OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

PipesHub

An open-source workplace AI platform for connecting enterprise knowledge sources to AI applications, agents and search experiences.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

PipesHub — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an AI assistant or internal search experience needs grounded access to distributed business knowledge and users must receive only material they are authorized to see.

Who it is for

  • Organizations bringing internal business-system knowledge into AI tools.
  • Teams building permission-aware enterprise search or cited research interfaces.
  • Developers connecting agents, workflows or MCP clients to organizational context.

Documented uses

  • Search across connected business systems.
  • Provide AI agents with enterprise context.
  • Return answers with citations to source documents.
  • Retrieve knowledge while respecting source-level permissions.
  • Represent relationships across enterprise data through knowledge-graph retrieval.
Before you choose

Requirements & limits

The repository is public, open source and licensed under Apache-2.0. It identifies Docker, cloud and self-hosted environments, but the supplied material does not establish pricing, account requirements or service availability.

  • Whether the required business systems are covered by the documented connector approach.
  • Whether source-level permission filtering and cited answers are necessary.
  • Whether the intended integration is an agent, workflow, MCP client, SDK-based application or search interface.
  • Whether a Python-based, self-hosted or Docker-oriented technical stack fits the team’s environment.
  • Whether knowledge-graph retrieval is useful for the relationships within the organization’s data.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Connect an AI assistant to indexed company knowledge

Give an AI assistant permission-aware, cited context from enterprise systems after PipesHub is running and data is indexed.

Before you start

  • A running PipesHub instance with data indexed.
  • A Personal Access Token; the repository states that no admin access is needed for this step.
  • An assistant supported by the documented example, such as Claude Code, Cursor or Codex.

Steps

  1. Mint a Personal Access Token in PipesHub.

  2. Connect the assistant using the documented integration method: one command for Claude Code, or one configuration file for Cursor or Codex.

  3. Ask a question about the indexed company knowledge.

  4. Review the cited sources returned with the answer and the permission-filtered context.

Expected outcome

The assistant can use indexed business knowledge and return an answer with citations, limited by the user’s access rights.

Guide limitations

  • The supplied material does not include the exact token-screen steps or configuration contents.
  • The example is described as taking about ten minutes once PipesHub is running with data indexed; this is not an independently verified test.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
pipeshub-ai/pipeshub-ai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction