Skip to content
Menu

Agent402

AI Agents

Is this your project? Claim and verify →

agent402.tools: 500+ pay-per-call tools, metered models and finished reports for AI agents, paid per call in USDC over x402 and MPP or by card. Open source, self-hostable, MCP-native. The applied layer of agentic finance.

Read more

What HEY knows

Building
Shipping consistentlyShipping: 14 meaningful events in 30 days; latest ship today. Evidence Source

Build Momentum 87How it is measured

Latest ship
Code changes this week (since Mon 19 Oct) · 6 commits · · Code activity

Why it matters: One of 14 meaningful events in the last 30 days: building continued, not a one-off.

FollowCreate alertTerminal previewView latest ship
Share

Follow puts Agent402 on your private watchlist; its changes then lead “Since you were last here” when you come back. Following needs an account; browsing never does.

No account? Email me Agent402’s changes

No account and no password. HEY stores the address and what you asked for, sends one confirmation, and nothing else until you confirm. Every email has a one-click unsubscribe that deletes the address.

Or read its RSS feed.

Token market · context
No token tracked
Not yet known
Unknown1 gap: API description (source unavailable). The API description it links could not be read.

HEY can answer 10 of the 11 research questions that apply · Research coverage

Compare with…The same summary, with every line’s evidence: snapshot API
What HEY checked — why it says this
Shipping.
“Shipping” by the activity rule: 14 meaningful events in the last 30 days, the newest 2026-10-19.
SourceRepositories, changelogs and feeds HEY reads for this project, and the ship events recorded from them.ReadRecordsCode changes this week (since Mon 19 Oct) · 6 commitsCode changes, week of 2026-10-12 – 2026-10-18 · 175 commitsv2.7.0: image and long-document judgment, exact sanctions matching, and deadlines on every outside call+2 moreWhat HEY derivedHEY’s activity rule reads the counted events as “Shipping”.Not concludedIt says what HEY can read of the building, not how good the project is, who is behind it, or what its token will do. Quiet or unknown is not "abandoned".
Verified Builder.
The quality gate found verified building evidence from the project's own sources.
Source29 registered sources, 0 of them context only.ReadRecordsCode changes this week (since Mon 19 Oct) · 6 commitsCode changes, week of 2026-10-12 – 2026-10-18 · 175 commitsv2.7.0: image and long-document judgment, exact sanctions matching, and deadlines on every outside call+7 moreWhat HEY derivedThe quality gate’s stored decision: “Verified Builder”.Not concludedA verified builder is one whose shipping HEY confirmed from public evidence. It does not say who runs the project — that is the ownership claim, a separate check.
Market figures are context only and never change activity status. Methodology
LinksWebsiteGitHubSources

Latest ship

Checked

Code changes this week (since Mon 19 Oct) · 6 commits

Code activitySource linked

What changed, in the repository’s own words:

1 active day in mikeypetrillo/agent402.

This week HEY looked inside 1 of 6 commits to see what changed: 1 changed code. One code change is enough for the week to count, so HEY stopped there.

Record ship:afcbf40b… · HEY counts it as building; it does not judge the release’s quality or what it means for the token.

View evidence ↗

Builder activity

Bars: meaningful, source-backed ships per week (count). Weeks run Monday to Sunday, UTC, labelled by their Monday. Commits are aggregated, a code week counted once. Hatched: 2 weeks before HEY began reading this project’s sources — not yet read, not zero.

Questions HEY can answer about Agent402 — as of 2026-10-19

Is Agent402 still being built?
DerivedShipping: 14 meaningful events in 30 days; latest ship today. Evidence
What did Agent402 ship last?
FactCode changes this week (since Mon 19 Oct) · 6 commits — Code activity, today. Evidence
What does HEY not know about Agent402?
Unknown1 gap: API description (source unavailable). The API description it links could not be read. Details

Build timeline

  1. Code changes, week of 2026-10-12 – 2026-10-18 · 175 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    5 active days in mikeypetrillo/agent402.

    This week HEY looked inside 3 of 175 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count. 4 automated commits (bot accounts or a repeating scripted message) not counted.

