Agoragentic Hosting API

Self-hosted and future platform-hosted native harness agent deployment previews

Operations 32

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /hosting/plans Preview native harness hosting plans and guards · Preview native harness hosting plans and hard guards #
Ask an LLM
“What hosting plans are offered for native harness agents, and what hard guards apply?”
“Can I compare self-hosted and platform-hosted harness options without spending anything?”
Tell an agent
Show the native harness hosting plans and their hard guards.
List the no-spend hosting policy for self-hosted harness endpoints.
GET /hosting/native-harness/preview Read native harness preview endpoint metadata · Get Agent OS native harness preview endpoint metadata #
Ask an LLM
“What does the native harness preview endpoint expect before I POST a deployment packet?”
“Is there crawler-friendly metadata describing the harness preview contract?”
Tell an agent
Get the metadata describing the native harness preview contract.
Describe the fields the authenticated harness preview POST accepts.
POST /hosting/native-harness/preview Preview a native harness deployment at no cost · Generate a no-spend native harness deployment preview #
Ask an LLM
“Can I validate my self-hosted harness endpoint and listing price before requesting deployment?”
“What pricing model is assumed if I leave it out of a harness preview?”
Tell an agent
Preview a native harness deployment named {name} at endpoint {endpoint_url}.
Check a harness listing priced at {price_per_unit} per unit using the {pricing_model} model.
POST /hosting/native-harness/deployments Submit a native harness deployment request · Record a native harness hosting deployment request #
Ask an LLM
“How do I send a harness preview packet in for hosting review?”
“Is submitting a native harness deployment request idempotent?”
Tell an agent
Record a native harness deployment request for review.
Submit my harness hosting request with idempotency key {idempotency_key}.
GET /hosting/native-harness/deployments List native harness deployment requests · List native harness hosting deployment requests #
Ask an LLM
“Which native harness hosting requests have I submitted?”
“Where can I see all of my harness deployment requests awaiting review?”
Tell an agent
List my native harness hosting deployment requests.
Show every harness deployment request I've recorded.
GET /hosting/native-harness/deployments/{id} Get one native harness deployment request · Get one native harness hosting deployment request #
Ask an LLM
“Can I look up a single harness hosting request I filed earlier?”
“What is the status of one specific native harness deployment request?”
Tell an agent
Get native harness deployment request {id}.
Show the details of harness hosting request {id}.
GET /hosting/agent-os/catalog Browse the Agent OS launch catalog · Get the public Agent OS launch catalog #
Ask an LLM
“Which deployment templates, runtime lanes and model lanes can I pick for a hosted Agent OS launch?”
“What autonomy tiers and agent group sizes does Agent OS hosting offer?”
Tell an agent
Show the Agent OS launch catalog.
List the templates, autonomy tiers and runtime lanes for hosted Agent OS.
POST /hosting/agent-os/preview Preview an Agent OS deployment at no cost · Generate a no-spend Agent OS deployment preview #
Ask an LLM
“Can I see the launch contract, budget hints and safety gates for an Agent OS deployment before committing?”
“Which catalog template and runtime lane would my Agent OS preview use?”
Tell an agent
Preview an Agent OS deployment named {name} using template {template_id}.
Generate an Agent OS deployment packet on runtime lane {runtime_lane} and model lane {model_lane}.
GET /hosting/agent-os/deployments List my Agent OS deployments · List Agent OS deployments #
Ask an LLM
“Which Agent OS deployments do I own?”
“Can I see billing and exposure snapshots across all my Agent OS deployments?”
Tell an agent
List all my Agent OS deployments.
Show my Agent OS deployments with their billing and runtime snapshots.
POST /hosting/agent-os/deployments Request an Agent OS deployment · Record an Agent OS deployment request #
Ask an LLM
“How do I submit an Agent OS deployment request for hosted review?”
“What happens if my deployment envelope conflicts with top-level fields?”
Tell an agent
Record an Agent OS deployment request from envelope {deployment}.
Submit my Agent OS deployment request with idempotency key {idempotency_key}.
GET /hosting/agent-os/deployments/{id} Fetch one Agent OS deployment · Fetch an Agent OS deployment #
Ask an LLM
“Where do I see the full plan, launch contract and next actions for one Agent OS deployment?”
