Integrations.
Starlings connects to the agents and tools your team already uses. Claude works inside your workspace as you, shared agents sit in your team list, and connectors file your history on the right client.
Your agents work inside the workspace.
An agent reads the same calls, tasks and documents as your team, and files its work where the team will look for it. Starlings logs each action under the name of the person who asked.
MCP
Your Claude reads and writes company data through Starlings, as you. Starlings logs every call.
- Reads
- Subjects, people, conversations, documents, events, tasks, issues, finished transcripts
- Writes
- A message, a task and its updates, an issue, an event, a room, a goal, a decision, a question for you to decide, a document, website content. Each one says a Claude did it
- Scope
- Writes are a scope you grant on connect, off by default. Settings lists each connected Claude, with Revoke
- Record
- Starlings logs every call. Admin and your own account page show the log. The log keeps no content, and keeps entries 90 days
- Protocol
- Model Context Protocol, over one signed endpoint
- Works in
- claude.ai, Claude Desktop, Claude Code
- Claude is a connector
- Your own assistant connects as you. A shared agent in Team has its own identity and answers through a signed runtime connection
Agents
Team lists agents next to people. Message one, answer a question with choices, or hand it a task.
- In Team
- Listed with people. Message one the way you message anyone
- Interactive questions
- An agent can ask with single or multiple choices. Submit your answer in chat to continue the same thread
- In Work
- Hand it a task. It reports back on the task
- On your behalf
- It acts as the person who asked
- What it can do
- Open an agent’s profile to see its runtime-reported skills, tools, connections, schedules and the documents it follows
- In a room
- From a command line, an agent hosts, admits guests, and reads the transcript
- Runs on Eve
- Envisioning’s shared agents run on Vercel Eve with their own skills, connections and keys. Signed handoffs and replies connect the runtime to Starlings
- One session per card
- Each task or issue has one agent session. Every turn resumes it. The thread and the card are the record
Bring the agents you already use.
Claude works with Starlings today, and Envisioning’s shared agents run on Vercel Eve. We’re building common integration points so agents from other providers can join too. The table shows which work today and which we still need to test.
Researched on 3 October 2026 from the linked official sources. These products are examples of an open ecosystem, not a complete catalogue or a limit on which agents should work with Starlings. They supply different parts of an agent’s capabilities. This is a capability comparison, not a reliability benchmark. Eve and Claude work with Starlings today; the other rows are integration opportunities, not supported connections or delivery commitments.
| Product and role | Capabilities | Relationship to Starlings |
|---|---|---|
| Vercel EveCustom agent runtime | Durable sessions, sandboxed code, typed tools, Markdown skills, connections, schedules, subagents and traces. Browser work can be added through tools. | Working todayRuns Envisioning’s agents outside Starlings. Signed handoffs carry the assignment; replies return to the conversation. |
| ClaudeAssistant and connector client | Chat, Code and Cowork; connectors, skills, files, scheduled tasks and browser or computer use. Capabilities depend on the client and plan. | Working todayClaude connects to Starlings over MCP as you. Read company records, prepare work and make writes you have allowed. |
| Grok BotPersonal and team agents | Persistent cloud computer, browser and terminal; connectors, reusable skills, routines, memory and coordination between bots. | Integration to validateA candidate MCP client for a member’s assistant. A bot participating in Team would need a separate signed adapter. |
| OpenClawAgent runtime you operate | Messaging channels, shell, files, browser, search, skills and plugins; background automation and coordination across agents. | Integration to validateA candidate runtime for a Team agent, with an adapter for Starlings identity, handoffs and replies. |
| HermesAgent runtime with procedural learning | Terminal, files, browser automation, MCP, memory, session recall, agent-created skills, scheduled work and delegation. | Integration to validateA candidate MCP client or Team-agent runtime. Pairing and signed message delivery need separate validation. |
| OpenAI DotsAlways-on personal assistant | Cloud computer and browser, connected apps, ongoing tasks and memory; background agents and delegation to Work or Codex tasks. | Integration to validateA candidate personal connector for reading context and returning work as the member who asked. |
| Meta MusePersonal and small-business assistant | Computer, browser, terminal, files and connectors; proactive work, parallel tasks and documents, PDFs, websites and interactive outputs. | Integration to validateA candidate custom connector. We still need to test how it signs in to Starlings and how its returned work gets reviewed. |
| InstinctPersonal assistant by text and calls | Phone and computer operation, connected applications and devices, personal context and proactive follow-up. Public developer details are limited. | Integration to researchAn integration to research. A public Starlings-compatible connector or developer contract has not been established. |
| ManusAgent for delegated tasks | Cloud sandbox and browser work, files, research and generated deliverables; connectors including MCP, plus an API for external workflows. | Integration to validateA candidate connector or task adapter for assignments and completion notifications. |
| Gemini EnterpriseEnterprise agent platform | Enterprise knowledge, research and multi-step workflows; custom ADK and A2A agents, with centralized management. | Integration to validateA candidate enterprise integration. Mapping company access and the agent’s acting identity comes first. |
| Microsoft Copilot StudioEnterprise agent builder | Knowledge-grounded conversations, workflows, connectors, REST and MCP tools; agent handoffs and file work depending on the harness. | Integration to validateA candidate MCP or workflow integration for teams using Microsoft 365. |
Coming later: agents working together. One agent researches a client brief and hands its sources to another agent, from a different provider, to write the draft. The result comes back to the project for a person to review. Each handoff names who is accountable and what the agent can access.
Works with the tools you keep.
Map each source to a project once. Starlings files only what you map.
Connectors
One connector per tool. Map a channel, a repository, or a folder to a project. Starlings files its past and new items on that project.
- You map
- Each connector lists what the tool holds. You pick the subject for each row, or skip it. A suggestion only prefills the choice
- One ledger
- Every import records what it filed and where. You can reverse a wrong mapping for that one row
- Off by default
- A connector runs only when an admin turns it on. When off, it reads nothing
- Google stays
- Gmail, Calendar, and Drive remain the record. Starlings reads and links, and never writes back
Google Workspace
Your team signs in with Google, and Starlings reads your calendar.
- Sign-in
- Google accounts from your company only, proven by Google itself
- Calendar
- Company meetings and your own calendars in one view. Your booking page offers only the times you are free
- Calls
- Start a call from a calendar event, and Starlings files its transcript on the event’s project
- Read only
- Gmail, Calendar and Drive remain the record. Starlings reads and links, and never writes back
An open standard for agents.
The instructions and skills an agent follows in Starlings are published under the Apache 2.0 licence, so any agent can learn how to file its work on the right client.
Agent instructions
What an agent reads before it works in a Starlings workspace.
Skills
Portable skills in the Agent Skills format, ready for any agent’s skills folder.
Request early access
Tell us which agents and tools your team uses today.