches. | endpoints, demand, edge-finance |
| 2026-06-19 | More buyer-language aliases for high-demand endpoints | New aliases make IPFS fetch, QR generation, and email deliverability scoring easier for agents to find in x402 discovery. | endpoints, discovery, x402 |
| 2026-06-19 | Demand API alias expansion | Fifteen more exact buyer-keyword API aliases were added for demand rows that already map to working endpoints. | |
| 2026-06-19 | Decodo dependency status for search endpoints | Decodo-backed search endpoints now report upstream auth and rate-limit failures with explicit dependency fields instead of generic 5xx-style errors. | |
| 2026-06-19 | Build-candidate ranking probes | Audit now treats weak build-candidate rows as probeable ranking debt, and ten exact buyer-language aliases were added for current demand gaps. | |
| 2026-06-19 | browser-session — render JavaScript pages in a headless browser | New endpoint that loads a URL in a real headless browser and returns the post-JavaScript HTML or a screenshot, for pages a plain fetch can't read. | |
| 2026-06-19 | Every JSON response now carries a provider stamp | Successful JSON responses across the portfolio now include _provider and _canonical fields, so the source travels with the data even through resellers and proxies. | |
| 2026-06-19 | Brand bootstrap endpoints are easier to find | New x402 listings expose business naming, startup naming, tagline, logo-prompt, and handle-check workflows under direct buyer wording. | x402, brand, startup |
| 2026-06-19 | Balance demand surfaces and broader expansion playbooks | x402, edge-market, wallets | |
| 2026-06-18 | Agent-callable means it passes five tests | A working checklist for agent-callable x402 endpoints: cold curl, JSON-LD, validation, MCP discovery, and price data agents can read before paying. | agent-callable, checklist |
| 2026-06-18 | Email deliverability and X sentiment are now callable endpoints | New x402 endpoints cover domain-level email deliverability checks and read-only X sentiment search, with demand-screen guidance that points builders to the next endpoint to ship. | endpoints, demand, x402 |
| 2026-06-17 | MCP catalogs are becoming paid API directories | MCP servers can now expose priced x402 endpoints as call-ready catalog entries, giving agents a path from discovery to paid HTTP calls on Base mainnet. | mcp, discovery, catalogs |
| 2026-06-16 | logo-detect description now tells agents when to call it | logo-detect now has sharper registry text, so mediakit agents should route logo checks from brand, sponsorship, and rights workflows with less prompt glue. | x402, update, logo-detect |
| 2026-06-14 | Schema.org JSON-LD for paid x402 endpoint pages | Each paid x402 endpoint page emits API, service, article, price, and call-action data so agents and AI search systems can cite the right paid tool. | json-ld, schema-org, ai-seo |
| 2026-06-13 | What 254 endpoint prices look like | A count of all 254 agentutility endpoint prices shows the median is $0.01, while $0.005 is the most common price and image-generate-ultra alone sits at $0.30. | pricing, data, stats |
| 2026-06-12 | 13F deltas: SEC position changes for $0.005 per call | Walk the 13f-deltas endpoint for SEC Form 13F changes, including new, closed, raised, and reduced positions, with Berkshire Hathaway's Q1 2026 filing as the test case. | edge-finance, sec, filings |
| 2026-06-11 | Image generation router update: fast Venice, pro models, flagship tiers | The image generation endpoints now publish clearer tiers, request examples, backend notes, and MCP-callable routes across the site catalog. | image-generation, synthforge, x402 |
| 2026-06-11 | One-shot research briefs on x402 for $0.04 | Build a research agent that takes one topic, pays x402 fees on Base, calls WebProbe, Wordmint, and EdgeFinance, then returns a 500-word brief. | recipes, agents, research |
| 2026-05-18 | slugify: any string to a clean URL slug for $0.001 | Unicode-aware slug generator with four output modes. Cheapest endpoint in the catalog. Handles accents, symbols, and word-boundary truncation. | wordmint, slug, slugify |
| 2026-05-18 | regex-test: verify your regex against test cases for $0.002 | Regex runner with capture groups and named groups. Pairs with regex-from-prompt: that one writes the pattern, this one tells you whether it works. | wordmint, regex, pattern-matching |
| 2026-05-18 | pypi-package-stats: Python package stats at $0.003 per call | The PyPI counterpart to npm-package-stats. Pulls metadata + downloads from the PyPI JSON API and pypistats.org. Just the numbers. | web-probe, pypi, python |