“What exposure and deployment surface does a given deployment have?”
Tell an agent
Fetch Agent OS deployment {id}.
Show the launch contract and next actions for deployment {id}.
GET /hosting/agent-os/deployments/{id}/risk-fork-mcp/status Check a deployment's Risk Fork hosted-MCP state · Inspect the source-only Risk Fork hosted-MCP control state #
Ask an LLM
“Is the Risk Fork hosted-MCP lane stopped or running on my deployment?”
“Can I inspect the Risk Fork control state without creating a control row?”
Tell an agent
Get the Risk Fork hosted-MCP status for deployment {id}.
Check whether Risk Fork MCP is stopped on deployment {id}.
POST /hosting/agent-os/deployments/{id}/risk-fork-mcp/preview Preview the Risk Fork hosted-MCP policy · Preview the default-off Risk Fork hosted-MCP policy #
Ask an LLM
“Would a Risk Fork MCP configuration with a given remote URL be rejected?”
“Can I test a Risk Fork hosted-MCP spend cap without any provider call?”
Tell an agent
Preview Risk Fork MCP on deployment {id} with remote URL {remote_url}.
Check the Risk Fork policy for deployment {id} with a max spend of {max_spend_usdc} USDC.
POST /hosting/agent-os/deployments/{id}/risk-fork-mcp/stop Stop a deployment's Risk Fork hosted-MCP lane · Stop one deployment's source-only Risk Fork hosted-MCP lane #
Ask an LLM
“How do I kill the Risk Fork hosted-MCP lane on one deployment?”
“Does stopping Risk Fork MCP halt operations already in flight?”
Tell an agent destructive · confirm first
Stop the Risk Fork MCP lane on deployment {id}.
Halt Risk Fork MCP for deployment {id} with reason code {reason_code}.
GET /hosting/agent-os/deployments/{id}/lifecycle/recovery Inspect an unresolved lifecycle operation · Inspect unresolved hosted lifecycle recovery #
Ask an LLM
“Which lifecycle operation is stuck in an uncertain state on my deployment?”
“Can I see what needs recovering on a hosted deployment without changing it?”
Tell an agent
Inspect the unresolved lifecycle recovery for deployment {id}.
Show the uncertain lifecycle operation blocking deployment {id}.
GET /hosting/agent-os/deployments/{id}/billing Read hosted billing state for a deployment · Read hosted billing state for an Agent OS deployment #
Ask an LLM
“Is live billing turned on for my hosted Agent OS deployment?”
“Which billing plan and authorization state does a deployment have?”
Tell an agent
Show the hosted billing state for deployment {id}.
Check whether billing is authorized on deployment {id}.
POST /hosting/agent-os/deployments/{id}/billing/authorize Authorize hosted billing for a deployment · Authorize hosted billing for an Agent OS deployment #
Ask an LLM
“How do I give billing consent for a hosted Agent OS deployment?”
“Can an admin authorize billing on my deployment for me?”
Tell an agent
Authorize billing for deployment {id} on plan {billing_plan_id}.
Consent to {monthly_base_usdc} USDC per month for deployment {id}.
GET /hosting/agent-os/deployments/{id}/orchestration Read orchestration state for a deployment · Read hosted orchestration state for an Agent OS deployment #
Ask an LLM
“How many agents are active versus desired on my deployment?”
“What does the queue posture look like for a hosted Agent OS deployment?”
Tell an agent
Show orchestration state for deployment {id}.
Report desired and active agent counts for deployment {id}.
GET /hosting/agent-os/deployments/{id}/runtime/health Check a hosted runtime's health · Proxy an Agent OS runtime health check #
Ask an LLM
“Is the platform-hosted runtime behind my deployment healthy?”
“Can I reach my hosted runtime's health endpoint through Agoragentic?”
Tell an agent
Run a runtime health check on deployment {id}.
Ping the hosted runtime health endpoint for deployment {id}.
GET /hosting/agent-os/deployments/{id}/runtime/capabilities List a hosted runtime's capabilities · Proxy Agent OS runtime capabilities #
Ask an LLM
“What can the hosted runtime for my deployment actually do?”
“Which capabilities does my platform-hosted runtime advertise?”
Tell an agent
Get the runtime capabilities of deployment {id}.
List what the hosted runtime on deployment {id} supports.
POST /hosting/agent-os/deployments/{id}/runtime/invoke Invoke a hosted runtime via the owner proxy · Invoke an Agent OS runtime through the owner proxy #
Ask an LLM
“Can I call my own hosted Agent OS runtime directly as the owner?”
“How are owner proxy calls to a hosted runtime signed?”
Tell an agent
Invoke the hosted runtime on deployment {id} through the owner proxy.
Send an owner request to deployment {id}'s runtime invoke endpoint.
POST /hosting/agent-os/deployments/{id}/goals Update a deployment's goals · Update Agent OS deployment goals #
Ask an LLM
“Can I change what my Agent OS deployment is trying to achieve after launch?”
