Discourse vs Hatz AI
Side-by-side trajectory, velocity, and editorial themes.
Discourse opens its AI bot to any external MCP server, treating the forum as an agent host.
Discourse runs on a monthly main release plus periodic security intermediates, and the editorial focus across recent posts is clearly AI plumbing. March added Bring-Your-Own MCP server support to the Discourse AI Bot, alongside documented AI credentials management and SSO auto-provisioning for forum admins. The team has also been adjusting its release-communication process, with backdated intermediate-release topics filling earlier gaps.
Discourse is positioning the forum as an environment that hosts agents, not just a place that uses AI features. By accepting any MCP-compatible tool provider as a backend, it makes itself the substrate community managers extend with arbitrary external capabilities — search, ticketing, knowledge bases, whatever the host wires in. SSO auto-provisioning and structured form templates round out the admin surface that this agent-host posture needs.
Expect deeper agent UX inside topics — more entry points and persona configuration — alongside audit and observability tooling for what external MCP tools do on a forum. Community trust depends on that side staying explainable.
Hatz AI is building the AI workspace for MSPs — per-message model routing, tenant tooling, custom MCP.
Hatz AI is shipping at a high cadence across three connected themes. First, model routing: Auto-LLM picks the right model per message based on task and tools, then layered into Lite, Performance, and Turbo tiers; the catalog keeps adding models (Opus 4.7, Gemini 3.5 Flash, Gemini 3.1 Flash Lite, Gemma 4) with per-model credit multipliers surfaced in the UI. Second, MSP control plane: bulk tenant creation via CSV, custom roles with credit limits, workshop access controls, and embedded support chat in the admin dashboard. Third, surface expansion: audio uploads with auto-transcription, image generation in workflows, file output attaching to chats, 60+ supported file types, speech-to-text in chat, and a steady cadence of integrations and custom MCP server improvements.
The product is taking shape as a multi-tenant AI workspace tuned for MSPs and partner-led delivery — the tenant CSV, credit limits, and workshop sharing are unusual for a generalist AI tool and tell you who buys this. Auto-LLM and tiered routing make sense in that context: an MSP needs cost control across many tenants without micromanaging model picks. Custom MCP and the broad integration cadence position Hatz as a tools-aggregator over multiple LLMs rather than a model wrapper.
Expect more MSP-centric controls — per-tenant budgets, white-label theming, billing reconciliation — and Auto-LLM to grow visible routing telemetry so MSP admins can see why a given model was picked. The custom MCP surface is likely to evolve toward a marketplace pattern with shareable MCP packages across tenants.
See more alternatives to Discourse →
See more alternatives to Hatz AI →