Hmbown/rlmagents

ملف Hmbown

آخر نشاط مصدر مسجل: ١٨ فبراير ٢٠٢٦ في ١٥:٠٨

آخر تحديث لفهرس SkillsMP: ٢٦ أكتوبر ٢٠٢٦ في ١١:٣٧

skills مجمعة: ٧

نجوم GitHub: ٤٩
تفرعات GitHub: ٤

ملف README للمستودع

مصدر ملف README للمستودع: README.md

قراءة الملف الأصلي

عرض ملف README كاملًا

# RLMAgents [![PyPI - Version](https://img.shields.io/pypi/v/rlmagents)](https://pypi.org/project/rlmagents/) [![CI](https://github.com/Hmbown/rlmagents/actions/workflows/ci.yml/badge.svg)](https://github.com/Hmbown/rlmagents/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/) `rlmagents` is an agent harness built on LangChain + LangGraph. It uses an RLM-style loop inspired by [Recursive Language Models](https://arxiv.org/abs/2512.24601) (Zhang, Kraska, Khattab, 2025), then adds practical agent tooling. Forked from [LangChain Deep Agents](https://github.com/langchain-ai/deepagents). Paper reference implementation: [alexzhang13/rlm](https://github.com/alexzhang13/rlm). ## Install ```bash pip install rlmagents ``` ## Usage ### CLI ```bash rlmagents # interactive session rlmagents -n "Explain this repo" # one-shot rlmagents -r # resume last conversation ``` ### Python ```python from rlmagents import create_rlm_agent agent = create_rlm_agent() result = agent.invoke({ "messages": [{"role": "user", "content": "Summarize the key ideas in this paper."}] }) ``` ```python # With a separate model for recursive sub-calls agent = create_rlm_agent( model="deepseek/deepseek-chat", sub_query_model="deepseek/deepseek-reasoner", sub_query_timeout=300.0, rlm_tool_profile="full", # full | reasoning | core ) ``` ## What Is an RLM? An RLM (Recursive Language Model) is a way to work on big tasks without stuffing everything into one huge prompt. In this project, that means: - Data can live in REPL/session state instead of only in chat context - The agent works in a loop by writing and running code (`exec_python`) - It can call recursive sub-queries with `sub_query` (`llm_query` alias) - It finishes with `finalize` (or optionally `Final` / `set_final(...)`) ## What It's Helpful For - Large codebase analysis where you need to inspect many files - Long documents that are too big for a single prompt - Multi-step tasks that mix search, code execution, and synthesis - Workflows that need citations/evidence tracking for final answers - Repeatable analysis pipelines via recipe tools ## What RLMAgents Adds - Evidence tracking and citations across tool calls - Multi-context isolation (separate REPL sessions with `context_id`) - Recipe tools (`validate_recipe`, `run_recipe`) - Agent harness tools: planning, filesystem, shell, sub-agents, skills, memory - `@file` loading plus auto-loading large tool results into contexts ## Monorepo Layout | Path | Package | Description | |------|---------|-------------| | `libs/rlmagents` | `rlmagents` | Python API + bundled CLI/TUI | | `libs/cli` | `rlmagents-cli` | Standalone CLI package (monorepo development) | | `libs/acp` | `deepagents-acp` | Agent Context Protocol integration | | `libs/harbor` | `deepagents-harbor` | Evaluation and benchmark tooling | | `libs/deepagents` | `deepagents` | Upstream-compatible SDK package | ## Development ```bash # check all lockfiles in the monorepo make lock-check # package-level checks cd libs/rlmagents uv sync --group test uv run pytest tests -q uv run ruff check rlmagents tests ``` Run from source: ```bash uv run --project libs/rlmagents rlmagents ``` ## Links - PyPI: https://pypi.org/project/rlmagents/ - GitHub: https://github.com/Hmbown/rlmagents - Upstream: https://github.com/langchain-ai/deepagents - Paper: https://arxiv.org/abs/2512.24601 - Paper code: https://github.com/alexzhang13/rlm

جارٍ تحميل ملف README للمستودع…

Skills في هذا المستودع

مطوّرو البرمجيات المهن الحاسوبية الأخرى محللو أبحاث السوق ومتخصصو التسويق معلمو التعليم العالي، جميع الآخرون

٤ فئات مهنية · 100% مصنفة

skill

المهنة

الوصف

آخر تحديث

arxiv-search

معلمو التعليم العالي، جميع الآخرون

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

لغة النص الأصلي: الإنجليزية

2026-02-18

skill-creator

المهن الحاسوبية الأخرى

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5)…

لغة النص الأصلي: الإنجليزية

2026-02-18

skill-creator

المهن الحاسوبية الأخرى

لغة النص الأصلي: الإنجليزية

2026-02-17

langgraph-docs

مطوّرو البرمجيات

Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.

لغة النص الأصلي: الإنجليزية

2026-01-30

web-research

محللو أبحاث السوق ومتخصصو التسويق

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

لغة النص الأصلي: الإنجليزية

2026-01-30

query-writing

مطوّرو البرمجيات

For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations

لغة النص الأصلي: الإنجليزية

2026-01-15

schema-exploration

مطوّرو البرمجيات

For discovering and understanding database structure, tables, columns, and relationships

لغة النص الأصلي: الإنجليزية

2026-01-15

عرض ٧ من أصل ٧ skills مجمعة.

التثبيت بمساعدة مساعد ذكي

انسخ هذا الطلب إلى المساعد الذكي الذي تستخدمه.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/Hmbown/rlmagents.