[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-94435":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":16,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":18,"hasPages":18,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":20,"readmeContent":21,"aiSummary":22,"trendingCount":16,"starSnapshotCount":16,"syncStatus":23,"lastSyncTime":24,"discoverSource":25},94435,"prime-agent","PrimeIntellect-ai\u002Fprime-agent","PrimeIntellect-ai","A self-improving RLM agent for coding workflows and long-running autonomous tasks.",null,"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fprime-agent","TypeScript",5995,477,21,87,0,61.04,false,"main","2026-08-24 04:01:22","\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fprimeintellect.ai\">\n    \u003Cpicture>\n      \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F40c36e38-c5bd-4c5a-9cb3-f7b902cd155d\">\n      \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F6414bc9b-126b-41ca-9307-9e982430cde8\">\n      \u003Cimg alt=\"Prime Intellect\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F6414bc9b-126b-41ca-9307-9e982430cde8\" width=\"312\" style=\"max-width: 100%;\">\n    \u003C\u002Fpicture>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">\nPrime Agent: A Self-Improving RLM Agent\n\u003C\u002Fh3>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"packages\u002Fcoding-agent\u002Fdocs\u002Findex.md\">Documentation\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fverifiers\">Verifiers\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fprime-rl\">PRIME-RL\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbadlogic\u002Fpi-mono\">pi-mono\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fprime-agent\u002Factions\u002Fworkflows\u002Fci.yml\">\n    \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fprime-agent\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fprime-agent\u002Factions\u002Fworkflows\u002Fbuild-binaries.yml\">\n    \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FPrimeIntellect-ai\u002Fprime-agent\u002Factions\u002Fworkflows\u002Fbuild-binaries.yml\u002Fbadge.svg\" alt=\"Build Binaries\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\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:\u002F\u002Fwww.primeintellect.ai\u002Fblog\u002Frlm)** treats context as variables (*prompt-as-a-variable*) and tools like recursive subagents as function calls (*programmatic tool \u002Fsub-agent calling*) inside a persistent REPL.\n- The **[Continual Harness](https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.09998)** 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:** `\u002Frefine` 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 messages and orchestrate one another without routing everything through the user.\n- **Long tasks keep moving:** automatic compaction, persistent goals, heartbeats, schedules, autonomous mode, and retained subagents preserve progress across turns and terminal sessions.\n\n## Getting Started\n\nInstall the latest stable release on macOS or Linux:\n\n```bash\ncurl -fsSL https:\u002F\u002Fapp.primeintellect.ai\u002Fprime-agent\u002Finstall.sh | sh\n```\n\nThe 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.\n\nStart Prime Agent from the repository or directory you want it to work in:\n\n```bash\ncd \u002Fpath\u002Fto\u002Fproject\nprime-agent\n```\n\nOn first launch, run `\u002Flogin` 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.\n\n> [!WARNING]\n> 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.\n\nUseful commands:\n\n```bash\nprime-agent agents                   # Browse running, idle, and saved sessions\nprime-agent attach \u003Cagent>           # Reattach to a running session\nprime-agent --resume \u003Cpath|id>       # Resume a saved session\nprime-agent status                   # Inspect background service state\nprime-agent doctor [--fix]           # Inspect or repair background services\nprime-agent update [--force]         # Update Prime Agent\nprime-agent shutdown [--force]       # Stop every agent, worker, and background service\n```\n\n## Built for Long-Running Work\nPrime Agent is built for long-running work, especially for evaluations in research. These features are available in the TUI, and when run autonomously. \n\n- **Continual Harness:** `\u002Frefine` can persist focused, reviewable lessons as supplemental prompts, memories, reusable skill descriptions, or subagent specifications, with recorded refinement history. It does not replace packaging and reviewing new executable skills.\n- **Direct agent-to-agent communication:** running agents and retained subagents can discover one another, exchange messages, and steer active work.\n- **Daemon-backed continuity:** active sessions, IPython state, schedules, and subagents keep running when the terminal detaches and can be reattached later.\n- **Heartbeats and schedules:** `\u002Fheartbeat`, `rlm_heartbeat`, and `prime-agent schedule` can re-enter a session periodically or at a specific time.\n- **Persistent goals:** `\u002Fgoal` keeps an objective and its progress active across turns until it is completed, paused, or cleared.\n- **Bounded autonomous mode:** `\u002Fautonomous` continues within configured turn, token, and time budgets and can run user-defined quality gates. A passed gate checks only what that gate verifies; reaching a limit does not imply task success.\n\n## Documentation\n\n- [Quickstart](packages\u002Fcoding-agent\u002Fdocs\u002Fquickstart.md) — install, authenticate, and run a first session\n- [Usage and CLI reference](packages\u002Fcoding-agent\u002Fdocs\u002Fusage.md) — commands, sessions, autonomous limits, and output modes\n- [Long-running and background agents](packages\u002Fcoding-agent\u002Fdocs\u002Flong-running-agents.md) — detach and reattach, goals, heartbeats, and schedules\n- [RLM programming model](packages\u002Fcoding-agent\u002Fdocs\u002Frlm.md) — persistent IPython, subagents, skills, and the trust model\n- [JSON mode](packages\u002Fcoding-agent\u002Fdocs\u002Fjson.md) and [RPC mode](packages\u002Fcoding-agent\u002Fdocs\u002Frpc.md) — headless automation and integrations\n- [Skills](packages\u002Fcoding-agent\u002Fdocs\u002Fskills.md) — install and create reusable capabilities\n- [Provider setup](packages\u002Fcoding-agent\u002Fdocs\u002Fproviders.md) — subscription and API-key providers\n- [Architecture overview](packages\u002Fcoding-agent\u002Fdocs\u002Farchitecture.md) — daemon, worker, kernel, and persistence boundaries\n- [Development](packages\u002Fcoding-agent\u002Fdocs\u002Fdevelopment.md) — build and run from source\n\n## Acknowledgements\n\nOur agent and TUI is built on top of [`pi`](https:\u002F\u002Fgithub.com\u002Fearendil-works\u002Fpi). We thank the authors of `pi` for their valuable work.\n\n## License\n\nPrime Agent is fully open source and released under the [MIT License](LICENSE).\n","Prime Agent 是一个面向编程工作流与长期自主任务的自优化递归语言模型（RLM）智能体。它基于持久化 IPython 控制环境，通过“提示即变量”和“子智能体即函数调用”的抽象，支持程序化工具调用、并行子智能体调度、可验证的上下文精炼（\u002Frefine）以及可复用技能包管理；其 Continual Harness 机制将记忆、技能描述与子智能体规范作为可增量更新的持久状态存储。适用于代码生成与调试、自动化研究实验、长时间运行的工程任务编排等需上下文连续性与渐进式能力演化的场景。",2,"2026-08-08 02:30:12","trending"]