AFFiNE
AFFiNE ships stable iOS Share Extension imports while patching editor correctness and selfhost deployment
A side-by-side editorial comparison of Joplin and Softr — release velocity, themes, recent moves, and the top alternatives to consider.
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.
Softr ships MCP and embedded agents, making no-code apps AI-orchestratable
Softr has added two substantial capability layers in rapid succession: autonomous agents embedded directly into user apps (August 26), and full MCP integration that makes every platform surface controllable via Claude, ChatGPT, or any MCP-compatible client (September 6–8). Both ship on all plans with no additional AI credits required. The platform still centers on visual no-code building, but these moves position it as infrastructure for AI-driven workflows rather than a pure visual builder.
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.
Softr has added two substantial capability layers in rapid succession: autonomous agents embedded directly into user apps (August 26), and full MCP integration that makes every platform surface controllable via Claude, ChatGPT, or any MCP-compatible client (September 6–8). Both ship on all plans with no additional AI credits required. The platform still centers on visual no-code building, but these moves position it as infrastructure for AI-driven workflows rather than a pure visual builder.
Softr is converging on a model where apps built on its platform are simultaneously human-navigable and machine-orchestratable. The MCP rollout — announced as a multi-day series of drops — indicates they are treating AI interoperability as a primary product surface, not a feature add-on. The logical extension is multi-step agentic chains that span data sources and scheduled workflows, which their August agent launch already scaffolds.
Softr will likely expand scheduled agents into more complex multi-step automation chains, and extend MCP coverage to user-management and permission APIs. The remaining MCP drops telegraphed for the week of September 6 will reveal how far they are willing to expose internal platform primitives to external AI orchestration.
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 Joplin or Softr.
AFFiNE ships stable iOS Share Extension imports while patching editor correctness and selfhost deployment
SiYuan 3.8.4 makes AI agents first-class participants in personal knowledge management
Readwise ships library-wide Ghostreader with tool-calling: tag, annotate, save across your full archive
GitHub Copilot splits into cost tiers and deepens agentic automation across the dev stack
Nuclino ships its MCP server in January 2026, making the team knowledge base queryable by AI agents—a directional move toward AI-native knowledge management.
Wiki.js 3.0 beta closes enterprise auth and SEO gaps at sprint pace
See all Joplin alternatives → · See all Softr alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — mcp — within Collab. Softr is currently shipping more aggressively (velocity 7.5 vs 6.3), with 2 editorial sparks in the last 30 days against 1. 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. Softr is currently shipping more aggressively (velocity 7.5 vs 6.3), with 2 editorial sparks in the last 30 days against 1. For your specific use case, the alternatives sections above list other Collab products to evaluate alongside.
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.
Top Softr alternatives in Collab are ranked by recent ship velocity. Browse the "Softr alternatives" section above for the current picks, or visit /alternatives/softr for the full list with editorial commentary on each.