Prime Agent: A Self-Improving RLM Agent for Coding and Autonomous Tasks

Introduction

Prime Agent is an open-source coding and research agent built for general and long-running work. It is designed around two core abstractions:

• The Recursive Language Model (RLM) treats context as variables (prompt-as-a-variable) and tools like recursive subagents as function calls (programmatic tool/sub-agent calling) inside a persistent REPL.
• The Continual Harness stores supplemental prompts, memories, skill descriptions, and reusable subagent specifications as durable state that Prime Agent can refine through small, evidence-backed updates, local to the session by default.

Why Use and Key Benefits

Prime Agent combines a persistent Python control environment with durable harness state, so useful working context and reusable operating patterns can outlive a single chat window. Key benefits include:

• Everything is programmatic: A persistent Python REPL is the built-in model tool; file operations, shell commands, tool use, subagents, and context management happen through code.
• Subagents are built in: rlm.spawn(...) spawns real child agents for parallel or background work and returns their results programmatically.
• The harness can improve: /refine reviews the current trajectory and can apply small, evidence-backed updates to supplemental harness state. It never rewrites the immutable base system prompt, and recorded snapshots support rollback.
• Skills are executable: Skills are importable Python packages, and the built-in skill creator can turn recurring workflows into project or personal skills.
• Sessions run in the background: Daemon-backed agents keep running when the terminal disconnects and can be reattached later.
• Agents communicate directly: Running agents can exchange messages and orchestrate one another without routing everything through the user.
• Long tasks keep moving: Automatic compaction, persistent goals, heartbeats, schedules, autonomous mode, and retained subagents preserve progress across turns and terminal sessions.

Installation

Install the latest build with the one-command installer (every push to the rust branch publishes a fresh rolling beta; the stable channel ships on release):

For Linux/macOS:

curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh

On Windows, install from PowerShell:

irm https://app.primeintellect.ai/prime-agent/install.ps1 | iex

The sh one-liner also works under Git Bash on Windows. Both installers publish the same layout (the launcher under $HOME\.local\bin, the payload under $HOME\.local\share\prime-agent) and read the same release channel: darwin (arm64/x64), linux (arm64/x64), and windows (x86_64, win32-x64).

Examples

Start Prime Agent from the repository or directory you want it to work in:

cd /path/to/project
prime-agent

On first launch, run /login to choose a subscription or API-key provider. Prime Agent works in the current directory and can run commands and modify files there. Use a disposable clone, clean worktree, or another checkpoint you can inspect and restore.

WARNING
Prime Agent executes model-generated Python and project commands with your user permissions. Its worker and kernel processes improve lifecycle isolation and recovery; they are not a security sandbox. Review changes and use trusted repositories, instructions, and skills only. Run untrusted code or instructions in an external sandbox or restricted environment.

Useful commands:

prime-agent agents                   # Browse running, idle, and saved sessions
prime-agent attach <agent>           # Reattach to a running session
prime-agent --resume [path|id]       # Browse sessions or resume one directly
prime-agent status                   # Inspect background service state
prime-agent doctor [--fix]           # Inspect or repair background services
prime-agent update [--force]         # Update Prime Agent
prime-agent shutdown [--force]       # Stop every agent, worker, and background service

Links

• GitHub Repository: PrimeIntellect-ai/prime-agent
• Prime Intellect Website: primeintellect.ai
• Verifiers Repository: PrimeIntellect-ai/verifiers
• PRIME-RL Repository: PrimeIntellect-ai/prime-rl
• RLM Blog Post: The Recursive Language Model
• Prime Agent arXiv Paper: 2608.23552
• Continual Harness arXiv Paper: 2605.09998