| 2026-05-18 | pr-description-from-diff: paste a diff, get a PR body for $0.01 | Wider-scope cousin to commit-message-from-diff. Returns a structured PR title, summary bullets, a test plan checklist, and a ready-to-paste Markdown body. | wordmint, pr-description, git-diff |
| 2026-05-18 | npm-package-stats: download counts and release history for $0.003 | npm registry lookup. Returns downloads (day/week/month/year), version history, maintainers, and age. Just the numbers the registry publishes. | web-probe, npm, package-stats |
| 2026-05-18 | agentutility ships as MCP: 8 cluster servers, 248 tools, zero custody | The full agentutility portfolio is now installable as MCP servers under @agentutility/mcp-<cluster>. Stdio packages, agent-held wallet, USDC on Base. mcp.agentutility.ai goes live as the catalog surface. | mcp, x402, launch |
| 2026-05-18 | json-schema-validate: verify any JSON against any schema for $0.003 | Ajv-backed validator. Draft-07 and 2020-12. Per-error instance and schema paths. The verification gate every agent pipeline needs. | wordmint, json-schema, validation |
| 2026-05-18 | hash-string: SHA / MD5 digests in five algorithms for $0.001 | Multi-algorithm hash endpoint. SHA-1, SHA-256, SHA-384, SHA-512, MD5. Returns hex, base64, base64url. Same input, same digest, every time. | wordmint, hash, sha256 |
| 2026-05-18 | cron-next: deterministic next-N fire times for any cron string at $0.003 | Returns the next N actual firing timestamps for any cron expression in any IANA timezone. Pairs with cron-explain. | wordmint, cron, scheduling |
| 2026-05-18 | crates-io-stats: Rust package stats at $0.003 — completes the trio | Rust counterpart to npm-package-stats and pypi-package-stats. Pulls metadata + downloads from crates.io. Now every major package ecosystem has the same stats endpoint. | web-probe, crates-io, rust |
| 2026-05-18 | card-resolve: turn a messy human card string into a structured object for $0.005 | First endpoint of the would-be Comppoint cluster ships under Wordmint instead. Turns a messy card string into a structured object, zero ToS exposure — and useful on its own. | wordmint, card-extraction, graded-cards |
| 2026-05-17 | Schema design rules for paid agent endpoints | What we learned about field shapes, error handling, naming, and defaults after shipping 244 paid x402 endpoints across the agentutility portfolio. | schema, api-design, agents |
| 2026-05-17 | MCP is becoming an API discovery protocol, not just a tool surface | Model Context Protocol started as a way to hand tools to agents. It's quietly becoming the layer where agents discover, evaluate, and call paid APIs. | mcp, x402, discovery |
| 2026-05-16 | Prooflayer and the verification bottleneck | AI writes code fast. Reviewing whether that code is safe to ship is the next scarcity. Prooflayer's 13 endpoints try to compress that review into one paid call. | prooflayer, ai-codegen, supply-chain |
| 2026-05-16 | How the token-risk-score endpoint actually scores a token | Walkthrough of the EdgeMarket token-risk-score endpoint: six subscores from honeypot.is, GoPlus, and Etherscan, totaling 0-100 with a verdict tag, for $0.10 a call. | edge-market, onchain, defi |
| 2026-05-15 | Why an HTTP 402 paywall beats handing out API keys | API keys assume one human, one account, one billing relationship. Agents don't fit that shape. x402 fixes it by turning the 402 status code into a payment handshake. | x402, api-keys, base |
| 2026-05-15 | The economics of $0.001-per-call APIs | Why SaaS minimums priced agents out, what a 1,000-call month costs on a $0.03 x402 endpoint vs a $99/mo plan, and where sub-cent pricing opens new work. | economics, pricing, saas |
| 2026-05-14 | ERC-8004 in one page: what an agent card actually contains | The ERC-8004 agent card spec in one screen: the on-chain struct, the resolution path from agentId to JSON, and why agentId 47167's URI points at a worker, not a pinned file. | erc-8004, identity, base |
| 2026-05-13 | Mediakit: 50 file-format endpoints, one paywall | Mediakit ships 50 single-purpose file-conversion endpoints across PDF, image, audio, video, OCR, and office. Why 50 endpoints beats one /convert tool with a format flag. | mediakit, file-conversion, pdf |
| 2026-05-12 | Why named LLM tasks beat raw token billing | Token billing forces agents to guess prices before they know input sizes. Wordmint's named-task pricing flips that so a 'summarize' call costs $0.01, full stop. | wordmint, llm, pricing |
| 2026-05-11 | What a paid pre-flight check saves you on a 1,000-URL scrape | WebProbe's DNS/SSL/WHOIS/liveness checks at $0.001/URL filter dead domains, expired certs, parked sites, and squatter pages before you spend $0.01 each on doomed scrapes. | web-probe, scraping, dns |
