Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Conference Partner API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmyhuiban.com%2Fmyhuiban" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmyhuiban.com%2Fmyhuiban" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Conference Partner API.
Search conferences by keyword, field, ccf_rank, core_rank, or qualis_rank and narrow by submission or conference date window
Browse ranked conference lists such as cfp, upcoming, trending, most_competitive, or cp_index without a search keyword
Find journals by keyword, ISSN, CCF rank, or research field, and browse journal lists such as highest_if
Pull full conference detail including CFP text, acceptance-rate history, and edition history by conference id
GET STARTED
Retrieve a journal's full record or a researcher's public profile by id
Poll for changed venues with the updated_since filter to keep a local deadline tracker current
Patterns agents use Conference Partner API for, with concrete tasks.
★ Agent-run paper deadline tracker
A research assistant agent connected through Jentic keeps a lab's submission calendar current. It calls the conference search with field set to ai or nlp, a ccf_rank filter, and a submission_date_start and submission_date_end window, then reruns the search with updated_since to catch deadline changes. The lab gets a short, ranked list of venues worth targeting without anyone checking CFP pages by hand.
Call GET /api/conferences with field=ai, ccf_rank=a, submission_date_start=2026-12-01, and submission_date_end=2027-02-28, then list each conference's name, deadline, and detail_page link
Choosing a venue by ranking
Before submitting a paper, a researcher wants to compare venues by ranking rather than by keyword. The ranking-list endpoint returns pre-built lists such as ccf, core, qualis, cp_index, most_competitive, and trending, paged up to 100 entries per page. Paired with the CP-I score breakdown on each conference, it gives a reproducible shortlist instead of word-of-mouth advice.
Call GET /api/conferences/rankings/most_competitive with per_page=20 and return the top entries with their ranks
Journal shortlisting for a manuscript
When a manuscript is better suited to a journal, an agent searches journals by research field and CCF rank, or browses the highest_if and cfp journal lists filtered to one field such as data or security. It then fetches each candidate's full record by id to compare scope and ratings before the author decides where to submit.
Call GET /api/journals/rankings/highest_if with field=security, then call GET /api/journals/{id} for the first three results using a bearer credential
Venue and researcher detail lookup
For a deeper look at a single venue, the detail endpoints return CFP text, acceptance-rate history, edition history, structured ratings and comments, and related conferences or journals. The researcher endpoint returns a public profile by id. These calls require a free-account API key or a JWT from the login operation, sent as a bearer token.
Call GET /api/conferences/{id} with a bearer credential and summarise the acceptance-rate history and the latest CFP text
9 endpoints — the conference partner api searches a read-only dataset of academic conferences and journals, returning calls for papers, submission deadlines, locations, and ccf, core, and qualis rankings.
METHOD
PATH
DESCRIPTION
/api/conferences
Search academic conferences
/api/conferences/rankings/{ranking}
Browse conference lists and rankings
/api/conferences/{id}
Get full conference detail
/api/journals
Search academic journals
/api/journals/rankings/{ranking}
Browse journal lists and rankings
/api/researchers/{id}
Get a researcher's public profile
/api/login
Exchange email and password for a JWT
/api/conferences
Search academic conferences
/api/conferences/rankings/{ranking}
Browse conference lists and rankings
/api/conferences/{id}
Get full conference detail
/api/journals
Search academic journals
/api/journals/rankings/{ranking}
Browse journal lists and rankings
/api/researchers/{id}
Get a researcher's public profile
/api/login
Exchange email and password for a JWT
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Conference Partner by hand means telling anonymous endpoints from credentialed ones, handling the bearer key or JWT login, setting a real User-Agent to get past Cloudflare, and reading the 429 and 402 quota responses. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
Permission scoping
Every Conference Partner operation is a read except login, and the venue id sits in the URL path of the detail endpoints, so a rule can bound your agent to the search and ranking operations, or to detail reads under specific ids. You choose the operations it may call, so the login operation is not included unless you add it.
Credential isolation
Your Conference Partner API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find CCF A conference deadlines' or 'list trending conferences', and Jentic returns the matching Conference Partner operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Conference Partner API through Jentic.
What authentication does the Conference Partner API use?
Per its OpenAPI spec, the conference search, journal search, ranking-list, and statistics endpoints need no credential, sharing a small anonymous daily quota per source IP. The conference, journal, and researcher detail endpoints require a bearer credential in the Authorization header: either an API key from your account (it starts with hb_) or a JWT returned by POST /api/login. The spec also declares an X-Paid-Access apiKey header for per-request payment, which it marks as not live. Through Jentic, the key is stored once by your own Jentic One instance and injected at call time.
Can I search conferences by deadline and ranking with the Conference Partner API?
Yes. GET /api/conferences accepts query, field, ccf_rank, core_rank, qualis_rank, submission_date_start, submission_date_end, conference_date_start, conference_date_end, and updated_since, with page and per_page for paging. The field parameter takes values such as ai, vision, nlp, security, and systems.
What are the rate limits for the Conference Partner API?
The spec describes daily quotas rather than per-second limits. Anonymous clients share a small daily quota per source IP and get HTTP 429 when it runs out, and a credential raises the quota, returning HTTP 402 when exhausted. Repeating an identical request on the same day does not use quota again. The spec does not state the exact numbers; see https://www.myhuiban.com/developers for current limits.
Why does the Conference Partner API return a 403 with error code 1010?
The site sits behind Cloudflare, whose Browser Integrity Check rejects some default script User-Agents, such as Python urllib's and Perl LWP's, before the request reaches the API. It is not an auth or quota error. Send a descriptive User-Agent that names your tool and a contact URL on every request.
How do I build a deadline tracker with the Conference Partner API through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then import the Conference Partner API from the API Directory. Your agent searches for 'find academic conference deadlines', gets searchConferences with its input schema, and calls it with a field, a ccf_rank, and a submission date window. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Conference Partner API?
Yes. For example, write a rule that allows only searchConferences and listConferences, so the agent can find and rank venues but never calls the detail endpoints that draw on your account quota, and never calls the login operation. Add getConference later if you want it to read full CFP text.
For Agents
Search academic conferences and journals by keyword, field, CCF rank, and deadline window, browse ranking lists, and pull full venue or researcher detail from the Conference Partner dataset.
Use for: Find all CCF A conferences in AI with submission deadlines next month, List upcoming conferences with open calls for papers, Search for journals in computer vision ranked by CCF, Get the acceptance-rate history for a specific conference
Not supported: Does not submit papers, register attendees, or return full paper text or citation counts. Use for searching and ranking academic conferences and journals and reading their deadlines only.
The Conference Partner API searches a read-only dataset of academic conferences and journals, returning calls for papers, submission deadlines, locations, and CCF, CORE, and QUALIS rankings. It also serves curated ranking lists such as upcoming, trending, and most competitive conferences, plus site-level statistics. Each active conference carries cp_index, the Conference Partner Index: a 0-100 score with a per-factor breakdown and a confidence value. Search, ranking, and statistics calls work anonymously on a small daily quota, while per-venue and researcher detail calls need a free-account credential.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>