    View evidence

  2. v2.7.0: image and long-document judgment, exact sanctions matching, and deadlines on every outside call

    GitHub releaseSource verified

    Tagged 2026-10-16 at the 2026-10-15 release. One line per change; the mechanism behind each is on agent402.tools/changelog. Buyers · POST /v1/judge/vision (preview) asks typed questions about up to four PNG or JPEG images: yes or no, choice, score, and box answers (where… Show all
    • Tagged 2026-10-16 at the 2026-10-15 release. One line per change; the mechanism behind each is on agent402.tools/changelog. Buyers
    • POST /v1/judge/vision (preview) asks typed questions about up to four PNG or JPEG images: yes or no, choice, score, and box answers (where something is, as edges from 0 to 1). Model-backed; built on Jev features its maker labels experimental.
    • POST /v1/judge/locate (preview) finds up to four things in one image, each with whether it is there and its box.
    • POST /v1/judge/long (preview) runs /v1/judge's questions…
    View evidence

  3. Questions about images, and search that forgives a typo

    AnnouncementSource linked

    POST /v1/judge/vision (preview) asks typed questions about up to four PNG or JPEG images: a yes or no probability, a choice, a score, or a box that says where something is, as edges from 0 to 1. Name each image and refer to it as name in a question. Built on Jev features its… Show all

    POST /v1/judge/vision (preview) asks typed questions about up to four PNG or JPEG images: a yes or no probability, a choice, a score, or a box that says where something is, as edges from 0 to 1. Name each image and refer to it as name in a question. Built on Jev features its maker labels experimental, and model-backed. POST /v1/judge/locate (preview) finds up to four things in one image: each comes back with whether it is there and its box. A box is always returned, so found reads false when the model judges the thing absent. POST /v1/judge/long (preview) runs /v1/judge's questions over a…

    View evidence

  4. Code changes, week of 2026-10-05 – 2026-10-11 · at least 461 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    at least 4 active days in mikeypetrillo/agent402 since 2026-10-08; the count stops at the newest 100 commits listed.

    This week HEY looked inside 3 of 461 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count.

    View evidence

  5. A third model behind every judgment

    Feature releaseSource linked

    /v1/judge adds microsoft-decision-1 as a backend. The default order is now jev-latest, then microsoft-decision-1, then gpt-6-luna; name any one first with model. The answer names the model that served, and fallbackFrom when the first was unavailable.

    View evidence

  6. v2.6.0: collect slow reports later, richer SEC pages, and clearer refusals

    GitHub releaseSource verified

    Tagged 2026-10-08. One line per change; the mechanism behind each is on agent402.tools/changelog. Buyers · Slow routes (reports, video, the premium image, /api/decide/execute) accept Prefer: respond-async on a paid call: 202 with a job link at once, then GET /api/jobs/{id}… Show all
    • Tagged 2026-10-08. One line per change; the mechanism behind each is on agent402.tools/changelog. Buyers
    • Slow routes (reports, video, the premium image, /api/decide/execute) accept Prefer: respond-async on a paid call: 202 with a job link at once, then GET /api/jobs/{id} (free) returns the answer. Payment still settles only on a delivered answer; a failed run is not charged.
    • Every slow route states how long it can take and a client timeout that outlasts it.
    • An Idempotency-Key call sent again while its first copy is still running gets…
    View evidence

  7. Collect slow reports later, and richer free SEC pages

    Feature releaseSource linked

    A paid call to a slow route (reports, video, the premium image, decide execute) can send Prefer: respond-async: it answers 202 with a job link at once, and GET /api/jobs/{id} returns the answer when it is ready. Payment still settles only on a delivered answer; each slow route… Show all

    A paid call to a slow route (reports, video, the premium image, decide execute) can send Prefer: respond-async: it answers 202 with a job link at once, and GET /api/jobs/{id} returns the answer when it is ready. Payment still settles only on a delivered answer; each slow route now says how long it can take. An Idempotency-Key call sent again while its first copy is still running gets 409 with Retry-After instead of running twice. On the chat wires, a model provider refusing the request itself answers 400 with the reason, after failover has tried the next model. The free SEC company pages add…

    View evidence

  8. v2.5.0: ElevenLabs voices, Decide plans, Claude Code on a wallet, and a live payments view

    GitHub releaseSource verified

    Tagged 2026-10-07. One line per change; the mechanism behind each is on agent402.tools/changelog. Buyers · /api/tts and /api/tts-hd speak with ElevenLabs Eleven v4 Turbo and Eleven v4: ten distinct voices, 21 ElevenLabs voices by name, six formats, with a named backup when the… Show all
    • Tagged 2026-10-07. One line per change; the mechanism behind each is on agent402.tools/changelog. Buyers
    • /api/tts and /api/tts-hd speak with ElevenLabs Eleven v4 Turbo and Eleven v4: ten distinct voices, 21 ElevenLabs voices by name, six formats, with a named backup when the primary is busy.
    • Add diarize: true (speaker labels and word timestamps) on /api/transcribe, /api/transcribe-pro and the OpenAI transcription wire.
    • Add POST /api/decide (a call-ready plan for a task) and POST /api/decide/execute (runs it within a budget; unspent…
    View evidence

