PipesHub
Self-hosted workplace search and AI answers across 50+ connected apps, filtered by each user's permissions.
Quick answer
PipesHub is a self-hosted workplace search and AI answers across 50+ connected apps, filtered by each user's permissions, listed under Knowledge base & RAG. A typical small-business use: one search box and AI assistant over the company's Drive, Slack, email and wiki, without exposing files people can't open. Official hardware: minimum 8 GB RAM (recommended 16 GB RAM). That fits a Hetzner Cloud CPX32 server at about €35.99/month (server only, excl. VAT; €69.99/month for the recommended spec). License: Apache-2.0, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 27, 2026.
What is PipesHub?
PipesHub connects Slack, Google Drive, Gmail, Jira, Confluence, SharePoint, Notion and 50+ other systems, indexes them in real time or on a schedule, and answers questions with citations while respecting what each person is allowed to see. The same permission-aware retrieval is available to your own agents through APIs, SDKs (Node, Python, Go) and an MCP server. It works with any LLM provider; a managed PipesHub Cloud also exists.
Where it fits in a 10–200 person business
- One search box and AI assistant over the company's Drive, Slack, email and wiki, without exposing files people can't open
- Give internal agents or coding assistants secure access to company knowledge through MCP
- Replace a paid enterprise-search SaaS while keeping documents inside your own servers
These use cases are our editorial suggestions, not claims made by the project.
Can a business use PipesHub? (license)
| License | Apache-2.0 |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep the license and notices. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does PipesHub phone home?
| Telemetry (usage data sent to the vendor) | On by default Product metrics and event collection run in every service unless disabled. How to turn it off: Set TELEMETRY_COLLECTION_FLAG=false. Source: github.com/pipeshub-ai/pipeshub-ai/blob/main/deployment/docker-compose/ADVANCED_DEPLOYMENT.md |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Not documented |
| Single sign-on (OIDC / SAML / LDAP) | Free Google and Microsoft sign-in are built into the open-source app. The docs site still lists SAML SSO and generic OAuth, but the repository's 1.0 upgrade notes say both are removed in 1.0, so we leave them as not confirmed. Source: docs.pipeshub.com/system-overview/authentication · github.com/pipeshub-ai/pipeshub-ai/blob/main/docs/deployment/upgrading-to-1.0-sign-in.md |
| Audit log | Not documented |
| Role-based access control (RBAC) | Not documented |
| Data residency / GDPR notes from the project | Documented The project says it is fully self-hostable with any LLM provider in your own VPC, so data does not leave your infrastructure. |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does PipesHub need?
| Minimum | 8 GB RAM |
|---|---|
| Recommended | 16 GB RAM |
The project gives RAM classes rather than exact minimums: "8 GB-class laptop" for the Eval topology, "16 GB host / 8 GB Docker VM" for Slim, and "16 GB+" for Full. The Full image bundles an embedding model (about 1.3 GB extra); Slim downloads it on first use. No CPU or disk figures.
How much does it cost to host PipesHub per month?
| Minimum spec | 8 GB RAM → CPX32 (4 vCPU, 8 GB, 160 GB disk) €35.99/mo |
|---|---|
| Recommended spec | 16 GB RAM → CPX42 (8 vCPU, 16 GB, 320 GB disk) €69.99/mo |
How we got this: we took the cheapest Hetzner Cloud Regular Performance (shared AMD vCPU) plan with at least the RAM and vCPU the project lists, using prices read from www.hetzner.com/cloud/regular-performance on 2026-10-25. "From" monthly price cap shown by Hetzner, excluding VAT. Prices vary by location. Covers the server only; it excludes LLM API usage, backups, extra storage, GPUs and your time. Disk is not matched; add a volume if you need more than the plan includes.
How to deploy PipesHub
Method: Docker Compose (interactive installer)
curl -fsSL https://get.pipeshub.com/install | bash
# get.pipeshub.com redirects to the repo's install.sh; if it is unreachable use:
# curl -fsSL https://raw.githubusercontent.com/pipeshub-ai/pipeshub-ai/main/install.sh | bash
# then open http://localhost:3000From the official instructions: github.com/pipeshub-ai/pipeshub-ai/blob/main/deployment/docker-compose/ADVANCED_DEPLOYMENT.md. Always check the source for the current version before you run it.
