ORBIT — Open Retrieval-Based Inference Toolkit
git clone https://github.com/schmitech/orbit.git && cd orbit/docker
docker compose up -dThen test it:
curl -X POST http://localhost:3000/v1/chat \
-H 'Content-Type: application/json' \
-H 'X-API-Key: default-key' \
-H 'X-Session-ID: local-test' \
-d '{
"messages": [{"role": "user", "content": "Summarize ORBIT in one sentence."}],
"stream": false
}'That's it. ORBIT is listening on port 3000 with an admin panel at localhost:3000/admin (default login: admin / admin123).
For GPU acceleration: docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
The public sandbox hosts one chat workspace per adapter. Pick a demo to see ORBIT in action.
| Demo | Data Source | Try it |
|---|---|---|
| Simple Chat | LLM | simple-chat |
| Multimodal Chat | LLM + Files | chat-with-files |
| Multi-Source Chat | SQLite + PostgreSQL + DuckDB | composite-multi-source-explorer |
| Customer Orders | PostgreSQL | intent-sql-postgres |
| HR Database | SQLite | intent-sql-sqlite-hr |
| DuckDB Analytics | DuckDB | intent-duckdb-analytics |
| EV Population Stats | DuckDB | intent-duckdb-ev-population |
| JSONPlaceholder REST API | HTTP (JSON) | intent-http-jsonplaceholder |
| Paris Open Data API | HTTP (JSON) | intent-http-paris-opendata |
| MFlix Sample Collection | MongoDB | intent-mongodb-mflix |
| SpaceX GraphQL | GraphQL | intent-graphql-spacex |
Adapter wiring and sample domains live in config/adapters/ and examples/intent-templates/.
- Ask your database questions in any language — Connect Postgres, MySQL, MongoDB, DuckDB, or Elasticsearch and query them with natural language. Built-in language detection responds in the user's language automatically.
- Switch LLM providers without changing code — Swap between OpenAI, Anthropic, Gemini, Groq, Ollama, vLLM, and more with a config change.
- Build voice agents — Full-duplex speech-to-speech with interruption handling via PersonaPlex.
- Power agentic workflows — MCP-compatible, so AI agents can use ORBIT as a tool.
- Upload files and get answers — RAG over PDFs, images, and documents out of the box.
- Add guardrails and content moderation — Built-in safety layer with OpenAI, Anthropic, or local (Llama Guard) moderators to filter harmful content before it reaches users.
- Go from text to speech and back — Plug in STT (Whisper, Google, Gemini) and TTS (OpenAI, ElevenLabs, Coqui) providers for voice-enabled applications.
- Keep everything private — Self-host on your own infrastructure with RBAC, rate limiting, and audit logging.
LLM Providers: OpenAI, Anthropic, Google Gemini, Cohere, Groq, DeepSeek, Mistral, AWS Bedrock, Azure, Together, Ollama, vLLM, llama.cpp
Data Sources: PostgreSQL, MySQL, MongoDB, Elasticsearch, DuckDB, SQLite, HTTP/REST APIs, GraphQL
Vector Stores: Chroma, Qdrant, Pinecone, Milvus, Weaviate
| Without ORBIT | With ORBIT |
|---|---|
| One SDK per provider, rewrites when you switch | One OpenAI-compatible API across all providers |
| Separate pipelines for retrieval and inference | Unified model + retrieval + tooling gateway |
| Fragile glue scripts between data sources and LLMs | Production-ready connectors with policy controls |
| No visibility into what models are doing | Built-in RBAC, rate limiting, and audit logging |
- PoliceStats.ca — Explore Canadian Crime Statistics with AI. Ask about auto theft, break-ins, neighbourhood crime patterns, and cross-city comparisons, with answers grounded in source data citations.
Using ORBIT in production? Let us know and we'll add your project here.
| Client | Description |
|---|---|
| Web Chat | React UI |
| CLI | pip install schmitech-orbit-client |
| Mobile | iOS & Android (Expo) |
| Node SDK | Or use any OpenAI-compatible SDK |
Docker Compose (fastest path)
git clone https://github.com/schmitech/orbit.git && cd orbit/docker
docker compose up -dStarts ORBIT + Ollama with SmolLM2, auto-pulls models, and exposes the API on port 3000. The web admin UI is at /admin on the same host. Connect orbitchat from your host:
ORBIT_ADAPTER_KEYS='{"simple-chat":"default-key"}' npx orbitchatSee the full Docker Guide for GPU mode, volumes, and configuration.
Pre-built image (server only)
docker pull schmitech/orbit:basic
docker run -d --name orbit-basic -p 3000:3000 schmitech/orbit:basicIf Ollama runs on your host, add -e OLLAMA_HOST=host.docker.internal:11434 so the container can reach it. Includes simple-chat only.
From release tarball (production)
curl -L https://github.com/schmitech/orbit/releases/download/v2.6.5/orbit-2.6.5.tar.gz -o orbit-2.6.5.tar.gz
tar -xzf orbit-2.6.5.tar.gz && cd orbit-2.6.5
cp env.example .env && ./install/setup.sh
source venv/bin/activate
./bin/orbit.sh start && cat ./logs/orbit.log- Step-by-Step Tutorial — Chat with your own data in minutes
- Cookbook — Recipes for real-world use cases
- Documentation — Full architecture and setup guides
- GitHub Issues — Bug reports and feature requests
Contributions are welcome! Check the issues for good first tasks, or open a new one to discuss your idea.
If you find ORBIT useful, a star helps others discover the project.
Apache 2.0 — see LICENSE.