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
newdee/prompt-shelf
Prompt Shelf is a prompt management system that moves prompts out of application source code and into a versioned store with an API in front of it. The problem it targets is familiar in applications built on language models: prompts embedded in code make the code harder to read, every wording change requires a code change and a redeployment, there is no systematic history to compare or roll back, and non-engineers cannot contribute without touching the repository. Prompt Shelf answers this with commit-style version control designed for prompts, so each change is recorded, versions can be compared, and a previous version can be restored. Applications fetch the current prompt through a REST interface at runtime, which means a wording change reaches production without a build. Because retrieval sits on the request path, a Redis-compatible cache is used to keep lookups fast. Access is controlled through token authentication with role-based permissions, so who may edit a prompt and who may only read it is enforced by the service rather than by repository conventions. A web interface provides browsing, editing and history views for people who do not work in the codebase. The backend is written in Rust and stores prompts in a relational database, and the whole system is deployed with a docker compose file that brings up the API, the cache and the database together, with configuration supplied through environment variables. Documentation covers the endpoint set for authentication and prompt operations. The project fits small teams that want prompt iteration and A/B variations decoupled from their deployment cycle without adopting a large platform.
https://github.com/newdee/prompt-shelf
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...