NEW v0.7 — agent runtime + query console

One platform for
data and agents.

Orkana is the unified workspace for serious data engineering and agentic AI. Connect once, build pipelines with Spark and Trino, deploy agents on the same governed runtime — on cloud or fully on-prem.

Spark · Trino · Kafka Cloud · On-prem · Air-gapped SOC 2-ready
app.orkana.io / workspace - project / workflows
Orkana workflow builder
The integration tax

Enterprises want AI agents.
They get stuck wiring 10+ tools.

To put one production agent in front of real enterprise data, teams stitch together a stack of disconnected tools — each with its own auth, deployment, vendor, and on-call rotation.

Most projects never finish the plumbing. The agent ships late, on stale data, behind a queue of integration tickets.

Orkana replaces all of it

One platform. One auth. One deployment. One on-call.

13+ vendors to wrangle 13 contracts · 13 SSOs 13 on-call rotations + custom governance code
AirbyteConnectors
AirflowPipelines
JupyterNotebooks
Apache SparkProcessing
TrinoFederation
PineconeVector DB
LangChainAgents
n8n / ZapierGlue
Apache KafkaStreaming
KeycloakIdentity
DBeaverExploration
GrafanaVisualization
Time cost
12–18 mo

to wire a production stack before any AI value ships.

Money cost
$1–5M

in licenses, integration work, and headcount per enterprise, per year.

Outcome
95%

of enterprise GenAI pilots deliver zero measurable P&L impact.

Source · MIT, 2025
Product

Build, run, and govern everything in one workspace.

From raw Kafka stream to deployed agent. Visual workflows, native compute, agent runtime, dashboards, metadata explorer — all on the same data plane, same auth, same deployment.

Visual workflows

Drag-and-drop DAGs where every node runs real compute — Python, TypeScript, SQL, Spark, Trino, agents, HTTP, Kafka publish.

Agent runtime

Production-grade agents with built-in tool orchestration, retrieval, self-evaluation, and RBAC — talking to your data through the same engine.

Metadata explorer

Browse every schema, Kafka topic, S3 bucket, vector index. Columns, types, lineage and nullability inline — no second BI tool.

Dashboards & BI

Drag-and-drop charts on top of any query or workflow output. Track pipeline health, agent traces, and KPIs in the same surface.

100+ connectors

Databases, warehouses, S3, Google Drive, Slack, Telegram, Kafka, webhooks. Add a custom one in TypeScript in an hour.

Sovereign deploy

Run on AWS, Azure, GCP, or fully on-prem and air-gapped. Domain-based isolation lets one deployment serve twenty teams safely.

Data layer

Visual workflows.
Real compute.

A single canvas where every node is a real operation — a Spark job, a Trino query, a Python function, an HTTP call, an LLM step, a Slack notification, or a Kafka publish.

  • Python · TypeScript · SQL runtimes inline
  • Spark, Trino, Kafka as first-class engines
  • Branching, retries, scheduling built in
  • Runs, logs, traces, lineage for every execution
WORKFLOW · orkana-agent-rag● running · 7 nodes
Chat trigger Start event ParseList parser IfElse condition Trino query · sql Agent llm · tools Classify llm · route End push SUCCESS SUCCESS BRANCHED RUNNING SUCCESS ROUTED PENDING retry · low confidence
Agent layer

Agents that actually know your data.

Build agents on the same canvas as your pipelines. They query your warehouse, read from Drive and Slack, call internal APIs, and respect RBAC — out of the box.

  • RAG over pgvector with live re-indexing
  • Tool orchestration with execution traces
  • Self-evaluation loops with retry on low confidence
  • OIDC / SSO / RBAC end-to-end
AGENT · data-analyst● connected · 4 tools
Top 5 customers by churn risk this quarter?
→ trino.query · crm.customers
Pulled 12,400 accounts. Top 5 by risk score (RAG + behavioral signals):
1 · Nimbus Holdings0.91
2 · Axiom Labs0.88
3 · Portcore Inc.0.74
4 · Merenda AG0.71
5 · Kite & Sons0.68
Sources: crm.customers, events.app_sessions, support.tickets · 3.8s
Exploration

Browse every schema.
Stop tab-hopping.

Postgres, MinIO, Kafka, vector indexes — one explorer with columns, types, nullability and lineage inline. Engineers stop bouncing between DBeaver, Grafana, and the warehouse console.

