ollama/ollama
Ollama is a versatile platform that enables easy deployment, customization, and management of large language models locally across multiple operating systems with support for various model formats and a REST API.
Awesome AI Agents › AI Agent Deployment
MeetKai/functionary
Functionary is an advanced chat language model designed to interpret and execute functions or plugins dynamically. It intelligently determines when to trigger functions, whether to run them in parallel or sequentially, and can understand and utilize their outputs effectively. The model uses function definitions formatted as JSON Schema Objects, similar to OpenAI GPT function calls, enabling seamless integration and execution of various tools. This capability allows Functionary to extend beyond simple text generation, providing actionable responses by leveraging external functions or plugins as needed. The project offers multiple deployment options, including servers powered by vLLM and SGLang, catering to different user preferences and hardware capabilities. It supports various model sizes, from small to medium, with the medium models requiring substantial GPU resources for optimal performance. The system also supports LoRA adapters, allowing for modular and dynamic model enhancements either at startup or during runtime, enhancing flexibility and customization. Functionary has a rich development history with frequent updates and improvements, including the introduction of models capable of generating reasoning steps before tool usage, code interpreter abilities, and extended context lengths up to 128k tokens. It ranks highly on the Berkeley Function-Calling Leaderboard, demonstrating its effectiveness in function calling tasks. The project provides comprehensive documentation and examples to facilitate user adoption and integration. It also supports deployment via Docker containers, making it easier to manage dependencies and run the system in various environments. Additionally, Functionary offers a Text-Generation-Inference (TGI) service for efficient model inference, compatible with OpenAI-style requests and raw HTTP calls. Overall, Functionary represents a sophisticated approach to enhancing language models with functional execution capabilities, enabling more interactive and practical AI applications by combining natural language understanding with tool usage and result interpretation.
https://github.com/MeetKai/functionary
Also in AI Agent Deployment
alibaba/nacos
Nacos is a dynamic service discovery, configuration, and service management platform designed to simplify building and managing cloud-native applications and microservices.
e2b-dev/E2B
E2B is an open-source secure cloud runtime infrastructure that enables safe execution of AI-generated code in isolated sandboxes for AI applications and agents.
GoogleCloudPlatform/agent-starter-pack
A collection of production-ready Generative AI Agent templates for Google Cloud that accelerates development by addressing deployment, evaluation, customization, and observability challenges.
zebbern/claude-code-guide
Claude Code Guide is a comprehensive and authoritative resource providing detailed instructions, tips, and references for using the Claude Code CLI tool to interact with the Claude AI model, including advanced features and MCP integration.
boxlite-ai/boxlite
Rust engine giving AI agents hardware-isolated persistent micro-VMs that run any OCI image, embeddable as a daemonless library in Python, Node, Go, Rust or C, or run as a CLI, REST server or cloud control plane.
jim-schwoebel/awesome_ai_agents
A comprehensive and community-driven repository offering over 1,500 curated resources, tools, and projects related to AI agents for various applications and development needs.
Forethought-Technologies/AutoChain
AutoChain is a lightweight and extensible framework that simplifies building and automatically evaluating custom generative agents powered by large language models using custom tools and simulated multi-turn conversations.