Run Prime Agent in Agentastic
Prime Intellect's open-source RLM agent, with persistent sessions, recursive subagents, a continual harness, and native ACP chat.
What Agentastic adds
Give every task its own worktree, branch, or container.
Keep Prime Agent's real CLI and your existing configuration.
Inspect the diff, run code review, test, and open a pull request.
Launch Prime Agent
- Install the official CLI and sign in with your existing provider account.
- Open a repository in Agentastic. The connection is discovered from your PATH.
- Open Agent Home, choose Prime Agent, describe the task, and select worktree, local, container, cloud, or remote mode.
Every run gets its own git worktree, so three tasks can share a repository without sharing a branch or a build directory.
What Prime Agent supports
- Launch from a task description: supported
Type the task in Agent Home and Agentastic hands it to prime-agent at launch, so the run starts from your prompt instead of an empty session.
- Unattended runs: not supported
Prime Agent confirms its actions as it goes, so plan on watching the run rather than scheduling it.
- Plan before editing: not supported
Agentastic keeps plan mode out of the picker for Prime Agent rather than emulating it, so runs begin with edits.
- Resume a session: supported
Reopen the last Prime Agent session for a worktree and keep its history — useful when reviewing the diff turns up one more change.
- Structured chat: supported
Talk to Prime Agent in a native chat that renders thinking, nested tool calls, plans, and permission requests as structured events instead of scraped terminal output.
- Code review: not supported
Prime Agent writes the change; pair it with a review-capable agent for the pass before merge.
Agentastic reads these from Prime Agent's own CLI rather than emulating them, and modes it does not support stay out of the picker. The provider reference lists the exact flags for each launch, and how to compare coding agents covers what changes when you switch harnesses.
Prime Agent questions
Is there a GUI for Prime Agent?
Yes. Agentastic runs the real Prime Agent CLI (prime-agent) in a native Mac workspace with a git worktree, terminal, diff view, and code review for each task, plus a structured chat view of the session.
How do I run multiple Prime Agent sessions in parallel?
Start each task from Agent Home in worktree mode. Agentastic gives every run its own git worktree and terminal, so several Prime Agent sessions can work in one repository without editing the same files.
How do I install Prime Agent?
Run curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh, then sign in the way Prime Agent's documentation describes. Agentastic finds the prime-agent command on your PATH when you open a repository.
Does Agentastic charge for Prime Agent?
No. Agentastic is free and does not proxy model calls. It launches Prime Agent with the credentials and plan you already use, so any usage is billed by your provider, not by Agentastic.