swiss-ai-hub-core
The foundational shared library for Swiss AI Hub. Every other Swiss AI Hub Python package depends on it — you rarely install it directly.
What is Swiss AI Hub?
Swiss AI Hub is an open-source, self-hosted AI platform for enterprises. One
docker compose up starts ~30 integrated containers — LLM gateway (LiteLLM), vector search (Milvus), data pipelines
(Dagster), SSO (Keycloak), observability (Langfuse), a chat UI (Open-WebUI), and more. You build custom agents,
pipelines, processes, and bot integrations with the Python SDK; the platform provides the runtime.
What is this package?
swiss-ai-hub-core is the shared foundation the rest of the SDK is built on. It is a library, not a runnable
service — it provides the Swiss AI Agent Protocol (typed, event-driven messaging over NATS), authentication &
multi-tenancy, the Form configuration system, and shared AI/ML utilities. Every higher-level package imports it.
You usually don't install this directly
Install the package for what you're building — each one depends on swiss-ai-hub-core and pulls it in
automatically:
| You want to… | Install | Imports as |
|---|---|---|
| Build a workflow-based AI agent | swiss-ai-hub-agent |
swiss_ai_hub.agent |
| Expose a REST API + WebSocket gateway | swiss-ai-hub-api |
swiss_ai_hub.api |
| Connect agents to Teams / Slack / web chat | swiss-ai-hub-bot |
swiss_ai_hub.bot |
| Build a document-ingestion pipeline | swiss-ai-hub-pipeline |
swiss_ai_hub.pipeline |
| Orchestrate multi-entity processes | swiss-ai-hub-process |
swiss_ai_hub.process |
| Install the whole SDK | swiss-ai-hub (meta) |
(pulls all of the above) |
Reach for swiss-ai-hub-core on its own only in the rare case where you're writing a service that speaks the Swiss AI
Agent Protocol directly, without one of the higher-level engines above.
Installation
pip install swiss-ai-hub-core # usually unnecessary — it comes in with the package you actually want
All distributions share the swiss_ai_hub.* native (PEP 420) namespace, so
swiss_ai_hub.core, swiss_ai_hub.agent, … coexist as sibling modules regardless of which subset you install.
Links
- Source & issues: https://github.com/bbvch-ai/aihub-core
- Documentation: https://bbvch-ai.github.io/aihub-core/
License
Apache-2.0 — see packages/core/LICENSE. For the full per-package license matrix, see LICENSES.md.
Part of Swiss AI Hub. Built in Switzerland by bbv Software Services.
2 maintainers
Metadata
2 maintainers
Release files for swiss-ai-hub-core 0.295.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| swiss_ai_hub_core-0.295.0.tar.gz | 560.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| swiss_ai_hub_core-0.295.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.5 MB
Release files / swiss_ai_hub_core-0.295.0.tar.gz
| Download URL | swiss_ai_hub_core-0.295.0.tar.gz |
|---|---|
| Size | 560.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a0a0092fffc48f661c0be8340c7e2c8f54ee864114964aa67f06f0833fc06475
|
|
BLAKE2b-256 checksum How to use checksums |
be38d18a3c9730ce534ad1f8377b06324c4e5fc7d1db3a2999b2eb9190dff2bc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.20 {"installer":{"name":"uv","version":"0.11.20","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / swiss_ai_hub_core-0.295.0-py3-none-any.whl
| Download URL | swiss_ai_hub_core-0.295.0-py3-none-any.whl |
|---|---|
| Size | 949.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a530bf1b349d6c8573df16205663e72687af9e0675f8d09a0b1695d54e423700
|
|
BLAKE2b-256 checksum How to use checksums |
5cd8aee179f95238eb056a77c13497f1ec0868020458d4d9ae44b22dac975a6b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.20 {"installer":{"name":"uv","version":"0.11.20","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
