buy

Find and buy products, tickets, bookings and subscriptions for the user at supported stores. Start with `search` { query } to find the item and merchant page using Vaaya OneSearch (5¢ per search); the user can describe what they need without supplying a link. Before checkout, use `setup` to check payment and shipping readiness; resolve missing setup once. Persistent merchant accounts are managed at /store-connections. Use store_connection_id to select an account. Passwords and verification codes belong only on the merchant page, never in chat. PRODUCT DISCOVERY: if the user describes what to buy but provides no URL, use `search` { query: <product, variant, budget and preferred merchant if specified> } to locate it under the existing tool spending permissions; do not ask them to paste a link or say search for it first. Search is not purchase authorization. Respect search fees and spending limits; if search is unavailable, explain the actual error and then ask for a link. Verify the merchant, item and variant from the result; ask only when matches are ambiguous or details cannot be verified. Never invent a product URL, final total or delivery date from a search snippet. THE SEAMLESS PATH: once the user has told you what to buy and you have the exact item, merchant page URL and total, call `purchase` { item, merchant, url, total_cents, confirmed: true, confirmation: <the user's own words> } — it approves from their message (under the chat limit), starts buying in the user's cloud browser in the background and returns `message` ("Hold on — buying it now."): RELAY IT, then poll `status` { approval_id } every ~10 seconds and relay its `message` when the status is completed ("Done — …"), requires_action (read action_required.reason for the exact blocker) or failed. If `status` says the user's shipping address is missing, ask for it and call `address` { name, line1, line2?, city, state?, postal_code, country, phone? } then `checkout` { approval_id } to resume; if merchant authentication is pending, relay handoff_url and handoff_deadline. The durable worker checks authentication and resumes the same authorized purchase automatically. Do not ask the user to send done or submit codes in chat. If the handoff expires, relay the recovery page; it does not clear order or payment uncertainty. Other sub-commands: `search` { query } (protocol merchants plus a real web search; the web half bills 5¢), `propose` { item, merchant, total_cents, url?, notes?, confirmed?, confirmation? } (creates an approval; without `confirmed` it returns an approval link the user opens — show its `message` VERBATIM), `checkout` { approval_id, params? } (buys an approved purchase; for a browser merchant it runs in the background like `purchase`). Use the user's existing authorization of the exact item and total; do not ask them to confirm twice. Ask only for missing purchase details. Nothing is ever bought without the user's yes: `checkout` refuses anything else. Use `reconcile` { approval_id } after an uncertain submission: it only inspects the existing checkout and never submits payment. For an unavailable checkout or inconclusive reconciliation, relay recovery_url and recovery_instructions from status. The user can resolve the attempt on its approval page only after checking both merchant orders and payment records. A chat statement alone does not clear the lock, and expiration does not clear it. If status or replay says purchase_resolved, never reuse checkout on that approval. When the user requests another attempt, call propose with retry_of set to that resolved ID, current item/price and no confirmed flag, then show the new approval link. Check setup browser_allowance first; a daily_browser_limit requires waiting until resets_at, not reconnecting or changing request text. For a handoff, return action_required.url and the deadline. The user fixes 2FA, CAPTCHA, payment, address or booking issues on that authenticated page and uses Return control to Vaaya; do not call checkout to bypass a pending handoff. Status polling never creates a replacement. Resume only the same approval_id; do not recreate a purchase to bypass an unresolved attempt. `charged_cents` is the Vaaya tool fee, NOT a merchant charge; read merchant_payment separately, and never infer a hold or capture from Link approval. Never open `browserbase` sessions yourself to buy something — only `buy` can.

Argument	Type	Description
url	string	The exact product page the item came from — the driver starts there (`purchase`, `propose`).
city	string	City (`address`).
item	string	What exactly is being bought, in the user's words — variant, size, quantity (`purchase`, `propose`).
name	string	Full name for shipping (`address`).
email	string	Contact email for the order; defaults to the account email (`address`).
line1	string	Street address (`address`).
line2	string	Apartment / unit (`address`).
notes	string	One line for the driver/user: variant, size, colour, quantity, delivery window.
phone	string	Contact phone for delivery (`address`).
query	string	Describe the product, variant, budget and preferred store if any. `search` uses OneSearch to find matching items and merchant pages (5¢).
state	string	State / region (`address`).
params	object	The merchant's own purchase body (product id, quantity, email, shipping) for a protocol merchant (`purchase`, `checkout`).

close

Close an E2B sandbox session and stop its billing. Pass the `session_id`. Captures the final metered uptime cost and releases the hold. ALWAYS call this when finished with a session — an open session keeps billing per second of uptime. Safe to call repeatedly (idempotent).

