Fulcrum
Fulcrum ships MCP server and AI Toolkit to let AI assistants build and query field data forms
Comparison · Analytics
Count vs OpenHouse
A side-by-side editorial comparison of Count and OpenHouse — release velocity, themes, recent moves, and the top alternatives to consider.
Count vs OpenHouse: at a glance
What is Count?
Count is turning its BI canvas into a governed, agent-operated analytics platform.
Count is a data-canvas analytics tool reorganizing itself around an AI agent. In two months it shipped a full public REST API and hosted MCP server (governed agent access via OAuth and service accounts), a major agent upgrade that lets the agent read and edit the entire canvas and answer from Slack, and the ability to plug external MCP servers (Linear, HubSpot, Stripe, Slack, Drive) into the agent. Around the agent it keeps broadening warehouse support—ClickHouse, Snowflake semantic models, OSI—alongside chart and UX polish.
What is OpenHouse?
OpenHouse breaks ground on Iceberg views while tightening storage lifecycle and authorization
OpenHouse (LinkedIn's managed Iceberg tables service) is shipping at a rapid v0.5.x pace with multiple improvements per week. Recent work spans three areas: storage lifecycle management (native snapshot expiration with reference age defaults, orphan file reclamation), authorization hardening (routing RTAS operations through proper table privilege checks), and the first scaffolding for Iceberg view support (entityType discriminator, table-scoped HTS queries).
Count vs OpenHouse: editorial side-by-side
Count
6.3ANALYTICS
Count is turning its BI canvas into a governed, agent-operated analytics platform.
◆ Current state
Count is a data-canvas analytics tool reorganizing itself around an AI agent. In two months it shipped a full public REST API and hosted MCP server (governed agent access via OAuth and service accounts), a major agent upgrade that lets the agent read and edit the entire canvas and answer from Slack, and the ability to plug external MCP servers (Linear, HubSpot, Stripe, Slack, Drive) into the agent. Around the agent it keeps broadening warehouse support—ClickHouse, Snowflake semantic models, OSI—alongside chart and UX polish.
◆ Where it's heading
Count is building toward analytics where agents are first-class operators: a governed API/MCP layer for access, an agent that drives the canvas end to end, external tool reach via MCP, and connection-level context so guidance is captured once and inherited. Governance—permissions, scopes, service accounts—is the enabling layer that makes agent access acceptable in real data stacks rather than a bolt-on.
◆ Prediction
Expect more connection- and warehouse-level context controls, a widening catalog of supported external MCP integrations, and deeper Slack-native agent workflows.
OpenHouse
6.3ANALYTICS
OpenHouse breaks ground on Iceberg views while tightening storage lifecycle and authorization
◆ Current state
OpenHouse (LinkedIn's managed Iceberg tables service) is shipping at a rapid v0.5.x pace with multiple improvements per week. Recent work spans three areas: storage lifecycle management (native snapshot expiration with reference age defaults, orphan file reclamation), authorization hardening (routing RTAS operations through proper table privilege checks), and the first scaffolding for Iceberg view support (entityType discriminator, table-scoped HTS queries).
◆ Where it's heading
The entityType discriminator in v0.5.490 is the most directional move in this window — it creates the data model prerequisite for treating views as first-class entities alongside tables, something OpenHouse has not supported. Storage lifecycle work is converging on Iceberg-native mechanisms, reducing custom expiration logic. The post-commit operations framework in v0.5.492 is infrastructure that will allow OpenHouse to add downstream hooks (compaction triggers, notifications) without catalog coupling.
◆ Prediction
Iceberg view read support will arrive in the next several releases, building on the discriminator and HTS scaffolding now in place. The authorization model for views will be an open question — watch whether they reuse the table ACL path or introduce a parallel model.
Alternatives to Count and OpenHouse
Other Analytics 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 Count or OpenHouse.
Holistics
Holistics builds AI governance and docs-as-analytics in parallel, shipping both weekly
dbt Core
dbt 2.0 enters final RC with beta Snowflake interactive_table materialization and full ClickHouse MV support.
Lightdash
Lightdash is cutting its dbt dependency and building AI-powered authoring into every layer of its BI stack.
Keboola
Keboola's Kai AI assistant hits GA, completing the pivot from data platform to AI-native pipeline orchestration layer.
Omni
Omni's Apps reach general availability, completing its embedded analytics platform pitch.
See all Count alternatives → · See all OpenHouse alternatives →
Recent activity from Count and OpenHouse
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 14h agoOpenHousev0.5.492: Add a generic bounded post commit operations framework (#729)
- 5d agoOpenHousev0.5.491
- 5d agoOpenHousev0.5.490: Add entityType discriminator and table-scoped HTS queries (#696) ⚡
- 7d agoOpenHousev0.5.489: Backfill history.expire.max-ref-age-ms with Snapshot Expiration (#708)
- 11d agoOpenHousev0.5.488: [RTAS] Use table privileges for replacement (#711)
- 12d agoOpenHousev0.5.487
- 3mo agoCountConnect external MCP servers to the Count agent ⚡
- 3mo agoCountDashed lines
- 4mo agoCountNew workspace home
- 4mo agoCountClickHouse support
- 5mo agoCountMajor Count agent upgrade: edits any cell, runs in Slack ⚡
- 5mo agoCountPublic API and MCP server ⚡
Frequently asked questions
What is the difference between Count and OpenHouse?
They serve adjacent needs but don't currently overlap on shipped themes. Count and OpenHouse 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.
Is Count better than OpenHouse?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Count and OpenHouse 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 Analytics products to evaluate alongside.
What are the best alternatives to Count?
Top Count alternatives in Analytics are ranked by recent ship velocity. Browse the "Count alternatives" section above for the current picks, or visit /alternatives/count for the full list with editorial commentary on each.
What are the best alternatives to OpenHouse?
Top OpenHouse alternatives in Analytics are ranked by recent ship velocity. Browse the "OpenHouse alternatives" section above for the current picks, or visit /alternatives/openhouse for the full list with editorial commentary on each.