Known gotchas when self-hosting PipesHub
- On a cloud server, serve it over HTTPS (Cloudflare, Nginx or Traefik). Browsers block some requests over plain HTTP, and a white screen after an HTTP-only deploy is usually this. source
- Neo4j is required even in the small Eval setup, because records and permissions live in the graph store. Do not drop it to save RAM. source
- Product telemetry is on unless you set TELEMETRY_COLLECTION_FLAG=false, which turns all telemetry code off. source
- The upcoming 1.0 release removes SAML single sign-on and generic OAuth/OIDC sign-in; password, email OTP, Google and Microsoft sign-in stay. Workspaces using SAML should switch before upgrading. source
Alternatives in Knowledge base & RAG
- RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare PipesHub vs RAGFlow
- AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs PipesHub
- PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare PipesHub vs PrivateGPT
- Open Notebook Private, self-hosted alternative to Google NotebookLM with your choice of AI models. Compare Open Notebook vs PipesHub
- Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare Onyx (formerly Danswer) vs PipesHub
- FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare FastGPT vs PipesHub
- kotaemon Open-source RAG web app for chatting with your documents, with citations and GraphRAG. Compare kotaemon vs PipesHub
- MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare MaxKB vs PipesHub
- DocsGPT Open-source platform for AI agents and assistants that answer from your documents with sources. Compare DocsGPT vs PipesHub
PipesHub FAQ
How much RAM does PipesHub need?
The official minimum is 8 GB RAM. The recommended spec is 16 GB RAM. The project gives RAM classes rather than exact minimums: "8 GB-class laptop" for the Eval topology, "16 GB host / 8 GB Docker VM" for Slim, and "16 GB+" for Full. The Full image bundles an embedding model (about 1.3 GB extra); Slim downloads it on first use. No CPU or disk figures.
How much does it cost to self-host PipesHub?
The software is free to download. Based on the official minimum 8 GB RAM (recommended 16 GB RAM): That fits a Hetzner Cloud CPX32 server at about €35.99/month (server only, excl. VAT; €69.99/month for the recommended spec). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is PipesHub free for commercial use?
PipesHub is licensed under Apache-2.0 (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep the license and notices. This is a summary, not legal advice.
What are common problems when self-hosting PipesHub?
On a cloud server, serve it over HTTPS (Cloudflare, Nginx or Traefik). Browsers block some requests over plain HTTP, and a white screen after an HTTP-only deploy is usually this. Neo4j is required even in the small Eval setup, because records and permissions live in the graph store. Do not drop it to save RAM. Product telemetry is on unless you set TELEMETRY_COLLECTION_FLAG=false, which turns all telemetry code off. The upcoming 1.0 release removes SAML single sign-on and generic OAuth/OIDC sign-in; password, email OTP, Google and Microsoft sign-in stay. Workspaces using SAML should switch before upgrading.
Is PipesHub still maintained?
Yes, it is actively developed. Last commit: Oct 27, 2026. Latest release: v0.10.0 (Oct 12, 2026). Checked Oct 27, 2026.
How do I install PipesHub?
The official method is Docker Compose (interactive installer). The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/pipeshub-ai/pipeshub-ai/blob/main/deployment/docker-compose/ADVANCED_DEPLOYMENT.md
What are self-hosted alternatives to PipesHub?
Other apps in Knowledge base & RAG: RAGFlow, AnythingLLM, PrivateGPT, Open Notebook, Onyx (formerly Danswer), FastGPT, kotaemon, MaxKB, DocsGPT.
Sources
- GitHub repository: github.com/pipeshub-ai/pipeshub-ai
- Official documentation: docs.pipeshub.com
- License text: github.com/pipeshub-ai/pipeshub-ai/blob/main/LICENSE
- Hardware requirements, Gotcha 2: github.com/pipeshub-ai/pipeshub-ai/blob/main/deployment/docker-compose/ADVANCED_DEPLOYMENT.md#deployment-types-slim-vs-full-vs-eval
- Deploy instructions, Gotcha 3: github.com/pipeshub-ai/pipeshub-ai/blob/main/deployment/docker-compose/ADVANCED_DEPLOYMENT.md
- Gotcha 1: github.com/pipeshub-ai/pipeshub-ai#readme
- Gotcha 4: github.com/pipeshub-ai/pipeshub-ai/blob/main/docs/deployment/upgrading-to-1.0-sign-in.md
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-27. Spotted something out of date? Tell us.