概要
Prime Agent は、再帰言語モデル(RLM)と持続化フレームワークに基づいて構築されたオープンソースのプログラミングおよび研究エージェントです。永続的な IPython 環境を使用し、コードによるファイル操作、Shell コマンド、サブエージェントの実行を行います。バックグラウンドデーモン、エージェント間通信、自律モードをサポートしており、長時間実行されるタスクに適しています。
README プレビュー
\n \n \n \n \n \n \n \n\n\n\nPrime Agent: A Self-Improving RLM Agent\n\n\n\n Documentation •\n Verifiers •\n PRIME-RL •\n pi-mono\n\n\n\n \n \n \n \n \n \n\n\nPrime Agent is an open-source coding and research agent for general and long-running work. It is designed around two core abstractions:\n\n- The **[Recursive Language Model (RLM)](https://www.primeintellect.ai/blog/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.\n- The **[Continual Harness](https://arxiv.org/abs/2605.09998)** 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.\n\nPrime 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.\n\n- **Everything is programmatic:** persistent IPython is the built-in model tool; file operations, shell commands, tool use, subagents, and context management happen through code.\n- **Subagents are built in:** `rlm(...)` spawns real child agents for parallel or background work and returns their results programmatically.\n- **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.\n- **Skills are executable:** skills are importable Python packages, and the built-in skill creator can turn recurring workflows into project or personal skills.\n- **Sessions run in the background:** daemon-backed agents keep running when the terminal disconnects and can be reattached later.\n- **Agents communicate directly:** running agents can exchange messag