  9. ElevenLabs voices and speaker labels

    AnnouncementSource linked

    /api/tts now speaks with ElevenLabs Eleven v4 Turbo and /api/tts-hd with Eleven v4: each of the ten voice names has its own voice, 21 ElevenLabs voices can be named directly, and all six formats (mp3, opus, aac, flac, wav, pcm) are served. Transcription takes diarize:true for… Show all

    /api/tts now speaks with ElevenLabs Eleven v4 Turbo and /api/tts-hd with Eleven v4: each of the ten voice names has its own voice, 21 ElevenLabs voices can be named directly, and all six formats (mp3, opus, aac, flac, wav, pcm) are served. Transcription takes diarize:true for speaker labels and word timestamps from ElevenLabs Scribe v2, on /api/transcribe, /api/transcribe-pro and the OpenAI transcription wire, at the same price and cap. /api/tts and /api/tts-hd are repriced for the ElevenLabs models; current prices are on /pricing and in every 402. Most published examples now fetch from…

    View evidence

  10. Claude Code pays from a wallet

    Feature releaseSource linked

    The local proxy (agent402-openclaw 0.5.0, npx agent402-openclaw proxy) now answers the Anthropic Messages wire too: point Claude Code at it with ANTHROPIC_BASE_URL and each turn is paid from your wallet over x402, no key to buy.. The metered Messages route no longer refuses a… Show all

    The local proxy (agent402-openclaw 0.5.0, npx agent402-openclaw proxy) now answers the Anthropic Messages wire too: point Claude Code at it with ANTHROPIC_BASE_URL and each turn is paid from your wallet over x402, no key to buy.. The metered Messages route no longer refuses a thinking budget that only collides with its output cap: the budget is clamped along with max_tokens, so Claude Code on Haiku works..

    View evidence

  11. Code changes, week of 2026-09-28 – 2026-10-04 · at least 450 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    at least 7 active days in mikeypetrillo/agent402 since 2026-09-28; the count stops at the newest 100 commits listed.

    This week HEY looked inside 3 of 450 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count. 3 automated commits (bot accounts or a repeating scripted message) not counted.

    View evidence

  12. Purchases from other sellers run inside the buyer's authorization, and the paid path has two observers

    AnnouncementSource linked

    route-execute and seller-payability pay another seller for an EVM buyer only while the buyer's own authorization can still settle after that seller answers. With too little of the window left they answer 504 before paying anyone, and nothing is charged. A stock client's… Show all

    route-execute and seller-payability pay another seller for an EVM buyer only while the buyer's own authorization can still settle after that seller answers. With too little of the window left they answer 504 before paying anyone, and nothing is charged. A stock client's 300-second window always has room, and a payability check run in a shorter window says so in its flags.. On the report products, a wallet's concurrent runs are admitted while its balance covers them together. A run the balance cannot also cover answers 429 before it starts, and nothing is charged.. A paid call to another…

    View evidence

  13. The 402 body carries the payment requirements

    Feature releaseSource linked

    Every 402 from the paywall carries the same payment requirements in its JSON body as in the PAYMENT-REQUIRED header: x402Version, resource, accepts and extensions. A refused payment keeps its own explanation in the body beside them.. agent402-mcp 0.13.5, agent402-openclaw 0.4.4… Show all

    Every 402 from the paywall carries the same payment requirements in its JSON body as in the PAYMENT-REQUIRED header: x402Version, resource, accepts and extensions. A refused payment keeps its own explanation in the body beside them.. agent402-mcp 0.13.5, agent402-openclaw 0.4.4 and agent402-client 0.8.9 report a refused payment by its reason.. A paid call whose buyer disconnects before the answer is sent is not settled, within a daily allowance. Routes whose effect outlives the answer (memory writes, attestations, feedback, and purchases from other sellers) settle as before, and an…

    View evidence

  14. Code changes, week of 2026-09-21 – 2026-09-27 · at least 72 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    at least 3 active days in mikeypetrillo/agent402 since 2026-09-24; the count stops at the newest 100 commits listed.

    This week HEY looked inside 3 of 72 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count.

