Prime Agent: A Self-Improving RLM Agent Prime Intellect released Prime Agent, an open-source coding and research agent designed for long-running tasks, featuring a persistent IPython environment, recursive subagents, and a self-improving harness that refines supplemental state without altering the base system prompt. The agent supports background sessions, direct inter-agent communication, and executable skills, and is installable on macOS and Linux via a curl command. Documentation /PrimeIntellect-ai/prime-agent/blob/main/packages/coding-agent/docs/index.md • Verifiers https://github.com/PrimeIntellect-ai/verifiers • PRIME-RL https://github.com/PrimeIntellect-ai/prime-rl • pi-mono https://github.com/badlogic/pi-mono Prime Agent is an open-source coding and research agent for general and long-running work. It is designed around two core abstractions: - The treats context as variables Recursive Language Model RLM https://www.primeintellect.ai/blog/rlm prompt-as-a-variable and tools like recursive subagents as function calls programmatic tool /sub-agent calling inside a persistent REPL. - The 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. Continual Harness https://arxiv.org/abs/2605.09998 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. Everything is programmatic: persistent IPython is the built-in model tool; file operations, shell commands, tool use, subagents, and context management happen through code. Subagents are built in: rlm ... 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. Install the latest stable release on macOS or Linux: curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh The installer downloads a versioned release, verifies its SHA-256 checksum, installs the prime-agent command, and can prepare the IPython runtime used by the agent. 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, skills, and extensions 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