The intelligence & security layer
for AI agents
Trace, observe and connect intelligence on demand.
In a world where AI is getting more powerful, you need a way to observe and provide intelligence on demand.
Five pillars of
agent infrastructure
One-click OAuth to all major platforms. Automatic token refresh, secure credential storage, and one connection layer for every data source your agent needs.
Facebook
Google Ads
LinkedIn
TikTok
HubSpot
Salesforce
Gmail
Google Drive
Microsoft
Calendar
Postgres
Firecrawl
InstagramTokens are never stored in plaintext. Each credential is encrypted with a unique initialization vector and authenticated with GCM tags to prevent tampering.
Every agent request through Datagran is traced end-to-end. See latency, token usage, which data sources were hit, and the full decision chain.
Set granular policies per action type. Every agent request passes through the policy engine before execution—blocked actions never reach the data source.
Risk scoring, human-in-the-loop approvals, and full audit trails for every policy decision.
Personas are AI agents that evaluate other AI agents. They simulate adversarial scenarios, test for prompt injection, data exfiltration, and policy circumvention—before your agent goes live.
Attempts prompt injection and policy bypass
Validates outputs against regulatory rules
Flags biased or unfair targeting decisions
Prevents sensitive data from leaking out
Product
Datagran
Universal Memory
Give every AI agent persistent, queryable memory that scales from a single conversation to millions of interactions. Three tiers. One query. An LLM planner decides where to store and where to search.
Short-term Memory
Always in context. A rolling summary plus recent raw entries. Every data fetch is auto-ingested as a structured DG entry.
Compiled Wiki
NEWAn LLM planner evaluates every ingestion and decides what becomes durable knowledge. Structured markdown pages, interlinked, source-aware, and syncable to Obsidian.
Long-term Memory (RAG)
When the brain exceeds 50k tokens, overflow is embedded into vector chunks and archived for semantic search. Unlimited history, always retrievable.
How it works
Ingest
Any data (ads, CRM, web scrapes, or raw text) is auto-ingested into short-term memory as a DG entry.
Planner
An LLM planner evaluates new data and decides whether to create, update, or skip wiki pages.
Compile Wiki
The wiki compiler turns source material into structured, interlinked markdown pages with source refs.
Query
Ask a question and the planner searches short-term memory, wiki pages, and long-term RAG.
Sync
Wiki pages sync to Obsidian via a pull-only plugin. Managed folder, incremental diffs, zero Git.
Grounded answers
Agents answer with evidence from recent context, compiled wiki pages, and archived source material.
Adaptive recall
The memory planner balances freshness and relevance so old context is available without flooding the agent.
Connected wiki
Structured markdown pages keep people and agents aligned around the same source-aware knowledge base.
Implementation details live in the partner portal
Endpoint references, request and response examples, search traces, memory weighting, and Obsidian sync operations are documented for partners.
Sync
Obsidian
Wiki Sync
Your AI agent's compiled wiki, mirrored as interlinked markdown files inside your Obsidian vault. Pull-only, no Git, no config files. Install once, sync on demand.
What the Obsidian plugin does
The download is the plugin itself—a small app you install once into Obsidian. It's not a zip of wiki content.
Every time your agent ingests data, the wiki may update. Next sync pulls only changed files into your vault's managed folder.
Click “Sync now” whenever you want, or set a background interval (e.g. every 5 minutes) in plugin settings.
Datagran is the source of truth. Edits you make to synced files in Obsidian stay local and will be overwritten on next sync.
Setup in 5 minutes
Install the plugin, connect it to your Datagran wiki, then sync markdown pages into a managed folder in your Obsidian vault.
Download
Get the Datagran Wiki Sync plugin zip from this page.
Install
Add it to Obsidian community plugins and enable Datagran Wiki Sync.
Connect
Paste the target ID and plugin token generated from the partner portal.
Sync
Run Datagran: Sync now from Obsidian, or set an automatic interval.
Partner setup, token minting, vault paths, and sync details now live in the partner portal docs.
Open partner docs →What sync gives you
Obsidian reads compiled wiki pages from Datagran. Local edits stay in your vault.
The plugin writes only inside the Datagran folder you configure.
After the first sync, only changed wiki pages transfer into the vault.
Security
Encryption at
every layer
Your data, your tokens, your agent's memory—all protected with bank-grade encryption. Nothing is ever stored in plaintext.
AES-256-GCM
Every OAuth token is encrypted using AES-256 with Galois/Counter Mode. Each encryption uses a unique 96-bit initialization vector and produces an authentication tag.
Zero Token Exposure
Tokens are decrypted only at the instant they're needed, in memory, for the duration of the request. They're never logged, never cached, never written to disk unencrypted.
Infrastructure Security
TLS everywhere, encrypted storage at rest, isolated compute per partner, and full audit trails for every data access.
Ready to build?
Sign up for the Datagran Intelligence Layer and start connecting your agents to the data sources they need.