Teable
Teable ships Scheduled Routines, a four-tier AI model system, and multi-model image generation — three sparks in five days
A side-by-side editorial comparison of SiYuan and Joplin — release velocity, themes, recent moves, and the top alternatives to consider.
SiYuan v3.8.4 beta cycle adds agent-controlled database fields, MiniMax image gen, and skill file management
SiYuan is deep in the v3.8.4 pre-release cycle, now at beta.4, shipping a dense stream of enhancements across each daily build. The defining theme of this release cycle is agent-control expansion: the AI can now configure database fields, manage skill files, stream Markdown previews, and use custom AI provider headers — moving SiYuan from a tool where AI assists with writing to one where AI can reshape the workspace structure itself. Mobile UX and PDF annotation improvements are running in parallel.
Joplin 3.7 ships AI chat, semantic search, and MCP integration — all off by default, all controllable by the user.
Joplin 3.7 is the product's first real AI release: an in-app chat panel for querying the currently open note, semantic (meaning-based) search across notebooks, and an MCP server that lets external AI assistants connect to Joplin's note graph. The implementation is privacy-first by design — AI is disabled by default, local models (Ollama, LM Studio) are explicitly supported, and cloud AI services only receive the specific note content relevant to a request rather than the full notebook. A companion documentation post published September 14 lays out the privacy model explicitly.
SiYuan is deep in the v3.8.4 pre-release cycle, now at beta.4, shipping a dense stream of enhancements across each daily build. The defining theme of this release cycle is agent-control expansion: the AI can now configure database fields, manage skill files, stream Markdown previews, and use custom AI provider headers — moving SiYuan from a tool where AI assists with writing to one where AI can reshape the workspace structure itself. Mobile UX and PDF annotation improvements are running in parallel.
SiYuan is building toward an agent-orchestrated personal knowledge base, where the AI layer can modify not just content but the organizational schema. The skill file management system suggests an emerging plugin-like architecture for agent behaviors. As multimodal generation (MiniMax image support) gets wired in, SiYuan's trajectory is toward a locally-run AI workspace that rivals cloud-based tools without the data-residency trade-off.
v3.8.4 stable will ship soon given the move to beta.4. The agentic features (database field configuration, skill management) will attract integrations from local-first AI workflow builders. Expect MiniMax and other provider integrations to expand in the next cycle.
Joplin 3.7 is the product's first real AI release: an in-app chat panel for querying the currently open note, semantic (meaning-based) search across notebooks, and an MCP server that lets external AI assistants connect to Joplin's note graph. The implementation is privacy-first by design — AI is disabled by default, local models (Ollama, LM Studio) are explicitly supported, and cloud AI services only receive the specific note content relevant to a request rather than the full notebook. A companion documentation post published September 14 lays out the privacy model explicitly.
Joplin is repositioning from a sync-agnostic note-taking app into an AI-native knowledge base, differentiated by opt-in, local-first controls. The HMD Terra M preload partnership and the warrant canary point to a deliberate push toward privacy-conscious enterprise and professional users who distrust cloud-first tools. The MCP integration is particularly strategic: it makes Joplin's note graph accessible to external orchestration pipelines without locking into any particular AI provider.
The next major release will likely expand AI chat to multi-note context — currently limited to the open note — and add more configurable MCP tools. The HTR (handwritten text recognition) project from the 2024 French government partnership is also likely to appear in a near-term release.
Other Collab products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either SiYuan or Joplin.
Teable ships Scheduled Routines, a four-tier AI model system, and multi-model image generation — three sparks in five days
GitHub Copilot tightens enterprise governance while AI security scanning drops its CodeQL prerequisite
Mattermost v11.11 adds data spillage exposure tracking as v12.0 breaking changes loom
Nextcloud runs three LTS branches in parallel, shipping bug fixes and quiet performance wins.
Happeo doubles down on SEO content to own intranet search terms for mid-market buyers.
AFFiNE ships stable iOS Share Extension imports while patching editor correctness and selfhost deployment
See all SiYuan alternatives → · See all Joplin alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — local-first, mcp — within Collab. SiYuan and Joplin are shipping at a similar cadence (velocity 6.3 vs 6.3, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. SiYuan and Joplin are shipping at a similar cadence (velocity 6.3 vs 6.3, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Collab products to evaluate alongside.
Top SiYuan alternatives in Collab are ranked by recent ship velocity. Browse the "SiYuan alternatives" section above for the current picks, or visit /alternatives/siyuan for the full list with editorial commentary on each.
Top Joplin alternatives in Collab are ranked by recent ship velocity. Browse the "Joplin alternatives" section above for the current picks, or visit /alternatives/joplin for the full list with editorial commentary on each.