October 2026

Global search for pages and indexed content

29 October release

Global search (⌘K / Ctrl+K) still jumps to portal destinations. It also lists catalog entities and documentation that match your query, in one list. You type what you remember and open what your role allows.

The same rules apply to team-scoped entities as on the catalog and search pages. If you'd like tabs and filters, use the Search page.

See Search and navigation for more details.

Reach the owning team on Slack

29 October release

Catalog entities show an owning team. Optional Team Slack channel links on each team record give you a direct channel URL.

Open a component or other entity and read the owner when you need someone for an incident, a roadmap question, or access. In Users and Teams, the Slack column opens the channel when a link is set. Team leads add or change the link at creation or on the team overview.

See Users and Teams to learn more.

Restrict catalog visibility to the owning team

29 October release

Some imports are not ready for everyone in the organization. On import or edit, set Audience to Organization (default) or Team. Users outside the owning team cannot find or open a Team-scoped entity. Search and other catalog views follow the same rule.

See Catalog Visibility to learn more.

Set several import tags before entities land in the catalog

29 October release

On the configure step of import, add multiple tags per repository, copy tags to selected rows, and review the full set before you confirm. You avoid a second editing pass after import.

See Importing Repos for more details.

Scan Skill Guard scores on the skills list

29 October release

The Skills list shows the latest completed Skill Guard score when one exists, the current scan status when a scan is running, and a notification if Skill Guard is not configured.

You can pick which skills to open first.

See Skills to learn more.

Other catalog and UI changes

29 October release

Tech Landscape

20 October release

Tech Landscape in Venue.sh aggregates technology signals from your ingested repositories. You see a sorted list of technologies filter by one or more of them and browse repository cards that show what each repo uses.

• Open the page - Click Tech Landscape in the left-side navigation or open /tech-landscape. You can also use global search and type phrases such as tech stack, technologies, languages, or frameworks.
• Permissions - You need the same catalog read access as for the rest of the software catalog. If you cannot browse the catalog, Tech Landscape is not available to you.
• Technology list - Technologies that differ only by letter case or spacing count as one entry. The label uses the most common spelling in your data.
• Repository cards - Each card links to the catalog entity when one exists. When there is no entity the card still shows the repository name or remote identifier.
• Filters - Selected technologies appear as chips so you can see what you filtered on and clear filters quickly.

On the Tech Landscape page, the Assistant includes page context and starter prompts. You can ask which repositories use specific stacks, like:

• "Which repositories use TypeScript and React?"
• "What are the most common technologies in our organization?"

See Tech Landscape and Assistant for full details.

Shared Assistant conversations

20 October release

You can share a conversation from the full Assistant page with up to 50 people in your organization. Sharing is useful when a teammate needs the same context you already explored with the Assistant.

• Share - Open a conversation on the Assistant page and click Share. Select teammates and confirm. Later, you can remove access from the same dialog.
• Shared with me - Recipients open Conversations then the Shared with me tab. Each entry shows who shared it.
• Read-only copy - Opening a shared conversation shows a frozen snapshot. New messages you send in your own chat do not change what the recipient sees.
• Start from shared context - Recipients can click Start new conversation with this context, which allowss Venue.sh to copy the messages into a new conversation they own so follow-up questions can use that history.
• Your history - Conversations you shared show secondary text, such as, "Shared with N" in your history list.

Demo accounts cannot share or fork shared conversations.

See Sharing conversations in the Assistant docs.

Organization details for API clients

20 October release

GET /api/organization now returns the organization id, name, and slug for the signed-in caller. The route accepts a session cookie, a personal API key, or an OAuth bearer token.

OAuth-based clients can use it to show your organization name instead of only an internal identifier.

Fixes

20 October release

Repository import - Importing a repository whose display name contains a space (for example "Venue View") no longer fails during catalog registration. The entity keeps the display title and opens from the catalog as expected. See Importing repositories.

Skill Guard

08 October release

Skill Guard checks each skill for problems such as prompt injection attempts, unsafe commands and exposed credentials. Venue.sh scans a skill automatically the first time it discovers the skill. You do not need to start a scan yourself.

• Model selection - A Venue administrator picks the model that Skill Guard uses under Settings → AI Settings. The list shows only models that Skill Guard supports.
• Skill Guard tab - Each skill page now has an Overview tab, a Skill content tab, and a Skill Guard tab. The Skill Guard tab shows the risk score, the recommendation, the number of findings for each severity, and a list of findings you can filter by severity.
• Finding locations - A finding shows its file, line, and rule ID. A finding that applies to the whole skill shows Bundle-level.
• Coverage notices - If a scan could not inspect part of a skill, the tab explains why. For example, a companion file was not stored, or a file was too large to scan.
• Failure messages - If a scan fails, the tab explains the reason and links to the Support Portal. If the AI provider rejects the request, choose a different model in AI Settings.
• Reingesting - Reingesting a repository now scans skills that have never been scanned or whose last scan failed, even when the repository content has not changed.
• Model support - Skill Guard now works with Claude Opus 5.5 and Claude Sonnet 5.5. It also reuses a finished scan instead of repeating it.

See Skill Guard for what a scan checks and how to read the result.

Assistant questions

08 October release

The Assistant in Venue.sh can now stop in the middle of a response and ask you a question in the chat. Select one or more choices, add context if you want, and then submit your answer to allow the Assistant to continue.

See Assistant for more about using the Assistant.

Skill install command

08 October release

The install row on a skill's Overview tab now has an Agent selector that helps you pick the right coding agent.

Pick your coding agent, and Venue.sh adds the matching --agent option to the command when you copy it. Select Any agent to copy the command without the option.

Your browser remembers your choice for other skills.

Template lineage

08 October release

The About card on an entity page now shows Created from template if a template was used to create the entity. The text links to the template used, as well.

See Templates to browse and launch software templates.

Portal improvements

08 October release

Fixes

08 October release