Awesome GitHub RepositoriesUnified Model Interfaces

Pi is an autonomous coding agent and framework for building AI agents capable of executing independent loops. It functions as an agent state management system that tracks and persists tool calls throughout complex workflows, utilizing a command-line interface for interaction and control. The system features a self-extensible design, allowing agents to write and implement new capabilities and tools into their own runtime environment. It also includes a provider-agnostic abstraction layer that standardizes interactions across different large language model providers through a unified API. The

Hutool is a comprehensive suite of Java extensions designed to serve as a standard library extension. Its primary purpose is to reduce development boilerplate for common programming tasks and data manipulation through a collection of utility classes. The project provides specialized toolkits for database management using active record patterns and connection pooling, as well as network communication via a simplified HTTP client and asynchronous socket management. It includes security and identity capabilities such as symmetric and asymmetric encryption, image captcha generation, and JWT token

Llama-stack 是一个标准化的编排栈和生成式 AI API 网关。它提供了一个统一的通信层和一致的接口，用于部署、管理和与各种大语言模型提供商及部署进行交互。 该系统充当代理（agent）框架，管理工具执行和版本化的技能包，以自动化复杂任务。它包括一个批处理系统，用于通过离线处理处理大量异步请求，以及一个用于存储和搜索文档以实现检索增强生成（RAG）的向量数据库接口。 该栈涵盖了高级功能，包括 AI 代理编排、模型部署以及模型 API 的标准化，从而允许在不重写应用程序代码的情况下切换提供商。

Agent Squad is a multi-agent system orchestrator and language model agent orchestration framework. It serves as an AI workflow automation engine and tool integration layer designed to coordinate teams of specialized agents to solve complex tasks through routing, parallel execution, and state management. The project is distinguished by its ability to dynamically compose purpose-specific agents on-demand and route requests based on intent, language, or domain expertise. It supports advanced coordination patterns, including parallel subtask distribution, sequential task pipelines, and the abilit

Manifest is a language model provider unification system that standardizes access to multiple AI backends through a single interface. It functions as a centralized management layer for integrating various cloud-based and local model providers to simplify how applications request completions. The system provides intelligent model routing and high availability infrastructure by directing queries based on complexity and automatically triggering model fallbacks when a primary provider fails. It distinguishes itself through multi-tenant AI management, organizing agents into isolated groups with de

Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines, corrective actions, and structured output generation. It provides a unified API layer that connects to over 100 language models, applying consistent validation, streaming, and error-handling across providers. The framework validates and corrects model responses against safety and quality rules, detecting and mitigating risks in both inputs and outputs using pre-built and custom validators. The project distinguishes itself through a validator-pipeline architecture that sequentially appl

SpringBlade is a development framework and platform designed for building multi-tenant SaaS applications. It provides a comprehensive scaffold for both Spring Cloud microservices and monolithic Spring Boot architectures, enabling the rapid construction of enterprise-grade software. The platform distinguishes itself through integrated LLM orchestration and industrial IoT management. It features an LLM orchestration platform that combines large language models with knowledge bases and visual AI agent workflows, alongside an IoT hub for device connectivity, state synchronization, and edge flow o

Swarms 是一个多代理编排框架和自主代理工具包，旨在协调大语言模型代理。它作为一个用于管理代理关系的工作流引擎，提供了构建具有集成内存、工具调用能力和推理循环的自主代理的基础设施。 该框架的特色在于其多代理共识系统，利用投票、对抗性辩论和裁判代理来合成高质量的响应。它支持多种协作模式，包括导演-工作者层次结构、专家合成以及基于自然语言描述的自动化群体架构生成。 该系统涵盖了广泛的运营功能，包括通过领域特定语言进行基于图和顺序的工作流编排、针对不同模型提供商的统一接口，以及与 Model Context Protocol 的集成以实现动态工具发现。它还包括对检索增强生成、状态持久内存以及将代理功能公开为 Web 服务的能力的支持。 该项目提供用于代理管理的命令行界面，并支持通过 YAML 和模块化 markdown 技能文件进行配置。

