What problem it solves

Teams need to bring documents together so they can be searched, reasoned over and kept up to date. They also need a way to move from source-grounded retrieval to multi-step tasks while maintaining organized, current knowledge.

Key features

• Three knowledge workflows — RAG supports lookup, an agent handles multi-step tasks, and a wiki organizes knowledge. All three operate on the same knowledge bases.

  Source: README

• Source-grounded retrieval and reasoning — Quick Q&A answers from the knowledge base with RAG and cites its sources, while smart reasoning plans multi-step work and shows each step.

  Source: README

• Skills and sandbox execution — Skills can run in session-persistent Docker, E2B or Cube sandboxes with an interactive terminal and graphical desktop. Generated files can be previewed and downloaded.

  Source: README

• Broad data and integration support — Knowledge can be synchronized from multiple platforms and parsed from common document formats. Q&A, embedding, MCP, and API access extend the platform into existing workflows.

  Source: README

• Flexible deployment and operations — Models, vector databases, and storage backends can be replaced independently. The project supports local, private-cloud, Docker Compose, and Kubernetes deployment paths.

  Source: README, helm

Quick start

Copied verbatim from the project's README.

git clone https://github.com/Tencent/WeKnora.git
cd WeKnora
cp .env.example .env    # Edit .env as needed, see comments in the file
docker compose pull     # Pull the latest images
docker compose up -d    # Start core services

docker compose --profile neo4j --profile minio pull
docker compose --profile neo4j --profile minio up -d
docker compose down     # Stop services

Who it may suit

Inference: This may suit teams that need to search, reason over, and maintain enterprise documents, as well as developers building document-aware agents and knowledge tools.

Topics to discuss

• Which knowledge sources and document formats should be prioritized for connected workflows?

• How should permissions and approval policies extend to agent actions and sandbox execution?

• Which integrations are most useful for connecting shared knowledge to existing communication and development tools?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/Tencent/WeKnora#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.