AI Skill Hub 推荐使用：Slime 是一款优质的AI工具。已获得 5.8k 颗 GitHub Star，AI 综合评分 7.5 分，在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案，这是一个值得深入了解的选择。
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
Slime 依赖 Python 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 Python 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 Slime 的版本更新，及时通知重要功能变化。
Slime 是一款基于 Python 开发的开源工具，专注于 LLM、RL、AI 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
Slime 是一款基于 Python 开发的开源工具，专注于 LLM、RL、AI 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：pip 安装（推荐）
pip install slime
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install slime
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/THUDM/slime
cd slime
pip install -e .
# 验证安装
python -c "import slime; print('安装成功')"
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
slime --help
# 基本用法
slime input_file -o output_file
# Python 代码中调用
import slime
# 示例
result = slime.process("input")
print(result)
# slime 配置文件示例（config.yml） app: name: "slime" debug: false log_level: "INFO" # 运行时指定配置文件 slime --config config.yml # 或通过环境变量配置 export SLIME_API_KEY="your-key" export SLIME_OUTPUT_DIR="./output"
slime
slime is an LLM post-training framework for RL scaling, providing two core capabilities:
- High-Performance Training: Supports efficient training in various modes by connecting Megatron with SGLang;
- Flexible Data Generation: Enables arbitrary training data generation workflows through custom data generation interfaces and server-based engines.
In the agentic era, slime treats multi-turn tool use, sandbox interaction, environment feedback, and verifier/test-based rewards as data generation workflows. These workflows plug into the same training / rollout / Data Buffer loop through custom generation, custom reward, and server-based rollout engines, rather than requiring a separate agent framework.
slime is the RL-framework behind GLM-5.1, GLM-5, GLM-4.7, GLM-4.6, GLM-4.5 and apart from models from Z.ai, we also supports the following models: - Qwen series (Qwen3.6, Qwen3.5, Qwen3Next, Qwen3MoE, Qwen3, Qwen2.5); - DeepSeek V3 series (DeepSeek V3, V3.1, DeepSeek R1); - Llama 3.
Architecture Overview
Module Descriptions:
- training (Megatron): Responsible for the main training process, reads data from the Data Buffer, and synchronizes parameters to the rollout module after training.
- rollout (SGLang + router): Generates new data (including rewards/verifier outputs) and stores it in the Data Buffer. Custom generate functions can wrap this with multi-turn loops, tool calls, environment/sandbox interaction, and verifier-based reward.
- data buffer: A bridge module that manages prompt initialization, custom data, and rollout generation methods (including agentic workflows that produce samples through the same interface).
Quick Start
For a comprehensive quick start guide covering environment setup, data preparation, training startup, and key code analysis, please refer to: - Quick Start Guide
We also provide examples for some use cases not covered in the quick start guide; please check examples.
Agentic RL examples
For agentic RL workloads, the following examples plug into the standard rollout / Data Buffer loop through customization interfaces — they are not separate frameworks:
examples/multi_agent: Multi-agent rollout via a custom--rollout-function-path.examples/search-r1: Search/RAG-style multi-turn generation via--custom-generate-function-path.examples/fully_async: Fully-async rollout, useful for long-tail agentic generation where some samples take much longer than others.
See the Customization Guide for which interface to use for a given agentic workflow.
Developer Guide
- Contributions are welcome\! If you have suggestions for new features, performance tuning, or feedback on user experience, feel free to submit an Issue or PR 😊
- Use pre-commit to ensure code style consistency for your commits:
```bash apt install pre-commit -y pre-commit install
📈RLVE: Scaling LM RL with Adaptive Verifiable Environments
RLVE introduces an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). With joint training across 400 verifiable environments, RLVE enables each environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses.
FAQ & Acknowledgements
- For frequently asked questions, please see the Q\&A
- Special thanks to the following projects & communities: SGLang, Megatron‑LM, mbridge, OpenRLHF, veRL, Pai-Megatron-Patch and others.
- To quote slime, please use:
@misc{slime_github,
author = {Zilin Zhu and Chengxing Xie and Xin Lv and slime Contributors},
title = {slime: An LLM post-training framework for RL Scaling},
year = {2025},
howpublished = {\url{https://github.com/THUDM/slime}},
note = {GitHub repository. Corresponding author: Xin Lv},
urldate = {2025-06-19}
}Slime是高质量的AI工具，具有广泛的应用前景
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
- +GitHub 5.8k Star，社区高度认可
- +Apache-2.0 协议，可免费商用
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
总体来看，Slime 是一款质量良好的AI工具，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。
| 原始名称 | slime |
| 原始描述 | 开源AI工具：slime is an LLM post-training framework for RL Scaling.。⭐5.8k · Python |
| Topics | LLMRLAI |
| GitHub | https://github.com/THUDM/slime |
| License | Apache-2.0 |
| 语言 | Python |
收录时间：2026-05-27 · 更新时间：2026-05-27 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。