Argument	Type	Description
session_id*	string	The session_id to close.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "The session_id to close."
    }
  }
}

consult

Vaaya's consultant. Describe ANY external capability you or the user might want — generate an image/video, search or scrape the web, run code in a sandbox, send/receive email, enrich a contact — and it helps figure out the best way, teaching the user what Vaaya can do. It is CONVERSATIONAL and remembers prior turns. It returns: mode='converse' (a reply to RELAY to the user verbatim — questions, options, ideas; get the user's response and call consult again with it, so the conversation continues), mode='call' (an ordered list of calls to run via `use`, with a message explaining the preferred choice + alternatives + why; multi-step results may contain placeholders like '<from step 1: sandbox_id>' — run earlier steps first and substitute), or mode='unsupported'. Every reply includes `suggestions` (2-3 things to do next) — surface these to the user. AFTER you run a `call` result's calls via `use`, call consult ONE more time with a short note on the outcome (what was produced / any failures) — it returns result-aware, Vaaya-grounded next steps to offer the user (the `call` result's `after_running` field reminds you). Call consult whenever you hit a capability gap or the user wants to know what's possible. It does NOT execute or bill — you run returned calls via `use`. ALWAYS show the user consult's `message` and `suggestions` and let them steer.

read-only

Argument	Type	Description
intent*	string	Plain-English description of what you want, or your answer to a previous clarify question. Be concrete — include the prompt text, URL, budget, or target the task implies.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "intent"
  ],
  "properties": {
    "intent": {
      "type": "string",
      "description": "Plain-English description of what you want, or your answer to a previous clarify question. Be concrete — include the prompt text, URL, budget, or target the task implies."
    }
  }
}

docs

Vaaya's deep reference, FREE and instant. Pass `topic` to get the full playbook for a capability area — exact services, actions, params, prices, model lists, and gotchas — the same reference files the vaaya skill ships. Topics: 'setup' (connecting an agent, a chat app, or an unattended process), 'tools' (exact params of every Vaaya tool, GTM suite included), 'media' (image/video/audio models + product-demo videos), 'gtm' (leads, enrichment, outreach, signals, email), 'research' (OneSearch lanes, deep research, company/market research playbooks), 'data' (scraping, people, social platforms, public records, onchain, compliance), 'compute' (sandboxes, browser automation, files, memory, workers, phone calls, llm). Read the matching topic BEFORE non-trivial work in that area — it is cheaper than a wrong call. Never bills; safe to call any time.

read-only

Argument	Type	Description
topic*	string	Which reference to fetch.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "topic"
  ],
  "properties": {
    "topic": {
      "enum": [
        "setup",
        "tools",
        "media",
        "gtm",
        "research",
        "data",
        "compute"
      ],
      "type": "string",
      "description": "Which reference to fetch."
    }
  }
}

jobs

Jobs: a marketplace where humans hire humans, and each side's agent handles the steps. Call with { action, ...params }. Actions: list, get, mine, draft, update_draft, cancel, accept, submit_proof, record_verdict, request_release, dispute. A poster's agent drafts a job (budget_usd, definition_of_done, required_evidence) and gives its human the review_url; the HUMAN publishes, which holds the budget from their wallet. A doer's agent accepts an open job for its human and later submits that human's proof (summary + links). The poster's agent evaluates the proof against the definition of done with record_verdict. Only the poster, in their own browser on the job page, can release payment; no action here moves money to anyone. Never claim the agent did the work.

