Agent APIagent.ai ↗
Access agent listings, builder profiles, category tags, and execution stats from the Agent.ai marketplace via 6 structured endpoints.
What is the Agent API?
The Agent.ai API provides 6 endpoints to search, filter, and retrieve structured data from the Agent.ai AI agent marketplace. Use list_agents to run keyword searches across agent names and descriptions, get_agent_details to pull full metadata on a single agent including pricing tier, action types, and review scores, and list_builders to surface the top creators ranked by total execution count.
curl -X GET 'https://api.parse.bot/scraper/9cd35268-4784-4038-ba40-74bc4c5a07cd/list_agents?page=0&query=marketing' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace agent-ai-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
from parse_apis.agent_ai_api import AgentAI, Agent, Builder, PricingTier, AgentTag, ResourceNotFound
client = AgentAI()
# Search for marketing-related agents
for agent in client.agents.search(query="marketing", limit=5):
print(agent.name, agent.executions, agent.reviews_score, agent.pricing_tier)
# Filter agents by category using the AgentTag enum
for agent in client.agents.by_tag(tag=AgentTag.SALES, limit=3):
print(agent.name, agent.description, agent.is_premium)
# Get full details for a specific agent
detail = client.agents.get(agent_id="8hc9z3aiwok5ypt2")
print(detail.name, detail.reviews_score, detail.author.name)
# List available tags
for tag in client.tags.list():
print(tag)
# List top builders and explore their agents
for builder in client.builders.list(limit=3):
print(builder.display_name, builder.public_agents_count, builder.executions_count)
for agent in builder.agents.list(limit=2):
print(agent.name, agent.executions)
Search for AI agents by keyword, or list all agents if no query is provided. Returns paginated results sorted by relevance. Each page contains up to 20 agents. Paginates via a 0-indexed page counter; total pages and hit count are included in the response.
| Param | Type | Description |
|---|---|---|
| page | integer | Page number (0-indexed). |
| query | string | Search keyword to filter agents by name or description. |
{
"type": "object",
"fields": {
"pages": "integer total number of pages",
"total": "integer total number of matching agents",
"agents": "array of agent objects with agent_id, name, description, author, executions, reviews_score, _tags, pricing_tier, and more",
"current_page": "integer current page number (0-indexed)"
},
"sample": {
"data": {
"pages": 50,
"total": 1447,
"agents": [
{
"name": "Web Copy Analyzer",
"_tags": [
"Marketing",
"Sales"
],
"author": {
"name": "Shaalin Parekh",
"username": "Shaalin",
"twitter_username": "Shaalin"
},
"agent_id": "8hc9z3aiwok5ypt2",
"executions": 131,
"is_premium": true,
"description": "See exactly how your buyer would react to your website.",
"pricing_tier": "Premium",
"reviews_count": 1,
"reviews_score": 5
}
],
"current_page": 0
},
"status": "success"
}
}About the Agent API
Searching and Filtering Agents
list_agents accepts an optional query string and a 0-indexed page integer. Results include agent_id, name, description, author, executions, reviews_score, and _tags for each agent, alongside pagination fields pages, total, and current_page. To filter by category instead of keyword, filter_agents_by_tag accepts a required tag string — valid values come from get_agent_tags, which returns the full list of available category tag strings with no inputs required.
Agent Detail and Taxonomy
get_agent_details takes an alphanumeric agent_id (obtainable from list or filter results) and returns a richer response: action_types array, pricing_tier (Free, Premium, or Pro), is_premium boolean, reviews_count, and an author object containing name, username, twitter_username, avatar, and user_token. This is the only endpoint that exposes action_types, making it the right call when you need to distinguish agents by what operations they perform.
Builder Profiles
list_builders returns an array of builder objects ranked by executions_count, with fields including display_name, twitter_username, agent_ai_username, and public_agents_count. To get a specific builder's agents, pass any of those identifier values to get_builder_profile, which returns the full profile object plus an agents array of that builder's published agents.
The Agent API is a managed, monitored endpoint for agent.ai — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when agent.ai changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official agent.ai API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Index the full Agent.ai catalog by iterating
list_agentspages and storing agent metadata for internal search. - Build a category browser by mapping tags from
get_agent_tagsto paginated results fromfilter_agents_by_tag. - Compare agents by
pricing_tierandexecutionsto recommend free, high-usage options for a given use case. - Track top builders over time by polling
list_buildersand recording changes inexecutions_countandpublic_agents_count. - Enrich a directory of AI tools by pulling
action_typesand_tagsfromget_agent_detailsfor each agent_id. - Identify prolific creators in a niche by filtering
get_builder_profileresults against agents with a specific tag. - Audit the marketplace for premium-only agents by checking
is_premiumacross all paginatedlist_agentsresults.
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 100 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does Agent.ai provide an official public developer API?+
What does `get_agent_details` return that the list endpoints don't?+
get_agent_details adds action_types (an array describing what operations the agent performs), pricing_tier (Free, Premium, or Pro), is_premium boolean, and the full author object including twitter_username and user_token. The list and filter endpoints return a summary form of each agent without those fields.How does pagination work across list and filter endpoints?+
page integers. Responses include pages (total page count), total (total matching agents), and current_page. To retrieve all results, iterate from page 0 through pages - 1.Does the API expose agent review text or individual user reviews?+
reviews_score in list results and reviews_count in get_agent_details, but not individual review text, reviewer identities, or per-review ratings. You can fork this API on Parse and revise it to add an endpoint targeting individual review content.Can I retrieve agents sorted by criteria other than relevance or execution count?+
list_agents returns results sorted by relevance to the search query, and list_builders is sorted by execution count. Sorting by review score, creation date, or pricing tier is not currently supported by the endpoints. You can fork this API on Parse and revise it to add alternative sort parameters.