Integrations

Connected agents

Delegate coding tasks to Cursor, Codex, Claude Code, or OpenCode — HiveBase supervises the run and returns results for review with receipts.

Last updated 2026-07-27

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.

Rendering diagram…
HiveBase delegates a coding task to your chosen agent, supervises the run, and returns the result for review.

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

1

HiveBase creates a coding task

From a signal or your request, with repository and company Brain context attached — see Coding tasks.

2

The task is delegated

HiveBase hands the enriched task to the chosen agent (sandboxed or streamed, depending on the agent).

3

HiveBase supervises the run

Progress is tracked against the task so work is not a free-floating agent session.

4

You review the result

Proposed changes come back for review before merge. Verification verdicts separate “completed” from “delivered against evidence” — see Verification verdict.

5

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

PathUse when
MCP (mcp.hivebase.ai)Your agent (Cursor/Claude/etc.) needs read/write tools into HiveBase
Connected agentsHiveBase 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.