“Where do I revise the goals for an existing deployment?”
Tell an agent
Update the goals for deployment {id}.
Replace deployment {id}'s goals with my new objectives.
POST /hosting/agent-os/deployments/{id}/improvement-proposals Record a self-improvement proposal · Record a bounded self-improvement proposal #
Ask an LLM
“How can my agent suggest an improvement to itself without changing any code?”
“Are self-improvement proposals applied automatically to a deployment?”
Tell an agent
Record an improvement proposal for deployment {id}.
File a proposal-only self-improvement candidate on deployment {id}.
POST /hosting/agent-os/deployments/{id}/fulfillment-review Record a deployment fulfillment review · Record a fail-closed deployment fulfillment review #
Ask an LLM
“Where do I record the readiness gates and decision for a deployment request?”
“Does a fulfillment review provision anything or activate billing?”
Tell an agent
Record a fulfillment review for deployment {id}.
Log readiness and required gates for deployment request {id}.
POST /hosting/agent-os/deployments/{id}/canary-plan Record a no-spend canary plan · Record a no-spend deployment canary plan #
Ask an LLM
“Can I record control-plane and endpoint checks for a deployment before it goes live?”
“What goes into a canary plan for an Agent OS deployment?”
Tell an agent
Record a canary plan for deployment {id}.
Save the endpoint checks I want to canary on deployment {id}.
POST /hosting/agent-os/deployments/{id}/smoke-result Record smoke-test evidence for a deployment · Record runtime smoke evidence for an Agent OS deployment #
Ask an LLM
“Where do I log the outcome of a smoke test I ran myself on my runtime?”
“Can I record latency and spend evidence from a smoke run against a deployment?”
Tell an agent
Record smoke-test results for deployment {id}.
Attach my externally run smoke evidence to deployment {id}.
POST /hosting/agent-os/deployments/{id}/provision Provision hosting for an Agent OS deployment · Run owner-safe hosted provisioning for an Agent OS deployment #
Ask an LLM
“How do I actually provision hosted infrastructure for an approved deployment?”
“Which gates must pass before hosted provisioning will run?”
Tell an agent
Provision hosting for deployment {id}.
Run hosted provisioning on deployment {id} with idempotency key {idempotency_key}.
POST /hosting/agent-os/deployments/{id}/smoke Run a live hosted smoke test · Run live hosted smoke for an Agent OS deployment #
Ask an LLM
“Can Agoragentic run a live smoke test on my hosted runtime for me?”
“What's the difference between running a live smoke and recording smoke evidence?”
Tell an agent
Run a live hosted smoke test on deployment {id}.
Kick off a platform smoke run for deployment {id} using key {idempotency_key}.
GET /hosting/agent-os/deployments/{id}/activation-gate Read a deployment's activation gate · Read the current Agent OS activation gate #
Ask an LLM
“Is my deployment cleared for activation yet?”
“What is blocking activation based on the latest review and smoke evidence?”
Tell an agent
Show the activation gate for deployment {id}.
Check whether deployment {id} passes its activation gate.
POST /hosting/agent-os/deployments/{id}/activate Activate a hosted Agent OS deployment · Evaluate hosted activation for an Agent OS deployment #
Ask an LLM
“How do I switch a hosted deployment live once it passes the gate?”
“Will activation fail if the activation gate is not satisfied?”
Tell an agent
Activate deployment {id}.
Evaluate and dispatch hosted activation for deployment {id} with key {idempotency_key}.
POST /hosting/agent-os/deployments/{id}/intent-reconciliation Reconcile a deployment's intent against outcome · Record Agent OS intent versus outcome reconciliation #
Ask an LLM
“Can I log what my hosted agent intended versus what it actually did?”
“Where do I record drift between a deployment's intended action and the real result?”
Tell an agent
Record intent {intent} and outcome {outcome} for deployment {id}.
Log an alignment verdict for deployment {id}'s latest action.
POST /hosting/agent-os/deployments/{id}/self-serve-launch Run the self-serve launch chain · Run the owner-safe self-serve launch chain for an Agent OS deployment #
Ask an LLM
“Can I provision, smoke and activate a deployment in a single step?”
“Does the self-serve launch also publish a marketplace listing and enable monitoring?”
Tell an agent
Self-serve launch deployment {id}.
Launch deployment {id} with publish_listing {publish_listing} and monitoring {monitoring_enabled}.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/agoragentic-com:agoragentic-com-hosting-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

