Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Nirvana Task 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%2Fnirvanahq.com%2Fnirvanahq" | 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%2Fnirvanahq.com%2Fnirvanahq" | 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 Nirvana Task API.
Capture a task or project with name, note, tags, duedate, energy, and etime, defaulting to the inbox state
Query tasks by GTD state, type, tags, keyword, starred, overdue, and due_before or due_after dates
Move a task between states such as next, waiting, scheduled, and logbook, with completed set automatically on logbook
Record who a task is waiting on with waitingfor when the state is waiting
GET STARTED
List tags and areas with their task usage counts before tagging
Read per-state task counts and an analytics snapshot covering velocity, dormancy, inbox age, and project health
Patterns agents use Nirvana Task API for, with concrete tasks.
★ Agent task capture through Jentic
A personal assistant agent turns requests from chat or email into Nirvana tasks. It searches Jentic for 'create a task in Nirvana', receives the v1CreateTask schema, and posts a name with optional tags, duedate, and energy. Because the spec enforces combination rules, such as scheduled requiring startdate, the agent sets state and dates together in one valid request.
Search Jentic for 'create a task in Nirvana', then call POST /v1/tasks with name='Renew passport', tags=['errands'], duedate='2026-12-01', energy=1
Weekly review assistant
The GTD weekly review is about spotting stalled work. GET /v1/analytics returns a server-side snapshot covering tasks captured and completed in the last 7 and 30 days, tasks untouched for 30, 60, or 90 days, inbox age, waiting-for aging, and project health, and GET /v1/counts gives per-state totals, so an assistant can prepare a review summary before you sit down.
Call GET /v1/analytics and GET /v1/counts, then summarise inbox age, dormant tasks, and waiting-for items older than 30 days
Context lists and focus planning
Planning the day means pulling the right slice of next actions. GET /v1/tasks accepts state=next with comma-separated tags using AND logic, starred=true for the Focus list, and limit and offset for paging up to 200 results at a time, so an assistant can assemble a short list for a given context.
Call GET /v1/tasks with state='next', tags='office', limit=20 and return the task names sorted by energy
Closing the loop on delegated work
Delegated items need follow-up. PATCH /v1/tasks/{id} changes only the fields you send, so an assistant can move a task to waiting with a waitingfor value, and later to logbook, which sets completed to today automatically.
Call PATCH /v1/tasks/{id} with state='waiting' and waitingfor='Sam', then later PATCH the same id with state='logbook'
6 endpoints — the nirvana task api reads and updates tasks and projects in a nirvana gtd account, using getting things done states such as inbox, next, waiting, scheduled, someday, later, and logbook.
METHOD
PATH
DESCRIPTION
/v1/tasks
Query tasks
/v1/tasks
Create a task or project
/v1/tasks/{id}
Update a task
/v1/tags
List tags with usage counts
/v1/analytics
Get GTD system health analytics
/v1/counts
Get task counts per GTD state
/v1/tasks
Query tasks
/v1/tasks
Create a task or project
/v1/tasks/{id}
Update a task
/v1/tags
List tags with usage counts
/v1/analytics
Get GTD system health analytics
/v1/counts
Get task counts per GTD state
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Nirvana by hand means handling its bearer token and learning the state rules, such as scheduled needing startdate and waitingfor only with waiting, before your first write succeeds. Through Jentic you install once, import Nirvana from the API Directory, store the token once, and your agent calls it.
Permission scoping
Nirvana's read and write operations are separate paths and methods, so a rule can limit your agent to the ones it needs, such as reading tasks and analytics. You choose the operations it may call, so changes like PATCH /v1/tasks/{id}, which can move a task to trash, are not included unless you add them.
Credential isolation
Your Nirvana auth token 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 'create a task in Nirvana' or 'list next actions', and Jentic returns the matching Nirvana 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 Nirvana Task API through Jentic.
What authentication does the Nirvana Task API use?
Per its OpenAPI spec, the Nirvana Task API uses a bearer token, sent as `Authorization: Bearer <nirvana-auth-token>`. Through Jentic, the token is stored encrypted by your own Jentic One instance and injected at call time, so it stays out of the agent's prompt and logs.
Can I delete tasks with the Nirvana Task API?
There is no DELETE operation in the spec. To discard a task, PATCH /v1/tasks/{id} with state set to trash; to complete one, set state to logbook, which sets completed to today.
What are the rate limits for the Nirvana Task API?
The OpenAPI spec does not specify rate limits. Check https://nirvanahq.com for current limits. Task queries return at most 200 results per page through the limit parameter.
How do I add a task to Nirvana through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, add Nirvana from the Jentic API Directory, and store your Nirvana auth token. Your agent searches for 'create a task in Nirvana' and calls POST /v1/tasks with a name; the task lands in the inbox unless you set another state. 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 Nirvana Task API?
Yes. For a review assistant, write a rule that allows GET /v1/tasks, GET /v1/counts, and GET /v1/analytics, so it can read and summarise your system but cannot add or change tasks. For a capture assistant, allow POST /v1/tasks and leave PATCH out, so it can add to the inbox but not move or trash existing items.
Is there a Nirvana MCP server?
You don't need an MCP server to give your agent the Nirvana Task API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls it.
Can the Nirvana Task API change recurring tasks?
No. The spec marks the recurring state as read-only: recurring task templates are managed by the Nirvana app and cannot be created or modified through the API.
For Agents
Capture tasks into a Nirvana inbox, query tasks by GTD state, tags, keyword, and due date, move tasks between states, and read counts and system-health analytics for a weekly review.
Use for: I need to add 'renew passport' to my Nirvana inbox, List all next actions tagged @calls, Find all overdue tasks in Nirvana, Mark this task as done
Not supported: Does not manage calendars, team assignments, recurring task templates, or file attachments. Use for capturing, querying, and updating tasks and projects in a personal Nirvana GTD account only.
The Nirvana Task API reads and updates tasks and projects in a Nirvana GTD account, using Getting Things Done states such as inbox, next, waiting, scheduled, someday, later, and logbook. It filters tasks by state, type, tags, keyword, starred Focus status, overdue status, and due date range, and it creates and updates tasks with fields like duedate, startdate, waitingfor, energy, and etime. Read-only endpoints return tag usage counts, per-state task counts, and a server-side analytics snapshot of system health for weekly reviews. The API is in public beta.
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>