Argument	Type	Description
gaps	array	record_verdict: what is missing.
note	string	request_release: an optional note to the poster.
links	array	submit_proof: http(s) links to the evidence.
title	string	draft / update_draft: 5-120 characters.
action*	string	list (anyone): Lists jobs, newest first. get (anyone): Returns the job contract; parties also see proof, verdict reasons and the payment reference. mine (anyone): Jobs your human posted or is doing. draft (poster): Saves a draft and returns review_url. Nothing is held until your human opens review_url and publishes. update_draft (poster): Edits a draft. cancel (poster): Deletes a draft, or cancels an open job. An open job’s hold returns in full. accept (doer): Accepts an open job for your human, who then does the work. submit_proof (doer): Submits your human’s proof of work against the definition of done and required evidence. record_verdict (poster): Records your evaluation of the latest proof. It is a recommendation; it never pays. request_release (doer): Asks the poster to review and release. It is a request; it never pays. dispute (either party): Freezes the job; the money stays held for support

llm

Ask a DIFFERENT LLM a question and get its answer, billed per token from the Vaaya wallet (model cost + 3%, usually a fraction of a cent). Use it to get a second opinion from a rival model, cross-check an answer, summarize a huge blob cheaply, or query a specific model the user names (Kimi, GPT, Gemini, Claude, DeepSeek, and 300+ more). `model` accepts 'auto' (default: short prompts go cheap, long go mid), 'cheap' | 'mid' | 'best' tiers, or any exact OpenRouter slug like 'moonshotai/kimi-k3'. Typical costs: cheap tier well under 0.1 cents, best tier 1-3 cents per call. Not for the conversation you are already having — it is a one-shot ask to another model.

Argument	Type	Description
model	string	'auto' (default), 'cheap', 'mid', 'best', or an exact OpenRouter model slug (e.g. 'moonshotai/kimi-k3', 'anthropic/claude-opus-5').
prompt*	string	The question or task for the other model.
system	string	Optional system prompt for the other model.
max_tokens	number	Optional cap on the response length in tokens (default 4096, max 16384).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "'auto' (default), 'cheap', 'mid', 'best', or an exact OpenRouter model slug (e.g. 'moonshotai/kimi-k3', 'anthropic/claude-opus-5')."
    },
    "prompt": {
      "type": "string",
      "description": "The question or task for the other model."
    },
    "system": {
      "type": "string",
      "description": "Optional system prompt for the other model."
    },
    "max_tokens": {
      "type": "number",
      "description": "Optional cap on the response length in tokens (default 4096, max 16384)."
    }
  }
}

result

Fetch the status + output of an async job started by `use` (e.g. a video render). Pass the `job_id` that `use` returned with `{ async: true }`. Returns `{ status, result?, progress?, charged_cents }`: `running` (still working — when the job reports it, `progress` carries `{ phase, percent, rendered_frames, total_frames, eta_sec }` and `hint` is a one-line summary like "rendering 42% (380/900 frames, ~120s left)", so you can tell real progress from a hang; wait a bit and call again), `succeeded` (`result` holds the output, e.g. the video URL; the call is charged now), or `failed`/`cancelled` (no charge; on `failed`, read `error` AND `hint` — `hint` carries the service's usage notes, which usually explain how to fix the call). Safe to call repeatedly — it never starts new work or double-charges. ALWAYS use this to retrieve an async result instead of re-running `use` (re-running starts a new paid job).

read-only

Argument	Type	Description
job_id*	string	The job_id returned by an async `use` call.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The job_id returned by an async `use` call."
    }
  }
}

session

Run a command or code in an open E2B sandbox session (started by `use` with action `create_session`, which returns a `session_id`). Pass `session_id` plus either `command` (a shell command) or `code` (+ optional `language`: python/javascript/bash). Returns stdout/stderr/exit_code (or the code result). The sandbox stays alive — and billed per second of uptime — until you `close` it; re-running reuses the SAME box, so filesystem + process state persist between calls. ALWAYS `close` when done.

Argument	Type	Description
code	string	Code to execute (alternative to `command`).
command	string	Shell command to run in the sandbox.
language	string	Language for `code`: python (default), javascript, or bash.
session_id*	string	The session_id returned by create_session.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "session_id"
  ],
  "properties": {
    "code": {
      "type": "string",
      "description": "Code to execute (alternative to `command`)."
    },
    "command": {
      "type": "string",
      "description": "Shell command to run in the sandbox."
    },
    "language": {
      "type": "string",
      "description": "Language for `code`: python (default), javascript, or bash."
    },
    "session_id": {
      "type": "string",
      "description": "The session_id returned by create_session."
    }
  }
}