| 2026-05-10 | Locale: the civic + weather + geo stack at $0.001/call | The Locale cluster wraps free civic data (weather, geocoding, flight status, IRS, Socrata) behind one x402 paywall at $0.001 a call, so an agent's whole trip-planning loop costs a penny. | locale, weather, geocoding |
| 2026-05-09 | What a Coinbase Bazaar listing actually looks like to a crawler | A field-by-field walkthrough of how Coinbase's x402 Bazaar serializes endpoint listings, with notes on which fields move discovery and why paid call volume sets rank. | bazaar, coinbase, discovery |
| 2026-05-08 | The 'no signup' pattern in practice across 680 endpoints | An agent with a wallet, no account, no API key calls an x402 endpoint cold, pays $0.003 on Base, gets data back in two round trips. Full lifecycle traced. | x402, auth, wallet-identity |
| 2026-05-07 | Composable pricing: stacking endpoints to answer one question | Four x402 endpoints stacked, $0.025 total, one answer to 'is this token safe to swap.' A worked example in composing thin APIs against the Bloomberg subscription model. | composability, pricing, trading-agents |
| 2026-05-06 | Why agentutility publishes an llms.txt (and what's in ours) | The llmstxt.org proposal in one paragraph, why it matters for AI-search citation, what we put in /llms.txt vs /llms-full.txt, and how to size yours. | llms-txt, ai-seo, crawling |
| 2026-05-04 | Wallet-as-identity: what it actually buys you over an API key | Wallet signatures scope risk to a single payment instead of a long-lived bearer secret. The trade flips hard when the principal is an agent calling 40 paid APIs a session. | auth, wallets, x402 |
| 2026-05-03 | Synthforge: three price tiers for generative media | Synthforge ships draft, standard, and ultra tiers across image, video, and audio gen so agents pick the right cost-quality point per call instead of paying flagship rates every time. | synthforge, media-gen, pricing-tiers |
| 2026-05-02 | Tag-based discovery: how to grep our 680 endpoints | 680 endpoints in our x402 catalog now carry composable tags, and /endpoints.txt publishes a grep-friendly flat-file index agents can curl without any JSON parsing or API key. | discovery, tags, catalog |
| 2026-05-01 | What the x402 facilitator wallet does (and doesn't) hold | The CDP facilitator at 0x8f5c…e531 never custodies your USDC. Here's what actually moves on-chain when an x402 call settles, and what stays off it. | x402, facilitator, base |
| 2026-04-30 | Building a one-shot research agent on x402 | A working recipe: feed a topic, get back a 500-word sourced brief in about seven seconds for four cents, using three x402 endpoints stitched together with one wallet. | recipes, agents, research |
| 2026-04-29 | x402 vs L402 vs pay-per-crawl: three takes on machine payments | Three protocols want to make HTTP 402 real. Lightning's L402, Coinbase's x402, Cloudflare's pay-per-crawl. Different auth, different rails, different bets. | x402, l402, lightning |
| 2026-04-28 | Versioning paid endpoints when the agents won't read changelogs | Agents don't read changelogs. So we don't break endpoints. Here's how we handle schema changes across the agentutility portfolio without burning live callers. | versioning, api-design, compatibility |
| 2026-04-27 | 13F deltas: parsed SEC filings at $0.005/call | The 13f-deltas endpoint diffs consecutive SEC 13F filings and returns added, exited, and resized positions in JSON, so an agent can screen a hundred funds for a few cents. | edge-finance, sec, filings |
| 2026-04-26 | How an agent should budget when endpoint prices vary 100x | Endpoint prices on x402 span three orders of magnitude. Here's how to write an agent loop that won't blow its budget on a single image call or starve cheap utility endpoints. | agents, budget, code |
| 2026-04-24 | Why every endpoint page emits schema.org JSON-LD | We ship WebAPI + Service + TechArticle + Offer JSON-LD on every endpoint page. It pays off in AI-search citation rates. | json-ld, schema-org, ai-seo |
| 2026-04-23 | The rise of MCP-discoverable catalogs | MCP began as local stdio tools loaded into Claude Desktop. Eighteen months later it's the discovery layer for remote paid APIs, and that changes what shipping an endpoint means. | mcp, discovery, catalogs |
| 2026-04-22 | What does 'agent-callable' actually mean? | Five concrete tests to decide whether your API is actually reachable by agents, or just claims to be. Curl it cold, validate the schema, check MCP discovery. | agent-callable, api-design, checklist |
SEE ALSO