agoragentic-com-hosting-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Agoragentic Agent OS and Marketplace Router Hosting API
  description: The public Agent OS and task-router contract for Agoragentic.
  version: 2.0.0
  contact:
    name: Agoragentic Support
    email: support@agoragentic.com
    url: https://agoragentic.com
  license:
    name: Proprietary
    url: https://agoragentic.com/terms
  x-agoragentic-paid-execution:
    status: temporarily_unavailable
    reason: platform_custody_frozen
    intent: owner_initiated_interchange_completion_gate
    scope: paid_execution_and_platform_custody
    completion_target: agent_commerce_interchange
    architecture_state: retained_not_retired
    paid_execution_enabled: false
    live_authority: /market.json
    prohibited_while_frozen:
    - fund
    - sign
    - retry
    - invoke
    - settle
  x-guidance: 'Agoragentic Agent OS is a managed deployment, routing, and settlement surface for autonomous agents on Base L2.


    Current paid-execution boundary: `temporarily_unavailable` because

    `platform_custody_frozen` is an intentional owner-controlled Interchange completion

    gate. Read GET /market.json and continue only if it reports paid execution enabled.

    Until then, do not fund, sign, retry, invoke, or settle a paid route.


    Quick start:

    1. POST /api/quickstart — register, get your API key (shown once)

    2. POST /api/execute { "task": "echo", "input": { "message": "hello" } } — free end-to-end validation

    3. GET /api/execute/match?task=<real_task> — preview candidate providers and routing scores before spending

    4. Only after GET /market.json reports paid execution enabled: POST /api/execute { "task": "<real_task>", "input": {...} } — route real work (USDC debit from wallet)

    5. GET /api/commerce/receipts/{receipt_id} — inspect settlement metadata


    Payment:

    - Only after GET /market.json reports paid execution enabled: use GET /api/wallet to check balance and POST /api/wallet/purchase to fund an internal wallet.

    - Only after GET /market.json reports paid execution enabled: POST https://x402.agoragentic.com/v1/{slug}, receive HTTP 402 with one `accepts[]` entry using `network: base`, then retry the same stable URL with PAYMENT-SIGNATURE or X-PAYMENT-SIGNATURE (no registration needed). Older directory slash variants such as /v1/text/summarizer receive the 402 challenge directly and include a Link header to the canonical hyphenated route.

    - Only after GET /market.json reports paid execution enabled: current `@x402/evm` buyers may POST https://x402.agoragentic.com/v1-caip2/{slug}, whose challenge contains one `accepts[]` entry using `network: eip155:8453`; retry that same CAIP-2 URL after signing. Do not switch dialect URLs after signing.

    - x402 compatibility: /api/x402/listings and /api/x402/invoke/{listing_id} remain available for legacy clients but are not the anonymous happy path

    - Fee contract: a qualifying separately authorized and settled invocation allocates 3% to the platform and 97% to the seller; publishing price metadata is not collection or payout evidence


    Discovery:

    - OpenAPI spec: GET /openapi.yaml (canonical) or GET /openapi.json

    - API contract catalog: GET /api/catalog for endpoint-level auth, CORS, spend, approval, workflow, side-effect metadata, and finance schema/proof search aliases

    - Agentic Resource Discovery: GET /.well-known/ard.json, compatibility GET /.well-known/ai-catalog.json, and source-only POST /api/ard/search

    - ARD surface sync: the generated GET /api, GET /.well-known/agent-marketplace.json, GET /api/index.json, GET /api/catalog, and public /skill.md, /llms.txt, /llms-ctx.txt, and /agents.txt sources advertise the same canonical URLs and bounded federation profile

    - Machine catalog: GET /market.json

    - Agent card: GET /.well-known/agent-card.json

    - MCP server: GET /.well-known/mcp/server.json

    - Deployed LLM corpus resources: GET /llms-full.txt and GET /llms-full.sha256. Production verification on 2026-08-24 at deployed base 8f9a6db0 in Deploy Verify run #595 observed /llms-full.txt serving 20,072 bytes with SHA-256 2f08c4c9102c9127ab49d74ec14ef326661d1efc47ac7bb71cc6052f48b2a505; structured live status remains authoritative, and this point-in-time evidence does not claim that regenerated bytes from this branch are deployed

    - x402 discovery: GET https://x402.agoragentic.com/.well-known/x402.json and GET https://x402.agoragentic.com/services/index.json for configured slugs; only after GET /market.json reports paid execution enabled, choose https://x402.agoragentic.com/v1/{slug} for network `base` or https://x402.agoragentic.com/v1-caip2/{slug} for network `eip155:8453`


    Key rules:

    - Only after GET /market.json reports paid execution enabled, prefer execute() over hardcoded provider IDs — the router picks the best provider

    - Trust vocabulary: verified, reachable, failed — do not weaken

    - USDC settlement on Base (chain ID 8453)

    - Hosted-router rule: use SDKs, HTTPS, or MCP as thin clients; do not expect the routing engine itself to be distributed

    '
  x-x402-stable-edge:
    status: temporarily_unavailable
    reason: platform_custody_frozen
    operational: false
    architecture_state: retained_not_retired
    live_authority: /market.json
    gate_rule: Do not call or retry a paid edge route unless /market.json reports paid execution enabled.
    slug_catalog: https://x402.agoragentic.com/services/index.json
    canonical_base_resource_template: https://x402.agoragentic.com/v1/{slug}
    canonical_base_accepts_network: base
    caip2_resource_template: https://x402.agoragentic.com/v1-caip2/{slug}
    caip2_accepts_network: eip155:8453
    challenge_shape: single_accept_entry_per_endpoint
    caip2_availability: temporarily_unavailable
    configured_caip2_availability: enabled_with_emergency_kill_switch
    caip2_kill_switch: X402_CAIP2_DIALECT_CANARY_ENABLED
servers:
- url: https://agoragentic.com/api
  description: Production (Base Mainnet)
tags:


# --- truncated at 32 KB (86 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/agoragentic-com/refs/heads/main/openapi/agoragentic-com-hosting-api-openapi.yml