The First Agent-Native
Data Platform

Ingest, validate, transform, store, and retrieve your data — whether you're an AI agent talking through MCP or a developer writing config. One platform for both.

Try Free — No Credit Card Self-Host (Open Source) Docs

 $ datris ingest stock-price-data.csv --dest postgres \

    --ai-validate "all prices must be positive" \

    --ai-transform "uppercase all ticker symbols"
  ├ ✓ Pipeline created (stock_price_data)
  ├ ✓ Schema auto-detected (14 columns)
  ├ ✓ AI validation passed (all prices positive)
  ├ ✓ AI transform applied (12,847 rows)
  ├ ✓ Loaded to PostgreSQL
  └ Done in 4.2s

AI-Powered

Intelligence at every stage

Every step of your data pipeline is enhanced with AI. From ingestion to delivery, Datris makes data engineering accessible through natural language.

🔌

MCP Server

AI Agent Integration

First open-source pipeline with native Model Context Protocol. Agents can register pipelines, upload files, trigger jobs, profile data, and run searches.

✓

AI Data Quality

Plain English Validation

Validate with plain English rules via aiRule. AI evaluates every row using reasoning and domain knowledge — no regex required.

⚡

AI Transformations

Natural Language Transforms

Describe row transforms in natural language. Date conversion, categorization, entity extraction — no code needed.

📐

AI Schema Generation

Auto-Config from Any File

Upload any CSV, JSON, or XML and get a complete dataset configuration auto-generated. Skip the boilerplate entirely.

📊

AI Data Profiling

Instant Data Insights

Upload a file and get summary statistics, quality issues, and suggested validation rules — all powered by AI analysis.

🔍

AI Error Explanation

Root Cause Analysis

When jobs fail, AI analyzes the error chain and explains the root cause in plain English. No more digging through stack traces.

Architecture

Push and pull — one platform, two interfaces

AI agents and humans ingest data through the pipeline, store it across databases and vector stores, and retrieve it back — via MCP or API.

Ingestion Pipeline

Sources

Data Upload

MinIO

DB Pull

Kafka

Processing

1 Preprocessor

2 Data Quality (AI)

3 Transformation (AI)

Storage

MinIO (Parquet/ORC)

PostgreSQL

MongoDB

Kafka

ActiveMQ

REST API

Qdrant

Weaviate

Milvus

Chroma

pgvector

Notification

Email · Slack · Webhook

MCP — AI Agent Interface

Push

Create Pipelines

Upload Data

Trigger Processing

Configure Pipelines

MCP stdio · SSE

Claude Cursor OpenClaw Any MCP Agent

Pull

Query PostgreSQL

Query MongoDB

Semantic Search (Vector DB)

Monitor Jobs

Profile Data

Retrieve Results

RAG Pipeline

Full RAG pipeline built in

Extract, chunk, embed, and upsert documents into any major vector database. Build retrieval-augmented generation workflows without leaving your pipeline.

🗄️

5 Vector Databases

Qdrant Weaviate Milvus Chroma pgvector

✂️

Chunking Strategies

Choose the right chunking strategy for your use case:

🧠

Embedding Providers

Generate embeddings with cloud or local models:

📄

Document Extraction

Extract text from virtually any document format:

RAG Pipeline Flow

1 Document Extraction

→

2 Chunking

→

3 Embeddings

→

4 Vector Upsert

Model Context Protocol

Your AI agents are
first-class pipeline operators

Datris ships with a native MCP server. Claude, Cursor, OpenClaw, and any MCP-compatible AI agent can register pipelines, trigger jobs, search your data, and monitor pipelines — all through natural conversation.

Transports: stdioSSE (Server-Sent Events)

Compatible agents:

MCP Capabilities

Register pipelines and configure schemas
Upload data for processing
Trigger and monitor pipeline jobs
Profile data and get AI insights
Semantic search across vector databases
Query PostgreSQL and MongoDB directly

Example prompt

"Ingest sales_q4.csv into the analytics database and validate that 'revenue must be positive and date must be in 2024'."

Formats

Speaks every data language

Ingest structured data, unstructured documents, and archives. Output to vector stores, structured stores, or optimized columnar formats.

Format	Input	Output
CSV
JSON
XML		—
Excel (.xlsx)		—
Parquet	—
ORC	—
PDF		—
Word (.docx)		—
PowerPoint (.pptx)		—
HTML		—
Email (.eml)		—
EPUB		—
Archives (.zip, .tar)		—
Plain Text		—

AI Providers

Your choice of AI model

Use cloud AI from Anthropic or OpenAI, or keep everything local with Ollama. No vendor lock-in — switch providers without changing your pipeline config.

Anthropic Claude

Claude Opus 4.6, Sonnet 4.6, Haiku, and more

OpenAI

GPT-5, GPT-4.1, o3, and embedding models

⊙

Ollama

Run local models — Llama, Mistral, Phi, and more

Comparison

How Datris compares

The only platform combining MCP-native agent access, AI-powered data quality and transformation, multi-destination pipelines, and RAG — in a single open-source package.

Capability	Datris	Airbyte	Fivetran	dbt	Prefect	Dagster	NiFi	Meltano
MCP Server (native)	30+ tools
AI Data Quality
AI Transformation
Data Ingestion
Orchestration	Config-driven	~ Limited	~ Limited
Vector DB / RAG	5 DBs
Open Source	AGPL-3.0	Core		Core
No-Code	JSON config	~ UI	UI	SQL	Python	Python	Visual	CLI/YAML
Self-Hosted

Infrastructure

Self-hosted on open source

Runs anywhere Docker does. Built on proven open-source infrastructure — no proprietary services, no vendor lock-in, no surprise bills.

 $ git clone https://github.com/datris/datris-platform-oss.git
 $ cp .env.example .env
 # Add your API key (at least one required for AI features)
 $ docker compose up -d
 $ curl http://localhost:8080/api/v1/version

Clone. Configure. Launch. Your full pipeline in under a minute.

Get Started

Connect your agent in 60 seconds

Start a free 14-day trial — no credit card required. Get a dedicated MCP endpoint, REST API, and full platform UI instantly.

Try Free Read the Docs

Or send us a message:

The First Agent-NativeData Platform