Search Packages

textgrad

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

trace-opt

End-to-end Generative Optimization for AI Agents

tok-protocol

tok is an invisible bridge

promptcraft

PromptCraft is a prompt perturbation toolkit from the character, word, and sentence levels for prompt robustness analysis. PyPI Package: pypi.org/project/promptcraft

toonprompt

Universal prompt optimization CLI + Python SDK for Codex, Claude, Cursor, Gemini, Aider, and Continue with Toon-style structured compression.

llm-prompt-refiner

🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, and prompts into your token budget.

promptfoundry

Open-source, local-first, Production grade intelligent prompt management system. (not affiliated with any company)

marketing-agent-example

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

dspy-code

Claude Code for DSPy: AI-powered interactive development environment for DSPy

autoresearch-prompt-manager

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

scope-optimizer

SCOPE: Self-evolving Context Optimization via Prompt Evolution - A framework for automatic prompt optimization

autoresearcher-shonku

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

prompt-groomer

🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, and prompts into your token budget.

flowprompt-ai

Type-safe prompt management with automatic optimization for LLMs

shonku

Autonomous prompt management with versioning, A/B experiments, metrics, and LLM-driven optimization. Built on agno.

siare

Self-Improving Agentic RAG Engine - Evolve multi-agent RAG pipelines using Quality-Diversity optimization

promptimal

Optimize your prompts in the terminal

iflow-mcp-developzir-gepa-mcp

MCP server integrating GEPA (Genetic-Evolutionary Prompt Architecture) for automatic prompt optimization