Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Tillpad, 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%2Fcnrcode.com%2Fcnrcode" | 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%2Fcnrcode.com%2Fcnrcode" | 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 Tillpad API.
Store and read namespaced key-value pairs for agent state
Index files and notes and run semantic RAG search over them
Keep memory convention values across prefs, facts, and run scopes
Receive email into receive-only inboxes and register email webhooks
Schedule recurring HTTPS jobs at an interval
GET STARTED
Issue account, run, and sub keys with ACLs and wipe run namespaces with a signed receipt
Track metered usage and budgets and estimate whether an operation would be throttled
Patterns agents use Tillpad API for, with concrete tasks.
★ Agent Memory and State Through Jentic
An AI agent can keep its working state in Tillpad through Jentic instead of wiring a storage backend. The agent writes namespaced key-value pairs and memory convention values, reads them back on the next run, and keeps prefs and facts separate from run-scoped data. Because namespaces are addressed in the path, the agent's reach is easy to bound to its own folder.
Store a preference value under a namespace, then read it back on a later run to restore the agent's state
RAG Knowledge Base for an Agent
Tillpad turns uploaded files and plain-text notes into a retrieval base an agent can search. A workflow uploads documents into a namespace, indexes notes, and runs a semantic RAG search to pull the passages relevant to a question, optionally filtered by memory scope.
Upload a document into a namespace, index a note, then run a semantic RAG search and return the top matching passages
Receive-Only Email Inboxes for Workflows
An agent that needs to receive email, such as confirmations or inbound replies, can create a receive-only inbox in Tillpad and register an email.received webhook. It reads message metadata and attachments, downloads the raw MIME when needed, and blocks unwanted senders with a blocklist.
Create a receive-only inbox, register an email.received webhook, and list the messages that arrive
Ephemeral Run-Scoped Storage With Wipe Receipts
For short-lived jobs, Tillpad issues run-scoped keys whose namespaces can be wiped when the job finishes, returning a signed wipe receipt you can verify. That keeps a batch of agent work from leaving data behind and gives an auditable proof that it was removed.
Create a run key, store working data under its namespace, finish the run to wipe it, and verify the returned wipe receipt
66 endpoints — the tillpad api gives an agent bounded storage and search for its jobs.
METHOD
PATH
DESCRIPTION
/api/kvp/{namespace}/{key}
Store a key-value pair
/api/kvp/{namespace}/{key}
Read a key-value pair
/api/rag/search
Run a semantic RAG search
/api/files/{namespace}
Upload a file for RAG indexing
/api/inboxes
Create a receive-only inbox
/api/schedules
Create an HTTPS interval schedule
/api/keys
Create an API key with an optional ACL
/api/runs/{keyId}/finish
Wipe run-key namespaces and return a signed receipt
/api/kvp/{namespace}/{key}
Store a key-value pair
/api/kvp/{namespace}/{key}
Read a key-value pair
/api/rag/search
Run a semantic RAG search
/api/files/{namespace}
Upload a file for RAG indexing
/api/inboxes
Create a receive-only inbox
/api/schedules
Create an HTTPS interval schedule
/api/keys
Create an API key with an optional ACL
/api/runs/{keyId}/finish
Wipe run-key namespaces and return a signed receipt
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Tillpad API by hand means passing a bearer API key or session JWT, threading namespaces into your key-value and file paths, and watching the metered usage and budget so a write is not throttled. Through Jentic you install once, import Tillpad from the API Directory, store the key once, and your agent calls it.
Permission scoping
Tillpad puts the namespace in the URL path (the /api/kvp/ and /api/files/ paths), so a rule can pin your agent to one namespace and the storage operations you choose. You choose the operations it may call, so destructive ones like wiping a namespace or deleting an inbox are not included unless you add them.
Credential isolation
Your Tillpad 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 store a value or run a RAG search, and Jentic returns the matching Tillpad operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Tillpad API through Jentic.
What authentication does the Tillpad API use?
The Tillpad API authenticates with an HTTP bearer token, which can be an API key beginning with tp_ or a session JWT, per its OpenAPI spec. Health, config, sign-in, and webhook endpoints need no authentication, while storage, RAG, inbox, and schedule operations expect the token. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time.
Can I run RAG search with the Tillpad API?
Yes. You upload files or index plain-text notes into a namespace, Tillpad builds the vectors, and a semantic RAG search returns the matching content. A memory search can also filter by a memory scope such as prefs, facts, or run.
Can the Tillpad API receive email for my agent?
Yes. You create receive-only inboxes, list their messages and attachments, download raw MIME, and register an email.received webhook so your agent is notified when mail arrives. A blocklist lets you block sender addresses or domains.
How do I store agent state with the Tillpad API through Jentic?
Install Jentic One, then import Tillpad from the API Directory and store your key once. Your agent searches by intent such as store a value under a namespace, and Jentic returns the key-value operation with its input schema so the agent writes and reads state without wiring the storage API. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Tillpad API MCP server?
You don't need an MCP server to give your agent the Tillpad API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the storage, RAG, and inbox operations on demand. Operations are discovered when the agent needs them, so they do not fill its context ahead of time.
Can I limit what my agent is allowed to do with the Tillpad API?
Yes. Because the namespace sits in the URL path, you can write a rule that pins your agent to one namespace and allows only the storage and search operations it needs. Wiping a namespace, deleting an inbox, or revoking keys stays out of that set unless you add them, and every call is logged.
For Agents
Store namespaced key-value pairs and memory values, index files and notes for semantic RAG search, receive email into inboxes, and schedule HTTPS jobs. Run keys can be wiped with a signed receipt when a job ends.
Use for: I want to store a value under a namespace for later, Run a semantic search over my indexed notes, Upload a document for RAG retrieval, Create a receive-only email inbox for my agent
Not supported: Does not send outbound email, provide a full relational database, or execute agent code. Use for bounded key-value storage, RAG search, receive-only inboxes, and scheduled HTTPS jobs only.
The Tillpad API gives an agent bounded storage and search for its jobs. It stores namespaced key-value pairs and memory convention values, indexes files and notes for retrieval, and runs semantic RAG search over them. On top of storage it provides receive-only email inboxes with webhooks, scheduled HTTPS jobs, and metered usage with budget estimates. Run-scoped API keys can be wiped at the end of a job and return a signed wipe receipt, so ephemeral agent state does not linger.
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>