  • Unified metastore across all sources
  • Inline schema, types, nullability
  • SQL editor with history and run preview
  • Lineage graph over pipelines and agents
EXPLORER · postgres.public / kafka / s3● 4 connectors · 128 tables
SOURCES
postgres
▾ public
▸ ▦ customers
▸ ▦ db_connector
▸ ▦ dashboards
▸ ▦ workflows
▸ ▦ workflow_runs
kafka
▸ ⎇ topics (12)
▸ ⎇ consumers (4)
s3 · prod-lake
snowflake
db_connector TABLE AGENT-VISIBLE
postgres.public.db_connector · 7 columns · 12,482 rows
NameTypeNullKey
iduuidPK
namevarchar(128)
typeenum
configjsonb
created_attimestamptz
created_byuuidFK
versionint
Insight

Dashboards on the same data plane.

Drag-and-drop charts on top of any query or workflow output. Pipeline health, agent traces, and business KPIs — without spinning up a second BI tool.

  • Live charts wired to any source or workflow
  • Mixed widgets — tables, KPIs, pies, time series
  • Embeddable into internal tools via signed URL
  • Alerts on thresholds, with Slack/Telegram routing
DASHBOARD · pipeline-health● live · 30s
Runs · 24h
12,482
Success
99.2%
p95 latency
412ms
Runs over time
24H 12.4K
Success78%
Failed14%
Routed8%
Throughput by connectorevents / min
kafka postgres s3 mysql snow drive api
Integrations

Connect once.
Reuse everywhere.

One connector definition feeds workflows, agents, dashboards, and the metadata catalog. Add a custom connector in TypeScript in under an hour.

  • Warehouses & DBs — Postgres, BigQuery, Snowflake, Trino
  • SaaS & messaging — Slack, Telegram, Drive, S3
  • Streams — Kafka, webhooks, MQTT
  • Custom — TypeScript SDK, deploy to marketplace
Orkana
100+ connectors available
Retrieval

Knowledge that stays
in sync with reality.

Define a knowledge base from any source — content, code, SOPs. Pick a chunker, embeddings provider, and splitter; agents query it through the same governed retrieval engine.

  • Live re-indexing when source data changes
  • Bring-your-own embeddings — OpenAI, Cohere, local
  • Hybrid retrieval — vector + keyword + filters
  • Per-document RBAC with audit on every read
KNOWLEDGE BASE · product-docs● indexed · 4m ago
Sourcedrive://Product/Docs242 docs
Chunkerrecursive · 1024 / 128char
Embeddingsopenai · text-embedding-3-large3072d
Splittermarkdown-awareheading
RBACper-document · audit on readON
Schedulere-index on source changelive
Chunks
48,210
Avg length
812
Recall@10
94.1%
Architecture

Production runtime, not a notebook demo.

Java Spring Boot backend. Angular frontend. Kafka for events, Redis for state, Postgres + pgvector for data and embeddings. Spark and Trino for heavy work. Keycloak for identity. Every layer ships in the repo today.

Workflow builder Agentic chat AI Assistant Code editor Data Explorer Charts & BI
Agents + RAG Spark Trino DAG runner Code sandboxes Metadata catalog
Kafka Redis Postgres Vector store MinIO · S3 Keycloak IAM OpenTelemetry
Postgres BigQuery Snowflake S3 MinIO GCS Google Drive Slack Telegram Kafka Webhooks MQTT + 100 more
Docker Kubernetes AWS · Azure · GCP On-prem · Air-gapped
Who it's for

Three teams. One platform.

01

Data engineering teams drowning in tool sprawl

Replace Airbyte + Airflow + Spark + Trino + Grafana + DBeaver with one workspace. Same DAGs, same RBAC, half the on-call.

Mid-market Enterprise Saas
02

AI/ML teams shipping agents on real data

Skip the LangChain glue. Build agents that already have governed access to your warehouse, your docs, and your event streams.

Applied AI RAG Tool use
03

Regulated industries — banks, gov, healthcare

Deploy fully on-prem or air-gapped. Domain-based workspace isolation, audit on every read, no data leaves the perimeter.

Sovereign FSI Public sector
Pricing

Start in the cloud.
Scale to your perimeter.

Starter
$15/ workspace · month

For solo builders and evaluation. Hosted on Orkana Cloud, single workspace, community support.

  • 1 workspace · 3 seats
  • 10 connectors · 100 workflow runs/day
  • Built-in agent runtime
  • Community support
  • Public dashboards
Start free
Enterprise · On-prem
Custom/ talk to us

For regulated industries and sovereign deployments. Runs in your VPC, your DC, or fully air-gapped.

  • Self-hosted · air-gapped option
  • Domain-based isolation
  • Custom SLA · 24/7 on-call
  • Dedicated solution architect
  • Private connector marketplace
  • Compliance: SOC 2 · ISO 27001 · HIPAA-ready
Contact sales
Ready when you are

Stop stitching.
Start building.

See Orkana running on your stack in 30 minutes. We'll connect a sample warehouse, build a working agent, and ship a dashboard live on the call.

Tweaks

Accent color
Show pricing section
Compact spacing
Show grid background