NocoBase
NocoBase's Runner Agent gets conversation management, task links and agent switching mid-thread.
A side-by-side editorial comparison of Nifty and Tracecat — release velocity, themes, recent moves, and the top alternatives to consider.
Nifty is widening its MCP server from task access into files, docs, and safe concurrent edits.
Nifty's August digest is dominated by MCP expansion one month after the server shipped. Assistants can now upload a file from a path or URL, create and file Docs with visibility control, and attach or detach them from tasks; large document reads dropped from minutes to roughly a second, and a conflict check stops an assistant overwriting a teammate's later edit. Reporting also gained funnel charts, percentage number widgets, and a large speedup on twelve-month reports.
Tracecat's 1.3 alphas keep reworking agent plumbing: tunnels, multi-org MCP, pluggable runners.
Tracecat is mid-cycle on 1.3, and nearly every change is agent infrastructure. The alphas route agent MCP and tool calls through tunnels, let one MCP OAuth login cover multiple organizations, trace LLM proxy requests, and raise agent timeouts to two hours. The nightly builds add a session command store, chat steering, and now a pluggable runner for stdio MCP servers.
Nifty's August digest is dominated by MCP expansion one month after the server shipped. Assistants can now upload a file from a path or URL, create and file Docs with visibility control, and attach or detach them from tasks; large document reads dropped from minutes to roughly a second, and a conflict check stops an assistant overwriting a teammate's later edit. Reporting also gained funnel charts, percentage number widgets, and a large speedup on twelve-month reports.
The MCP server is clearly Nifty's main investment, and the August work is about making it fast and safe enough for real use rather than extending what it can reach. The concurrency guard is the notable detail: it treats an assistant as one writer among several, which is the problem every multi-agent workspace eventually hits. Distribution through the Microsoft 365 Copilot admin center aims the same capability at buyers who would never configure an MCP client themselves.
Expect the MCP surface to keep absorbing the remaining object types and Nifty to lean harder on admin-center distribution, with reporting performance work continuing behind it.
Tracecat is mid-cycle on 1.3, and nearly every change is agent infrastructure. The alphas route agent MCP and tool calls through tunnels, let one MCP OAuth login cover multiple organizations, trace LLM proxy requests, and raise agent timeouts to two hours. The nightly builds add a session command store, chat steering, and now a pluggable runner for stdio MCP servers.
The 1.3 line is making agents long-running, observable, and able to reach private infrastructure. Maintenance releases on 1.1 and 1.2 carried the same breaking org-scoping fix, so older lines are being patched in parallel.
Session commands and chat steering in the nightlies look set to land in the next 1.3 alpha as user-facing controls for steering running agent sessions.
Other PM 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 Nifty or Tracecat.
NocoBase's Runner Agent gets conversation management, task links and agent switching mid-thread.
Camunda opens the 8.11 cycle with job-worker fixes and variable metadata across gRPC, REST and MCP.
Todoist's 2026 bets are on capture: voice via Ramble, photos and files via Task Capture.
Atarim's AI experts now propose changes to live pages as drafts, and the app runs on phones.
Fibery's MCP server can now upload local files, so AI assistants can attach screenshots and images.
SmartSuite adds a scheduled JavaScript runtime with secrets and run history.
See all Nifty alternatives → · See all Tracecat alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — mcp — within PM. Tracecat is currently shipping more aggressively (velocity 6.3 vs 2.5), with 0 editorial sparks in the last 30 days against 0. 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. Tracecat is currently shipping more aggressively (velocity 6.3 vs 2.5), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other PM products to evaluate alongside.
Top Nifty alternatives in PM are ranked by recent ship velocity. Browse the "Nifty alternatives" section above for the current picks, or visit /alternatives/nifty for the full list with editorial commentary on each.
Top Tracecat alternatives in PM are ranked by recent ship velocity. Browse the "Tracecat alternatives" section above for the current picks, or visit /alternatives/tracecat for the full list with editorial commentary on each.