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
dot-agent/nextpy
Nextpy is presented as a framework for creating self-modifying software, with a strong emphasis on capabilities for AI agents and LLMs. Key features include robust guardrails, allowing users to define strict boundaries for AI system behavior to prevent overstepping limits. It offers enhanced control over LLMs through structured outputs, which is described as more effective than traditional chaining or prompting methods, giving prompt engineers precise control over response structure and generation. The framework incorporates a powerful prompt engine designed to handle much of the processing at compile time, aiming to reduce redundant LLM processing and maintain session state to reuse KV caches for open-source models. This approach optimizes token usage by transforming output tokens into prompt token batches, making them cheaper and faster. Nextpy also focuses on better AI generations, claiming to be more effective than chaining or prompt engineering by aligning with LLMs' processing patterns, and is specifically optimized for code generation. It includes features for detecting and correcting syntax errors in LLM-generated code. Modularity is a core aspect, supporting multiplatform deployment and extensibility, allowing Python or plain English integrations. It emphasizes a developer-first approach, promoting transferable knowledge. The framework also supports containerized and scalable agents that can be exported as simple files and run in various environments, optionally using Agentbox for optimized resource management within a sandbox. The project claims significant performance improvements over Streamlit. While it integrates components from many open-source projects, its core value proposition is around operationalising and governing AI agents and LLMs rather than training.
https://github.com/dot-agent/nextpy
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.
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.