BoundaryML/baml
BAML (Basically a Made-up Language) is an AI framework that facilitates reliable AI workflows and agents by transforming prompt engineering into schema engineering for structured output generation.
Awesome Infra for AI › Prompt Management
austin-starks/Promptimizer
Promptimizer is an open-source framework designed for the automated optimization of Large Language Model (LLM) prompts. It employs genetic algorithms to evolve and improve prompt effectiveness, allowing for multi-generational evolution, crossover, and mutation operations on prompts. The system facilitates the automated evaluation of prompt performance against specific datasets, enabling users to train and validate prompts to achieve desired behaviors. While the example in the repository focuses on AI-driven stock screening, the framework is general-purpose and can be applied to optimize prompts for various LLM applications. Key features include genetic algorithm-based prompt optimization, population management, automated prompt evaluation, and customizable parameters for controlling the optimization process. Users can define input questions, additional system prompts, and configure API keys for various LLM providers like Anthropic, OpenAI, or local models via Ollama. The project emphasizes the importance of generating 'ground truths' to guide the model's behavior and developing scoring heuristics, optionally using an LLM-based 'Prompt Evaluator,' to quantify output accuracy. It also provides tools for visualizing performance trends over generations, helping users understand how prompt effectiveness changes during the optimization process. The framework requires Node.js, Python, and MongoDB, and integrates with popular ML libraries such as matplotlib, seaborn, and pandas for data analysis and visualization.
https://github.com/austin-starks/Promptimizer
Also in Prompt Management
genkit-ai/genkit
Genkit is an open-source framework by Google for building and operating AI-powered applications across multiple languages, featuring unified APIs for various models, structured outputs, multi-modal...
pezzolabs/pezzo
Pezzo is an open-source, cloud-native LLMOps platform for streamlined prompt design, version management, instant delivery, collaboration, troubleshooting, and observability of AI operations.
dot-agent/nextpy
Nextpy is a framework for building self-modifying software, focusing on guardrails, structured outputs, a powerful prompt engine for pre-compiling and session state, and optimized code generation f...
neuron-core/neuron-ai
Neuron is a PHP framework for building and orchestrating AI agents, supporting LLM integration, prompt management, RAG, multi-agent workflows, and observability.
microsoft/aici
AICI (Artificial Intelligence Controller Interface) allows building Wasm-based controllers to constrain and direct LLM output in real time, enabling advanced generation strategies.
patterns-ai-core/langchainrb
Langchain.rb provides a Ruby interface for building LLM-powered applications, offering a unified API for various LLM providers, prompt management, and RAG capabilities.
Open-Source-Legal/OpenContracts
OpenContracts is an open-source document intelligence platform that processes unstructured documents into a programmable citation graph using AI agents, structured extraction, and a Model Context P...