    View evidence

  15. Integration and learn pages

    IntegrationSource linked

    The four Polymarket tools are retired. Each route answers 410 naming the nearest Kalshi tool: kalshi-markets for search and order books, kalshi-event for one market, kalshi-live-data for price history.. New /integrations pages for every published package and /learn explainers… Show all

    The four Polymarket tools are retired. Each route answers 410 naming the nearest Kalshi tool: kalshi-markets for search and order books, kalshi-event for one market, kalshi-live-data for price history.. New /integrations pages for every published package and /learn explainers for x402, HTTP 402, MPP and agent payments.. /llms-full.txt lists every catalog route with its price.. Tool pages now show parameters, example requests and responses, and related tools.. Model gateway: gpt-6-luna is the nano default and leads the auto router's fast band, gpt-6-sol is on the pro tier, Claude Opus 5.5…

    View evidence

  16. Five explorer-backed tools retired, and token-risk reads its facts from keyless probes

    AnnouncementSource linked

    contract-inspect, address-profile, token-info, token-holders and tx-inspect are retired. Each route answers 410 naming its replacement where there is one: contract-inspect to contract-source, address-profile to wallet-balance, token-info to token-metadata, tx-inspect to… Show all

    contract-inspect, address-profile, token-info, token-holders and tx-inspect are retired. Each route answers 410 naming its replacement where there is one: contract-inspect to contract-source, address-profile to wallet-balance, token-info to token-metadata, tx-inspect to tx-receipt. token-holders names none, because nothing in the catalog reads a holder list for an arbitrary token.. token-risk and token-risk-pro read every token fact from keyless probes instead: name, symbol, supply, holder count and the top holders with their share come from the token-security probe, the market from the…

    View evidence

  17. Typed judgments, a router that says who it is, and a leaderboard that reads the seller's own prices

    Feature releaseSource linked

    POST /v1/judge ($0.001): a typed judgment over supplied state · a choice from your named options with a probability for each, a position on levels you describe, or a yes/no as a probability. Model-backed, declared as such, input bounded by bytes so the worst case is knowable… Show all
    • POST /v1/judge ($0.001): a typed judgment over supplied state
    • a choice from your named options with a probability for each, a position on levels you describe, or a yes/no as a probability. Model-backed, declared as such, input bounded by bytes so the worst case is knowable before the call.. The router identifies itself on every paid call it makes on a buyer's behalf: User-Agent Mozilla/5.0 (compatible; Agent402-Router/1.0; +https://agent402.tools/crawler) and X-Agent402-Via: router; /crawler documents both.. A seller origin on a non-default port is accepted at x402 registration, MPP…
    View evidence

  18. Code changes, week of 2026-09-14 – 2026-09-20 · at least 151 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    at least 3 active days in mikeypetrillo/agent402 since 2026-09-18; the count stops at the newest 100 commits listed.

    This week HEY looked inside 3 of 151 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count. 3 automated commits (bot accounts or a repeating scripted message) not counted.

    View evidence

  19. Equities on a licensed feed, five tools and a pack retired, credits sales paused

    AnnouncementSource linked

    stock-quote and stock-history read Databento DBEQ.BASIC (four venues, consolidated per session): volume is reported as venueVolume, stock-history takes up to 250 sessions, and the 52-week high/low fields are gone. options-chain, premarket-quote, stock-dividends… Show all

    stock-quote and stock-history read Databento DBEQ.BASIC (four venues, consolidated per session): volume is reported as venueVolume, stock-history takes up to 250 sessions, and the 52-week high/low fields are gone. options-chain, premarket-quote, stock-dividends, earnings-calendar, dividend-calendar and the market-open skill pack are removed.. Prepaid card credits are no longer sold; existing keys keep redeeming.. Google's native generateContent wire on every gateway tier; POST /v1/audio/transcriptions (OpenAI transcription wire, multipart); service_tier "priority" on the pro and premium…

    View evidence

  20. v2.4.0: @x402 2.26 on our own handshake, Astra and Fable on premium, effort on the Messages wire, and a router that indexes

    GitHub releaseSource verified

    v2.4.0: @x402 2.26 on our own handshake, Astra and Fable on premium, effort on the Messages wire, and a router that indexes Every merge since v2.3.0 (2026-09-02 to 2026-09-18). Each change was verified against production the day it merged; the two live proofs still owed before… Show all
    • v2.4.0: @x402 2.26 on our own handshake, Astra and Fable on premium, effort on the Messages wire, and a router that indexes Every merge since v2.3.0 (2026-09-02 to 2026-09-18). Each change was verified against production the day it merged; the two live proofs still owed before this tag are listed at the end. Buyers
    • Two more frontier models on the premium tier. openai/gpt-6-astra and anthropic/claude-fable-5.1 are admitted at $0.50 on /v1/premium/chat/completions and the Messages and Responses wires ($10/$50 headline, 1M context, reasoning mandatory). A 4k-char prompt…
    View evidence

