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...
Awesome Infra for AI › Prompt Management
BoundaryML/baml
BAML is an AI framework designed to streamline the development of reliable AI workflows and agents. It introduces a domain-specific language that treats LLM prompts as functions, mapping input parameters to a defined output type. This approach, termed 'schema engineering,' enables developers to focus on the structure and types of model outputs, leading to more consistent and predictable results from large language models. BAML supports generating type-safe functions in various languages including Python, TypeScript, Ruby, Go, and others, allowing seamless integration into existing applications. Key features include full typesafety, streaming support, built-in retries, and wide model compatibility across major LLM providers (OpenAI, Anthropic, Gemini, Vertex, Bedrock, and any OpenAI-compatible endpoint). The framework's "Schema-Aligned Parsing" (SAP) algorithm ensures reliable structured outputs even from models without native tool-calling APIs, supporting complex output formats like markdown within JSON or chain-of-thought. BAML also offers robust developer tooling, including VS Code and JetBrains IDE extensions, providing playgrounds for rapid prompt testing and visualization of API requests, significantly accelerating the iteration speed for prompt development. It supports advanced client strategies such as retry policies, fallbacks, and model rotations, all statically defined, with options for runtime model selection via a Client Registry. Additionally, BAML aids in building streaming UIs with type-safe interfaces and utilities for frameworks like Next.js, and is fully open-source (Apache 2) and designed for offline operation.
https://github.com/BoundaryML/baml
Also in Prompt Management
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...
microsoft/prompty
Prompty is a markdown-based file format (.prompty) and runtime for creating, managing, and executing LLM prompts, providing tools for development, previewing, and tracing.