21 dependents
| Package | Description | Downloads/month |
|---|---|---|
| DSPy: The framework for programming—not prompting—language models | 7.1M | |
| Our library for RL environments + evals | 2.3M | |
| Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic wor... | 60K | |
| Dreadnode Strikes SDK | 59K | |
| DAO AI: A modular, multi-agent orchestration framework for complex AI workflows.... | 12K | |
| Mantisdk - AI Agent Training and Evaluation Platform | 4K | |
| Adaptive Agentic AI Reasoning using Microsoft Agent Framework -- Join the Discor... | 3K | |
| DSPy with litellm replaced by litelm and numpy made optional | 2K | |
| An agent framework for production engineering | 2K | |
| Solution to facilitate the writing and execution of E2E tests understandable by ... | 1K | |
| Run GEPA on your favorite non-python libraries. | 365 | |
| A library for prompt optimization. | 252 | |
| Compositional framework for building and orchestrating Compound AI Systems and N... | 250 | |
| Agentic Code Optimization & Deep Evaluation for Superior Coding Agent Experience... | 217 | |
| Chatixia: a domain-agnostic skill-based AI agent framework | 205 | |
| Comprehensive logging and visualization infrastructure for DSPy GEPA optimizatio... | 159 | |
| Structured automated feedback for code-generating agents — so they can work long... | 143 | |
| GEPA-powered prompt optimization for vowel eval spec generation | 101 | |
| Super Code Mode: MCP/Cloudflare adapters and GEPA optimization harness | 77 | |
| DSPy: The framework for programming—not prompting—language models | 71 | |
| A short description of the project. | 70 |
