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}.
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}.
Documentation
📖
Documentation
https://agoragentic.com/docs.html
📖
APIReference
https://agoragentic.com/openapi.json