隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
DSPy: The framework for programming—not prompting—language models
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
DSPy solves the problem of fragile and labor-intensive prompt engineering by introducing a declarative programming model where prompts are treated as trainable parameters. It automates the optimization of prompts and weights, making AI systems more robust and adaptable across tasks and models, unlike traditional approaches that require manual tweaking for each use case.
部署现实
当前可用的安装信号是：pip install dspy。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build a wide range of AI systems, from simple classifiers to sophisticated RAG pipelines and agent loops, with automatic optimization of prompts and weights. Real-world use cases include knowledge-intensive NLP tasks, multi-stage language model programs, and self-refining pipelines with computational constraints. The ceiling is high, as DSPy supports fine-tuning and prompt optimization together, enabling state-of-the-art performance on complex tasks with minimal manual intervention.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
stanfordnlp/dspy 被追踪为 Python 项目，主要属于 LLM Tool 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 37k Star，今日 +0，本周 +525，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 60 天，未关闭 Issue 为 653，约占总 Star 的 1.76%。这只是采用信号，不替代工程尽调。
采用检查：3.2k Fork 和 37k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「Python 技术栈团队评估生态原生工具」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 525。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
37k 星标
复用
3.2k 复刻
关注
37k 关注者
维护
moderate
许可证
MIT
未解决 Issue
653
DSPy is a framework for programming—rather than prompting—language models, enabling fast iteration on building modular AI systems and optimizing their prompts and weights. It supports simple classifiers, sophisticated RAG pipelines, and Agent loops.
核心特性
- Declarative self-improving Python framework for LM programming - Algorithms for optimizing prompts and weights - Supports building classifiers, RAG pipelines, and Agent loops
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
pip install dspy70
健康评分
一般
提交活跃度
Jan 9, 2023
创建于
Aug 14, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
stanfordnlp
GitHub 主页affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
avelino/awesome-go
A curated list of awesome Go frameworks, libraries and software
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
DSPy solves the problem of fragile and labor-intensive prompt engineering by introducing a declarative programming model where prompts are treated as trainable parameters. It automates the optimization of prompts and weights, making AI systems more robust and adaptable across tasks and models, unlike traditional approaches that require manual tweaking for each use case.
能力范围
Developers can build a wide range of AI systems, from simple classifiers to sophisticated RAG pipelines and agent loops, with automatic optimization of prompts and weights. Real-world use cases include knowledge-intensive NLP tasks, multi-stage language model programs, and self-refining pipelines with computational constraints. The ceiling is high, as DSPy supports fine-tuning and prompt optimization together, enabling state-of-the-art performance on complex tasks with minimal manual intervention.
结论
DSPy is ideal for developers and researchers who want to move beyond manual prompt engineering and build scalable, self-improving AI systems. It is not for those who prefer simple, quick prompt-based solutions without a learning curve. The key trade-off is the initial complexity of learning the framework versus the long-term benefits of automated optimization and modularity.