dspy

Tag

Cards List
#dspy

@0xtotem: Ported PEEK to @DSPyOSS You can wrap any DSPy agent (ReAct, RLM, ...) into this new module to benefit from the better p…

X AI KOLs Following ↗ · 2026-05-25 Cached

Ported the PEEK method to DSPy, allowing any DSPy agent to benefit from improved performance and cost reduction as demonstrated in the linked paper.

0 favorites 0 likes
#dspy

@dosco: PEEK coming to ax-agent https://github.com/ax-llm/ax

X AI KOLs Timeline ↗ · 2026-05-24 Cached

PEEK feature is coming to ax-agent, a TypeScript library for automatic prompt generation and AI agents, supporting multiple providers.

0 favorites 0 likes
#dspy

@ManningBooks: Prompt engineering gets messy fast. What starts as a simple instruction can turn into endless tweaking, context adjustm…

X AI KOLs Following ↗ · 2026-05-21 Cached

Manning Books announces a new early access book 'Building LLM Applications with DSPy', teaching how to use the DSPy framework to optimize LLM prompts with Python. The book is 50% off through June 3rd.

0 favorites 0 likes
#dspy

@DanKornas: Your text corpus shouldn’t stay trapped in paragraphs. kg-gen is a Python package for extracting knowledge graphs from …

X AI KOLs Timeline ↗ · 2026-05-21 Cached

kg-gen is an open-source Python package that uses language models (via LiteLLM and DSPy) to extract knowledge graphs from plain text or conversation messages, featuring chunking, clustering, and flexible provider routing.

0 favorites 0 likes
#dspy

@MaximeRivest: https://x.com/MaximeRivest/status/2055293570119065875

X AI KOLs Following ↗ · 2026-05-15 Cached

MaximeRivest explains DSPy's five core components—Optimizers, Signatures, LMs, Modules, and Adapters—and argues that effective AI engineering requires mastering these elements, highlighting the often-overlooked role of rendering structured outputs.

0 favorites 0 likes
#dspy

@wsl8297: Discovered a recursive multi-agent framework on GitHub: ROMA (Recursive Open Meta-Agent). It solves complex problems through a hierarchical recursive structure, decomposes tasks into parallelizable components, and enables agents to handle more intricate reasoning tasks. GitH…

X AI KOLs Timeline ↗ · 2026-05-13 Cached

ROMA is a recursive multi-agent framework built on DSPy, designed to solve complex reasoning tasks through a hierarchical recursive structure. It supports task decomposition, parallel processing, and multiple LLM providers.

0 favorites 0 likes
#dspy

@MaximeRivest: Compound AI System for Images are way under appreciated. We need gepa, dspy, autoresearch style optimization to go from…

X AI KOLs Following ↗ · 2026-05-11

Maxime Rivest argues that compound AI systems for images are undervalued and suggests leveraging optimization frameworks like DSPy and GEPA to automate pipeline creation involving SAM and classifiers.

0 favorites 0 likes
#dspy

@intertwineai: Part 2 of the @DSPyOSS Skills series is up→ how to get DSPy + GEPA + RLM up and running in minutes in Claude and Codex …

X AI KOLs Timeline ↗ · 2026-04-21

Tutorial shows how to quickly set up DSPy with GEPA and RLM using Claude and Codex, providing copy-paste ready code.

0 favorites 0 likes
#dspy

@isaacbmiller1: DSPy 3.2.0 is out! Here are a few highlights: - dspy.RLM improvements around parsing, tool execution, and failure recov…

X AI KOLs Following ↗ · 2026-04-21 Cached

DSPy 3.2.0 improves dspy.RLM parsing, tool execution, and failure recovery, plus ongoing work to decouple from LiteLLM.

0 favorites 0 likes
#dspy

@dosco: very cool writeup on applying RLM and DSPy to multi-modal data. this bit really got me thinking...

X AI KOLs Following ↗ · 2026-04-20 Cached

A social media post highlighting a writeup on applying RLM and DSPy to multi-modal data.

0 favorites 0 likes
#dspy

@DSPyOSS: indeed it's all just signatures (specs), modules ("harnesses", "inference scaling"), and optimizers (learning algorithm…

X AI KOLs Following ↗ · 2026-04-20 Cached

A post reflecting on the DSPy framework's architecture built around signatures, modules, and optimizers, and noting its continued growth since 2022.

0 favorites 0 likes
#dspy

@lateinteraction: Building good AI software requires a crisp mental model of problems vs solutions. If you assume that AI will do the pro…

X AI KOLs Following ↗ · 2025-04-24 Cached

The article emphasizes the need for a clear mental model in AI software development to properly specify problems and avoid overengineering, contrasting with assumptions about AI handling problem definition.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback