mudler/LocalAI
LocalAI is an open-source AI engine that enables running various AI models (LLMs, vision, voice, image, video) on any hardware, including CPU-only systems, with a composable and extensible architec...
Awesome AI Agents › LLM Framework Tools
chr15m/runprompt
runprompt turns a prompt into a command line program. It reads a dotprompt file, a format defined by Google in which YAML front matter carries the model name, configuration and input and output schemas while the body holds the prompt template, and it executes that file against a model provider. The script has no installation ceremony: it can be downloaded and made executable on its own, run through uvx straight from the repository, or installed with pip or uv to be used as a library from other Python code. Data reaches the template through several channels, since a JSON argument or piped stdin is parsed into named variables, while the special STDIN, ARGS and INPUT variables always hold the raw input, so a prompt can be dropped into a shell pipeline next to ordinary Unix tools. A prompt can also be given inline with a flag instead of living in a file. Output can be constrained with a Picoschema declaration, in which fields are written as a name, a type and a description with a question mark marking optional fields, and the script then returns validated JSON that downstream commands can parse. Tool calling is supported by pointing the run at a Python file: every function with a docstring becomes a tool the model may call during execution, which lets a prompt read files, call APIs or act on the local system and makes the script usable as a small agent harness rather than only a text generator. Several providers are supported, including Anthropic, OpenAI, Gemini, OpenRouter and Ollama, selected by the model string, and responses can be cached. The intended use is to treat prompts as first-class artifacts that live in a repository under version control and run reproducibly from scripts, instead of being retyped into a chat interface.
https://github.com/chr15m/runprompt
Also in LLM Framework Tools
langfuse/langfuse
Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features.
567-labs/instructor
Instructor is a popular Python library that simplifies working with structured outputs from large language models by providing validation, retries, and streaming support across multiple LLM providers.
TEN-framework/ten-framework
TEN Framework is a real-time, distributed, cloud-edge collaborative multimodal AI agent framework supporting multiple programming languages for building high-performance AI applications.
google/adk-samples
A collection of sample agents built with the Agent Development Kit (ADK) to accelerate development of conversational and multi-agent workflows, designed for customization and integration with Google Cloud services.
truefoundry/cognita
Cognita is an open-source, modular, and production-ready RAG framework by TrueFoundry that simplifies building, customizing, and deploying scalable Retrieval Augmented Generation applications with a no-code UI and extensive integration features.
lemony-ai/cascadeflow
In-process Python and TypeScript library that cascades model calls inside the agent loop, routing each query or tool call between small and flagship models by quality, cost, latency and budget.
shroominic/codeinterpreter-api
An open-source API that implements the ChatGPT Code Interpreter for sandboxed Python code execution, enabling data analysis, visualization, and interactive AI-driven computational tasks with local execution and scalable production deployment.