spb/tools-spboucher-ai
Public
1{2 "slug": "dspy",3 "name": "DSPy",4 "aliases": ["dspy-ai", "Declarative Self-improving Python"],5 "vendor": { "name": "Stanford NLP and the DSPy community", "slug": "stanford-nlp", "website": "https://dspy.ai" },6 "homepage_url": "https://dspy.ai/",7 "docs_url": "https://dspy.ai/current/",8 "repo_url": "https://github.com/stanfordnlp/dspy",9 "license_url": "https://github.com/stanfordnlp/dspy/blob/main/LICENSE",10 "product_type": "framework",11 "product_status": "active",12 "summary": "Python framework for programming language-model pipelines with typed signatures and modules, then optimizing prompts and weights automatically against a metric",13 "description": "DSPy is an MIT-licensed Python framework that started at Stanford NLP in 2022 and treats LLM pipelines as programs to compile rather than prompts to hand-tune. A signature declares a task's typed inputs and outputs; modules such as `Predict`, `ChainOfThought` and `ReAct` decide how the signature is executed, including tool use; and optimizers (MIPROv2, GEPA and others) rewrite instructions, select few-shot demonstrations or fine-tune weights to maximize a user-defined metric on example data. Models are addressed through provider-prefixed names, so the same program can target hosted APIs or local runtimes.\n\nThe approach suits research groups and teams that need measurable, reproducible pipelines: classification, extraction, retrieval-augmented QA or multi-stage reasoning where a labeled development set exists. Its limits are that optimization consumes many model calls, that results depend on the quality of the metric and data, and that the compiled prompts are less transparent than hand-written ones. The project is at version 3.x and remains actively developed with a lineage of published papers.",14 "capabilities": ["Typed signatures for task specification", "Modules: Predict, ChainOfThought, ReAct and custom compositions", "Optimizers such as MIPROv2 and GEPA for prompts and weights", "Metric-driven evaluation and compilation", "Provider-agnostic model addressing"],15 "workflows": ["Compile a classification pipeline against a labeled dev set", "Optimize a RAG program's instructions and demonstrations", "Compare optimizers on the same metric"],16 "advantages": ["Systematic alternative to manual prompt engineering", "Research-backed optimizers", "MIT license and active community"],17 "limitations": ["Optimization is model-call intensive", "Requires labeled examples and a good metric", "Compiled prompts are harder to audit"],18 "prerequisites": ["Python 3.10+", "A model provider or local runtime"],19 "audiences": ["NLP researchers", "Engineers building measurable LLM pipelines"],20 "alternatives": ["langchain", "pydantic-ai", "promptfoo", "instructor"],21 "categories": [{ "slug": "llm-ops", "primary": true }, { "slug": "agent-frameworks", "label": "Modules and ReAct agents" }],22 "tags": ["llm", "python", "open-source", "prompt-optimization", "rag"],23 "use_cases": ["evaluate-llm-apps", "build-agents"],24 "operating_systems": ["macos", "linux", "windows"],25 "execution_modes": ["local", "self-hosted"],26 "interfaces": ["library"],27 "deployment_models": ["embedded"],28 "integrations": ["OpenAI", "Anthropic", "Ollama", "LiteLLM", "MLflow"],29 "data_formats": ["JSON"],30 "languages": ["Python"],31 "source_model": "open-source",32 "license_spdx": "MIT",33 "pricing_model": ["open-source", "free"],34 "self_hostable": true,35 "sources": [36 { "url": "https://dspy.ai/current/", "type": "official_site", "title": "DSPy", "supports": ["name", "summary", "capabilities", "license_spdx"], "checked_at": "2026-11-02" },37 { "url": "https://github.com/stanfordnlp/dspy", "type": "repository", "supports": ["license_spdx", "languages"], "checked_at": "2026-11-02" },38 { "url": "https://github.com/stanfordnlp/dspy/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" }39 ],40 "confidence": "high",41 "discovery_method": "editorial-research",42 "depth": "standard",43 "editorial_status": "reviewed",44 "visibility": "public",45 "featured": false,46 "author": "batch-A"47}48