  21. Settlement evidence read from the chain on every rail we pay on, an identity of our own, and a monthly view

    AnnouncementSource linked

    Settlement evidence no longer depends on a third party's registry. The Base scan seeds its wallet list from our OWN crawl as well as Coinbase's Bazaar: an origin we indexed ourselves, payTo read from its own live 402, could settle any volume on chain and stay settled:null, which… Show all
    • Settlement evidence no longer depends on a third party's registry. The Base scan seeds its wallet list from our OWN crawl as well as Coinbase's Bazaar: an origin we indexed ourselves, payTo read from its own live 402, could settle any volume on chain and stay settled:null, which the router reads as settlement_required forever. Reported by a seller whose payTo appears in none of the 15,636 Bazaar rows. It stays a seed and never evidence
    • the chain decides what settled, and the payTo binding that stops a seller inheriting another wallet's volume is untouched. Algorand was the same shape and…
    View evidence

  22. Code changes, week of 2026-09-07 – 2026-09-13 · at least 143 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    3 active days in MikeyPetrillo/Agent402.

    This week HEY looked inside 3 of 143 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count. 1 automated commit (bot accounts or a repeating scripted message) not counted.

    View evidence

  23. Code changes, week of 2026-08-31 – 2026-09-06 · at least 197 commits

    Code activitySource linked

    What changed, in the repository’s own words:

    5 active days in MikeyPetrillo/Agent402.

    This week HEY looked inside 3 of 197 commits to see what changed: 3 changed code. In a burst week, enough of a sample has to change code for the week to count. 3 automated commits (bot accounts or a repeating scripted message) not counted.

    View evidence

  24. v2.3.0: Typed 402s, tokenized assets, MPP on the edge, and two alarms that stopped lying

    GitHub releaseSource verified

    Thirty PRs merged on 2026-09-02, every one verified on production the same day. Buyers · Typed 402s. Every challenge carries the typed output schema as accepts[0].outputSchema (one copy, first accept) as well as in the bazaar extension, and every route validates under… Show all
    • Thirty PRs merged on 2026-09-02, every one verified on production the same day. Buyers
    • Typed 402s. Every challenge carries the typed output schema as accepts[0].outputSchema (one copy, first accept) as well as in the bazaar extension, and every route validates under @x402/core's own schemas. Stock x402 clients, native MPP buyers and mppx x402 buyers all still settle.
    • Tokenized real-world assets. rwa-list, rwa-markets, rwa-asset, rwa-issuers, rwa-issuer: 649 tokenized stocks, ETFs and commodities with onchain market data and the 33 issuers behind them, $0.003 to…
    View evidence

Research notes

Written by HEY researchers and reviewed before publishing. Commentary with sources — not the project's own claims, and not evidence of shipping.

Know something about Agent402? Sign in with GitHub to submit a research note. Notes are reviewed before they appear here.

What changed

51 changes on HEY’s record for Agent402: 24 releases · 17 other ships · 2 build pace changes · 8 weeks of code pushed.

All 51 changes for Agent402 →

The full change record holds 30 more, of kinds this list leaves out — lock records and HEY’s own research bookkeeping among them. Full record (JSON)

Research coverage

HEY can answer 10 of the 11 research questions that apply.

10 of 11 applicable dimensions measuredShow each dimension

Identity

  • IdentityMeasuredRead 1mo ago.

Building

  • Building activityMeasuredRead 12m ago.
  • RepositoriesMeasured
  • ReleasesMeasuredRead 3d ago.
  • TimelineMeasured

Official site

  • Official docsMeasuredRead 1h ago.
  • API descriptionSource unavailableThe API description it links could not be read.
  • Official site changesMeasuredRead 21d ago.

Code and packages

  • Repository detailsMeasuredRead 15h ago.
  • Published packagesMeasuredRead 30m ago.
  • Package advisoriesMeasuredRead 9h ago.

Not applicable here: Contract creation, Contract activity, Verified source, Contract interface, Current market, Market history, Supply distribution, Locks, Market checks, Protocol economics.

A count of what HEY has read, never a score: projects are not compared or ordered by it. Unknown is never zero. The same states: coverage API.

Sources

23 more sources (docs)

Security context: 1 audit report found · a published security contact. An audit shows an audit took place; it is not a guarantee of safety.