Why it matters
This release is significant for builders as it offers a self-hosted, privacy-focused environment for integrating AI agents into knowledge workflows. Developers can leverage SiYuan's architecture and API to build more sophisticated AI-powered applications and tools for personal productivity.

What changed

SiYuan has released version v3.8.11-rc.3 of its open-source, privacy-first knowledge workspace. This version continues to develop the platform's core functionality, which includes fine-grained block-level referencing, Markdown WYSIWYG editing, and support for various content types like mathematical formulas, charts, and PDF annotations. The workspace is designed for humans and AI agents to collaborate, with features such as AI writing and Q&A chat via OpenAI API, and Tesseract OCR integration. The release also includes updates to its architecture and ecosystem, with projects like lute for the editor engine, bazaar for a community marketplace, and petal for a plugin API. Installation options are extensive, including desktop and mobile app markets, direct installation packages, package managers, and various hosting solutions like Docker, Kubernetes, Unraid, and TrueNAS. The Docker deployment has been refined, with specific instructions for running the container using b3log/siyuan image, including parameters for workspace mapping, access authentication, and user IDs (PUID/PGID) to manage permissions. The latest release candidate, v3.8.11-rc.3, indicates ongoing development and refinement of these features.

Why it matters for builders

For AI builders, SiYuan offers a robust, self-hosted foundation for developing and deploying AI-powered knowledge management solutions. The platform's emphasis on privacy and local data storage is crucial for applications handling sensitive information. The integration of AI features, such as OpenAI API support for writing and Q&A, provides a direct pathway for incorporating generative AI into user workflows. Furthermore, SiYuan's extensibility through its plugin API (petal) and community marketplace (bazaar) allows developers to create custom agents, tools, and integrations, fostering a rich ecosystem for AI-driven productivity.

Practical impact

Builders can explore integrating their custom AI agents or services with SiYuan by utilizing its API and plugin architecture. The Docker deployment options provide a straightforward method for self-hosting and scaling SiYuan instances, enabling the creation of private, AI-enhanced knowledge bases. Developers can experiment with the AI writing and Q&A chat features, potentially extending them or building custom interfaces on top of the OpenAI API integration. The block-level referencing and SQL query embed features also offer opportunities for building more complex data-driven AI applications within the workspace.

Caveats and source limits

The provided source is a GitHub repository description and excerpt, focusing on features and deployment. Specific details regarding the exact changes in version v3.8.11-rc.3, such as bug fixes or new AI agent functionalities introduced in this particular release candidate, are not detailed. The pricing model for advanced features is mentioned but not elaborated upon, and independent benchmark results for AI performance are absent. The source primarily describes the platform's capabilities and architecture rather than providing in-depth technical documentation for advanced AI agent integration.

Sources

Written with AI assistance from the linked sources; every claim below was checked against them automatically. How we produce articles.

Claim check: 5/5 supported claims - 5 evidence links - 100% avg confidence
  • SiYuan is an open-source, privacy-first, self-hosted knowledge workspace designed for human-AI agent collaboration.supported - github.com
  • SiYuan supports AI writing and Q&A chat via OpenAI API.supported - github.com
  • SiYuan offers features like block-level reference, two-way links, custom attributes, and SQL query embeds.supported - github.com
  • SiYuan supports Docker deployment with options for PUID, PGID, workspace mapping, and access authentication.supported - github.com
  • The latest release is v3.8.11-rc.3.supported - github.com

Caveats

  • Single-source caution: verify critical details at the linked source.
Radar score 87/100 - how it was calculated
Reliability82
Freshness95
Novelty73
Technical85
Developer96
Ecosystem72
Confidence96
  • Reliability 82: GitHub metadata supports source trust
  • Freshness 95: Fresh GitHub release date
  • Novelty 73: Fresh GitHub release
  • Technical 85: Repository technical metadata
  • Developer 96: Developer tooling signals
  • Ecosystem 72: Fresh GitHub release
  • Confidence 96: Claims have reliable evidence
Share
XLinkedInHacker News

Discussion

Loading comments...

Related articles

Agents - Nov 19, 2026Mingle: Bring AI Agents to Your Chat Apps LocallyMingle is a new open-source project that allows AI agents to integrate directly into existing chat applications like Slack, Discord, and WeChat. It runs entirely on the user's machine, ensuring data privacy and eliminating the need for external servers or subscriptions.Agents - Nov 18, 2026faf-cli v8.10.0 Enhances AI Agent Context with Project FactsThe faf-cli tool has released version 8.10.0, introducing "Project Facts" to provide AI coding agents with versioned, stack-specific context. This update ensures that AI agents receive accurate information about a project's real stack, reducing guesswork and improving code generation.Agents - Nov 18, 2026Rome OS: Open-Source Agent OS for Recursive AgentsRome OS is an open-source operating system for recursive AI agents, designed to scale the agent's environment rather than just model size. It offers a collaborative, guardrailed space for human-agent interaction, enabling agents to build their own workflows and improve over time.Agents - Nov 20, 2026Grajo: Self-Hosted Agentic Framework and MCP PlatformGrajo is an open-source, self-hostable agentic framework and Model Context Protocol (MCP) platform. It allows users to build and run AI agents with persistent memory, research capabilities, and P2P sharing, while also serving as an MCP platform to connect existing AI clients like Claude Code and Cursor.Agents - Nov 19, 2026OpenCrawl Core: Multiplayer Context Layer for Coding AgentsOpenCrawl Core introduces a multiplayer context layer designed to enhance collaboration among coding agents. It enables agents to share search results, memory files, and coordinate actions, working with models like Claude Code and Codex.Agents - Nov 17, 2026Overleaf CLI (olcli) v0.17.0 Adds AI Agent IntegrationThe Overleaf CLI tool, olcli, has released version 0.17.0, introducing an MCP server for AI agents. This allows AI agents to interact with Overleaf projects, prompting users before making changes.