Skip to content

Agents

Cocurdex coordinates multiple agent sessions in one workspace. Runtimes and providers evolve during pre-release; this page describes the product model and the agents available today.

  • Each session has a clear status and derived attention state (see Desktop).
  • You can run more than one session without merging them into a single transcript.
  • Permissions, questions, and plan approvals surface in the UI instead of happening silently.
  • Prefer the narrowest permission and write mode that still lets the task complete.
Id (--agent) UI label Runtime Notes
claude-agent Claude Agent External claude CLI Plan mode, steering, native write
codex Codex External codex CLI Plan mode, steering, native write; auth via Codex itself
opencode OpenCode External opencode CLI Streaming; steering not supported
grok-build Grok Build External grok CLI (ACP transport) Strong multi-step implementer; permission modes over ACP
pi Cocurdex Built-in Branded as Cocurdex in the product UI; read-oriented default

External agents must be installed and authenticated on your machine. If a CLI is missing, the agent shows as unavailable until you install it.

Situation Start with
You already use Claude Code / Claude CLI claude-agent
You already use OpenAI Codex codex
You want Grok-oriented implementation grok-build
You use OpenCode elsewhere opencode
Lightweight chat-style turn without native workspace write pi (Cocurdex)

Agents use provider configs (API base URL, credentials, catalog) and models registered in the app. Configure providers in the desktop UI; list them from the CLI:

Terminal window
cocurdex provider list
cocurdex provider models <provider-id>

Cocurdex reuses your existing provider setup where possible (for example Codex account state under ~/.codex). Do not paste secrets into product notes or the public docs site.

Permission modes are agent-specific. Risk levels:

Risk Intent
normal Ask or carefully gate tool use
elevated Broader auto-approve for edits / review
dangerous Full or bypass-style access — use deliberately
Mode id Risk
claude-default normal
claude-accept-edits elevated
claude-bypass-permissions dangerous
Mode id Risk
codex-default normal
codex-auto-review elevated
codex-full-access dangerous
Mode id Risk
grok-ask normal
grok-auto elevated (Grok’s risk classifier; may cost extra model calls)
grok-always-approve dangerous
Mode id Risk
opencode-ask normal
opencode-allow elevated
opencode-deny normal

No separate permission-mode list in the fallback catalog; write mode defaults to read-only.

When an agent requests a privileged action, Cocurdex surfaces a permission card (and may show path/action detail). Resolve from the session UI or from session tui in the CLI.

Control Values Meaning
Collaboration default, plan Plan mode when the runtime supports a plan-first loop
Write mode read-only, native-write Whether tools may change the workspace

Not every agent supports every combination. For example, Grok Build focuses on native write; built-in pi is read-oriented.

Some runtimes can change model, thinking / reasoning effort, permission, or related axes without recreating the provider session. That preserves conversation continuity and provider-side cache. If a control is missing for an agent, it is intentionally unsupported — there is no silent “restart the session under the hood” fallback.

When an agent supports steering, you can send follow-up guidance while a run is active (or queue follow-ups until the current turn finishes — configurable in chat settings). When steering is unavailable, wait for the turn to finish or stop the session.

Stop a running session from the UI or:

Terminal window
cocurdex session stop <session-id>

Typical pattern:

  1. One session implementing a feature
  2. One session investigating a bug or reviewing a branch
  3. Optional plan-mode session for design

Keep titles short and status visible. Switch only when attention demands it — do not merge unrelated work into one transcript to “save a session slot.”