Integrations
Connected agents
Delegate coding tasks to Cursor, Codex, Claude Code, or OpenCode — HiveBase supervises the run and returns results for review with receipts.
Most integrations give HiveBase context to read. Connected agents are different: for coding work, HiveBase can hand a task to an external agent, supervise the run, and bring the result back for review — so execution happens in the tool built for it, while company context, verification, and receipts stay in HiveBase.
This is not “set and forget autonomous shipping.” Proposed changes stay reviewable; merge and high-blast actions follow trust & safety.
Agents you can delegate to
Claude Code
Anthropic's coding agent — typically sandboxed runs with returned diffs.
Cursor
Streams work back as it progresses in the Cursor environment.
Codex
OpenAI's coding agent path for delegated implementation.
OpenCode
Open-source coding agent, sandboxed for supervised runs.
How delegation works
HiveBase creates a coding task
From a signal or your request, with repository and company Brain context attached — see Coding tasks.
The task is delegated
HiveBase hands the enriched task to the chosen agent (sandboxed or streamed, depending on the agent).
HiveBase supervises the run
Progress is tracked against the task so work is not a free-floating agent session.
You review the result
Proposed changes come back for review before merge. Verification verdicts separate “completed” from “delivered against evidence” — see Verification verdict.
Receipt when the world changes
Applied actions leave an action receipt where the mutation path supports it.
Linear is not a delegation target yet
Linear is source-first: cached issues can ground work after explicit promote/link, but direct Linear comments, assignments, delegation, and provider-session-to-agent bridging stay disabled until the certified journaled path is live. See Linear.
What you control
- Choose which agent runs a task — or let HiveBase recommend one.
- Agents work with repository + company context, not a blank prompt.
- Proposed changes are reviewed before they merge — nothing ships silently by default.
- Every run is tracked against its task and logged.
- Outbound / irreversible steps still hit approval boundaries.
MCP vs delegation
| Path | Use when |
|---|---|
MCP (mcp.hivebase.ai) | Your agent (Cursor/Claude/etc.) needs read/write tools into HiveBase |
| Connected agents | HiveBase owns the task and delegates implementation outward |
They complement each other. Many teams use MCP for continuous context in the IDE and connected agents for supervised, receipted coding tasks on the board.