The First Agent-Native
Data Platform
The ingestion and data-quality layer that feeds the stores you already run — driven by AI agents over MCP, developers, and analysts. Datris sits beside your warehouse and your lake. It doesn't replace them.
keyFields on the pipeline.
Type what you want.
The Assistant builds it.
Datris ships with an Assistant Agent inside the platform UI. Tell it what data you want. It asks a few sharp scoping questions, picks the right source and destination, generates the fetcher, requests credentials securely, runs the job, confirms the rows landed, and lets you query the result — usually in seconds, with no hand-written config.
- Clarifies scope before building — picks the right source, destination, and cadence with you
- Generates and runs the fetcher (tap) for external APIs and files
- Requests credentials through a secure form — never in chat history
- Polls job status and confirms rows actually landed before saying "done"
- Flags things you didn't ask about — upsert vs append, fair-use policies, schema drift
- Answers natural-language questions over the data once it's in
- "I'm looking for corporate earnings data."
- "Ingest these PDFs into a vector store for RAG."
- "Refresh treasury yields from FRED nightly and let me query trends."
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.
Push and pull — one platform, two interfaces
Datris owns data acquisition, validation, normalization, storage, and observability. Your agents focus on reasoning and decisions — not on solving integration problems for the hundredth time. The boundary gets more valuable with every new source and every new agent.
Self-host on open source
Prefer to run it yourself? Datris is fully open source. Built on proven 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.
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.
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, and query your structured, document, and vector data in real time — all through natural conversation.
- Register pipelines and generate schemas from sample data
- Create, schedule, and run AI-generated taps
- Ingest documents into vector databases (extract → chunk → embed)
- 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
- Manage credentials via Vault — without ever holding the key
Speaks every data language
Ingest structured data, unstructured documents, and archives. Output to vector stores, structured stores, or optimized columnar formats.
| Format | Input | Default Destination |
|---|---|---|
| CSV | SQL DB | |
| JSON | NoSQL DB | |
| XML | NoSQL DB | |
| Excel (.xlsx) | SQL DB | |
| Parquet | SQL DB | |
| ORC | SQL DB | |
| Vector DB | ||
| Word (.docx) | Vector DB | |
| PowerPoint (.pptx) | Vector DB | |
| HTML | Vector DB | |
| Email (.eml) | Vector DB | |
| EPUB | Vector DB | |
| Archives (.zip, .tar) | Unpacked, routed | |
| Plain Text | Vector DB |
Destinations are fully configurable. Route any format to any target — SQL databases, NoSQL stores, vector databases, REST endpoints, Kafka topics, or ActiveMQ queues.
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.
How Datris compares
The only platform combining MCP-native agent access, AI-generated taps, AI-powered schema, data quality, and transformation, multi-destination pipelines, and document RAG — in a single open-source package.
| Capability | Datris | Airbyte | Fivetran | dbt | Prefect | Dagster | NiFi | Meltano |
|---|---|---|---|---|---|---|---|---|
| MCP Server (native) | 40+ tools | |||||||
| AI-Generated Taps | Python fetchers | |||||||
| AI Schema Generation | From file | |||||||
| AI Data Quality | Plain-English | |||||||
| AI Transformation | Plain-English | |||||||
| Data Ingestion | ||||||||
| Multi-Destination Pipelines | Parallel writes | ~ DIY | ~ DIY | |||||
| Document RAG Pipeline | Extract → embed | |||||||
| Vector DB Destinations | 5 DBs | ~ Few | ||||||
| Vault Secrets | Built-in | ~ Add-on | ~ | ~ Add-on | ~ Add-on | ~ | ||
| Orchestration | Config-driven | ~ Limited | ~ Limited | |||||
| Open Source | AGPL-3.0 | Core | Core | |||||
| No-Code | JSON / MCP / UI | ~ UI | UI | SQL | Python | Python | Visual | CLI/YAML |
| Self-Hosted |
Connect your agent in 60 seconds
Get an API key and dedicated MCP endpoint, REST API, and full platform UI instantly.
Send us a message
Questions, feedback, or just want to chat — we'd love to hear from you.