Stay Updated with DSPyWeekly!
DSPyWeekly Issue No #18
Published on January 16, 2026
📚 Articles
dsprrr: Programming not prompting—LLMs in R
dsprrr brings the power of DSPy to R. Instead of wrestling with prompt strings, declare what you want, compose modules into pipelines, and let optimization find the best prompts automatically.
Productionalize a GEPA optimized Model on Databricks | by AI on Databricks | Jan, 2026 | Medium
After optimizing your first model using GEPA on Databricks (previous blog), you now have a smaller model that can perform on par or better than a larger frontier model! The logical next step is to utilize and scale the optimized model to process your data. The big question then becomes “How do I productionalize my optimized model?”
PAPER: Blue Teaming Function (Calling Agents)
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three different attacks, and we measure the effectiveness of eight different defences. These experimental evaluation on four representative LLMs using Ollama3 and DSPy.
Keep Your Data Fresh with CocoIndex and LanceDB
The main goal of this post is to demonstrate how to build an indexing flow in CocoIndex to persist a multimodal dataset (text + images) in LanceDB. A flow is incremental, meaning that the incoming data is processed in real time, and the CocoIndex engine continually monitors the source and flow logic for updates. We then run a second-stage flow update in CocoIndex, where we update the target data by enriching it with new features extracted by an LLM, using DSPy.
gepa-rpc - Tyrin
GEPA prompt optimization for Vercel's AI SDK. dead simple, DSPy-inspired API, and still feels native to AI SDK.
Paper Breakdown - Build on DSPy
Tweet by the founder
🎥 Video
Breno Brito - Future proof your AI product - YouTube
In this talk I will cover frequent AI system problems caused by using prompts and opaque frameworks instead of a descriptive programmatic approach, using DSPy.
Conversation with Maxime on state of attachments - DSPy Interview Series - YouTube
In this episode, we sit down with Maxime, the creator of the essential Attachment Library and a prolific contributor to the DSPy community. We dive deep into why the current developer stack is failing AI engineers and how Maxime is rebuilding his environment from scratch—from a new Markdown-first IDE to functional wrappers for DSPy.
DSPy: How to Program LLMs Properly
DSPy is changing how we build LLM applications. Instead of writing fragile prompts, DSPy lets you program large language ... | Channel: Yuva D
dspy-cli - DSPy programs as HTTP APIs in seconds - Drew Breunig
Drew ran strategy, data science, and major client projects at PlaceIQ (acquired by Precisely) – a pioneer in mobile location ... | Channel: Information Shelf
🚀 Projects
vericle/intellyweave
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy. | Language: Python | License: BSD 3-Clause "New" or "Revised" License
yotambraun/flowprompt
Type-safe prompt management with automatic optimization for LLMs. DSPy-style optimization, A/B testing, multimodal support, and more. | Language: Python | License: MIT License
NathanZaldivar/regspy
regspy is a regex pattern generator using ai | Language: AutoHotkey
Fadeleke57/nanocode
nanocode in dspy! | Language: Python
ivanvza/dspy-skills
A DSPy integration for the Agent Skills specification, enabling ReAct agents to dynamically discover and use modular, sandboxed skills | Language: Python
MorningStarTM/Synthetic-Data-Generator
This Project for Creating unified tool to generate synthetic data (text and sensorial data) using LLM with the help of DSPy | Language: Python | License: MIT License
zch-danny/medical-agentic-rag
???? Agentic RAG ?? - LlamaIndex + DSPy | Language: Python
Thanks for reading DSPyWeekly!