Stanford's DSPy hits 39k GitHub stars for programming-not-prompting LLMs
_jaydeepkarale · x · 2026-11-16
DSPy, Stanford NLP's open-source framework for programming—rather than prompting—language models, has reached 39.1k GitHub stars and 3.5k forks across 4,865 commits. DSPy (Declarative Self-improving Python) lets developers build modular AI systems with compositional Python code instead of brittle prompts, and ships algorithms that automatically optimize both prompts and weights—applicable to classifiers, RAG pipelines, and agent loops. MIT-licensed, docs at dspy.ai.
More from coding & agent
- Antigravity doubles context window for Gemini 4 models — MickeySteamboat · 2026-11-16
- Indie dev cuts $400-600/month by ditching Vercel, Ahrefs and Sanity — yihui_indie · 2026-11-16
- Swarms' AgentRearrange orchestrates multi-agent pipelines via a single flow string — KyeGomezB · 2026-11-16
- Mapping 11 weeks of coding agent sessions (8,000+ messages) as a river — dbreunig · 2026-11-16
- Microsoft open-sources TokenEconomizer, cutting coding agent costs 18–31% — aigclink · 2026-11-16
- Track cost per finished task, not token price: the agent metric that matters — arpit_bhayani · 2026-11-16