Nimbus
FuseBase is pivoting into AI app building while its marketing still sells the old portal category.
A side-by-side editorial comparison of NocoBase and Tracecat — release velocity, themes, recent moves, and the top alternatives to consider.
NocoBase is wiring its AI employees and its JS blocks to call each other
NocoBase is a self-hosted low-code platform, currently building 2.2.0 in the open across alpha and beta pre-releases. The visible work splits between a client v2 rewrite — tabs, subpages and pop-ups gaining linkage rules, configurable route entry modes — and an AI employees layer that is being connected to the platform's JS blocks in both directions.
Tracecat is drawing hard boundaries around what its agents are allowed to touch
Six release candidates in two weeks on the 1.0.0-beta.51 line. The agent surface is where most work lands: batch approvals, a Mistral provider, catalog IDs for custom models, interactive turns prioritised on a shared queue, and streaming status for pending approvals. Running alongside it is a steady tightening of the execution boundary — nested action execution constrained, run_python excluded from agent tools, inbound auth no longer forwarded to user MCP servers, and the Action Gateway made mandatory as an explicit breaking change.
NocoBase is a self-hosted low-code platform, currently building 2.2.0 in the open across alpha and beta pre-releases. The visible work splits between a client v2 rewrite — tabs, subpages and pop-ups gaining linkage rules, configurable route entry modes — and an AI employees layer that is being connected to the platform's JS blocks in both directions.
The AI employees feature started as an assistant sitting beside the app. These releases dissolve that boundary: JS blocks can trigger AI employee tasks through a RunJS API, and AI employees now have frontend tools that operate JS blocks. Custom application logic and the agent layer become mutually callable, which is a different product than a chat panel bolted onto a builder. Around it, the approval workflow is being ported to client v2 with card-style selection and inline usage instructions.
With the call path open in both directions, the unresolved question these entries raise is governance — what an AI employee is permitted to execute and under whose authority — so expect permission scoping around AI employee tasks before 2.2.0 stabilizes.
Six release candidates in two weeks on the 1.0.0-beta.51 line. The agent surface is where most work lands: batch approvals, a Mistral provider, catalog IDs for custom models, interactive turns prioritised on a shared queue, and streaming status for pending approvals. Running alongside it is a steady tightening of the execution boundary — nested action execution constrained, run_python excluded from agent tools, inbound auth no longer forwarded to user MCP servers, and the Action Gateway made mandatory as an explicit breaking change.
This is a security automation platform working out how much autonomy to hand an agent and where the trust boundary sits. The pattern across candidates is capability and constraint arriving together: each new agent affordance comes with a narrowing of what agents can reach. Integration work on SentinelOne, Okta SAML, Google SecOps and MCP connections fills the rest.
Expect the beta.51 candidate run to converge toward a 1.0.0 release with the Action Gateway as the single enforced execution path, and further constraints on agent tool access as more MCP servers are connected.
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 NocoBase or Tracecat.
FuseBase is pivoting into AI app building while its marketing still sells the old portal category.
Atlassian is building the plumbing for other people's AI agents to work inside Jira.
Hive is turning Buzz into a delegator while grinding out resourcing depth and UI polish.
Wiring itself under monday.com, ClickUp and Trello as the capacity layer they lack
Wiring itself under monday.com, ClickUp and Trello as the capacity layer they lack
Celoxis publishes PMO thought-leadership at pace; the product ships out of view.
See all NocoBase alternatives → · See all Tracecat alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
Both compete on the same themes — ai-agents — within PM. NocoBase and Tracecat 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. NocoBase and Tracecat 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 PM products to evaluate alongside.
Top NocoBase alternatives in PM are ranked by recent ship velocity. Browse the "NocoBase alternatives" section above for the current picks, or visit /alternatives/nocobase 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.