stocks

Buy tokenized stocks on Base using only the user’s prepaid Vaaya balance, never the welcome credit or the GitHub credit line. Commands: list (supported token tickers), portfolio (owned stocks and buying power), quote {symbol, amount_cents}, buy {symbol, amount_cents, idempotency_key}, order {order_id}. When the user asks to buy a specified stock and dollar amount, resolve its supported token ticker (Apple = AAPLc) and call buy directly; no activation or additional approval step. amount_cents is the maximum total prepaid spend including provider fees. Use a unique idempotency_key for each intended purchase and reuse it on retries. Query order until confirmed/failed; queued/submitted is not success. Do not increase the user’s spend or retry a failed purchase as a new order without instruction. Ask only for missing or ambiguous purchase details. If prepaid_required or buyingPowerCents is insufficient, offer a $14/$40/$60 prepaid pack: POST /api/v1/topup with pack_cents 1400/4000/6000 and the same account bearer token returns a Stripe Checkout url. With authorization for that pack amount, the user’s Instinct agent can pay the URL in its browser using the card saved in Instinct; otherwise give the URL to the user. Vaaya cannot charge Instinct’s card directly. Do not include card details or tokens in a handoff. Check GET /api/v1/wallet wallet.prepaid_cents, then portfolio buyingPowerCents before resuming the same purchase key. A share purchase alone does not authorize a top-up. Stop on needs_review as well as failed.

Argument	Type	Description
symbol	string	Token ticker from list, e.g. AAPLc. Required for quote and buy.
command*	string	list (supported tickers), portfolio (holdings + buying power), quote, buy, or order (status by id).
order_id	string	Order id returned by buy. Required for order.

use

Execute a single external call, and bill on success. Used for any external capability (image/video/audio generation, web search, scraping, email, document parsing, code sandbox, browser automation, embeddings, etc.). The server validates params against a registered schema and proxies to the upstream — you never pass URLs or API keys. Call it directly when you know the exact (service, action, params, max_cost_cents) — from the vaaya skill's catalog or a call you've made before; when unsure, get the call from `consult` rather than guessing.

Argument	Type	Description
action*	string	Action within the service (e.g. "search", "generate", "create_session"), taken from the call `consult` returned.
intent	string	Optional: the one-line `why` from the consult call you're running (or the user's goal for it). Used only for internal transaction visibility — it never affects validation, billing, or execution. Pass it through when you have it.
params*	object	Parameters from the call `consult` returned, validated against the service's registered schema.
service*	string	Service identifier, taken verbatim from the call `consult` returned.
max_cost_cents*	number	Hard ceiling in cents on what you will be charged. `use` refuses if the registry price exceeds this. Pick at least 2× the listed price so retries work.

Input schema (JSON)

vaaya_account

Show which Vaaya account this connection is linked to and its money state. Returns { email, name, user_id, connected_client, scopes, balance_cents, credit_line, available_cents, credits_url, switch_account }. Call it whenever the user asks "which account is connected", "what's my balance", "how much credit is left", or "how do I switch accounts" — and relay the answer. `credit_line` is the credit the account can spend past its prepaid balance (the welcome credit plus any GitHub-score line); `available_cents` = balance + active line, the number calls are gated on.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

vaaya_logout

Disconnect this client from the current Vaaya account: revokes this connection's authorization server-side, so every later call fails with 401 until the user reconnects. Call it when the user asks to log out, sign out, disconnect, or switch Vaaya accounts — then relay the returned switch steps VERBATIM (the browser sign-out step is what actually enables switching accounts).

destructive

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

vaaya_onboard

Public onboarding hint for an agent whose user isn't linked to Vaaya yet. Returns where the human should go to connect (and sign up if new). Call this when vaaya_test_connection reports needs_auth, or any tool returns unauthorized, then relay the instructions to the user. If the user IS already linked it returns `first_call` instead — show `first_call.show_to_user` as written so they know what to try.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

vaaya_test_connection

Round-trip ping that confirms the agent → Vaaya connection and whether the user is linked. Returns { ok:true, userId, scope, version, server_time, first_call } when linked — SHOW `first_call.show_to_user` to the user as written, it is the same set of starter examples the website and installer give them. Returns { ok:false, needs_auth:true, verification_uri, signup_uri, instructions } when not linked yet — relay that to the user so they can connect (and sign up if new).

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

Vaaya

Try it

buy

Vaaya

Try it

buy

Tools (14)