This project is a multimodal AI proxy and content generation hub that provides a unified web interface for interacting with multiple large language models and generative AI services. It functions as a secure API access gateway, routing requests from a single dashboard to various external AI backends using configurable base URLs and API keys. The platform is delivered as a cross-platform progressive web application, allowing for installation on Linux, Windows, and MacOS. It distinguishes itself by consolidating text, image, audio, and video generative controls into a standardized interface, su

Wenda 是一个 LLM 编排平台和自定义工作流引擎，旨在通过统一界面管理多个语言模型后端。它充当自托管 AI 网关，能够执行复杂的任务序列和自动化对话流。 该系统利用 JavaScript 插件来编排工作流并触发外部 API 调用。它通过将来自向量存储和离线文件的相关数据注入提示词来支持检索增强生成，从而提高响应准确性。 该平台专为私有网络部署而构建，具有多用户访问管理功能，并能够运行量化的开源模型以适应特定的硬件约束。它还包括基于会话的历史跟踪，以保持对话上下文。

Genkit is an LLM application framework and generative AI developer toolkit designed for building production AI applications. It serves as an AI workflow orchestrator that coordinates model calls and agentic tool usage through type-safe execution flows. The project provides a unified model interface and plugin architecture to standardize access to diverse large language models, vector stores, and telemetry backends. It distinguishes itself with a dedicated observability suite for tracing execution steps and a developer toolkit for prompting, debugging, and evaluating AI logic via a local inter

Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

TaskingAI 是一个 AI 代理编排器和应用平台，用于构建、部署和扩展 AI 原生应用。它作为一个多租户后端即服务（BaaS），提供了在共享架构上托管和管理跨多个用户或组织的独立 AI 代理实例的基础设施。 该平台具有可视化工作流构建器和项目管理控制台，允许用户在进入生产环境前，通过图形界面配置代理逻辑并测试对话工作流。 该系统通过统一接口标准化跨云和本地提供商的交互，从而编排大语言模型。它通过将外部数据源和搜索插件集成到模型工作流中，支持检索增强生成（RAG）。其他功能包括用于追踪对话历史的状态化会话管理，以及用于扩展代理工具的插件式架构。

AIOS is an LLM agent operating system and orchestration kernel designed to manage memory, resource scheduling, and tool execution for multiple autonomous AI agents. It serves as a comprehensive framework for developing and deploying agents, featuring a dedicated resource manager that coordinates model backends, GPU memory, and isolated kernel instances. The system distinguishes itself through a semantic memory engine that uses vector search and autonomous clustering for long-term knowledge management, and a semantic file system that allows users to control computer files and system operations

Plano is an AI agent orchestrator and LLM gateway proxy that unifies access to multiple AI providers through a single interoperable interface. It functions as a model routing engine that decouples applications from specific vendors using semantic aliases, allowing traffic to be shifted between providers without modifying application code. The system distinguishes itself with intent-based agent routing, which directs prompts to specialized agents based on semantic analysis. It features an interceptor-based filter chain system that acts as guardrail middleware to enforce safety policies, rewrit

Promptify 是一套专为模型评估、提示词管理、Token 成本跟踪、结构化提取和统一 API 网关访问而设计的工具。它提供了一个标准化接口，用于管理跨多个大型语言模型提供商的请求和响应。 该项目具有一个提示词管理平台，用于工程化和版本化带有结构化输出验证的提示词。它包括一个专门的评估框架，用于根据标记数据集测量模型性能（使用精确率、召回率和 F1 分数），以及一个 Token 成本跟踪器来监控模型请求的财务支出。 该库涵盖了自然语言处理的广泛功能，包括命名实体提取、文本分类和问答。它通过异步批处理支持高容量工作流，并通过模式验证将非结构化文本转换为类型化数据结构，从而确保数据一致性。

Aigcpanel is a visual workflow automation tool and model lifecycle manager designed for generative AI media pipelines. It provides a unified interface to install, launch, and configure both local and remote AI model endpoints, acting as an orchestration platform for large language models and AI tools. The system features a drag-and-drop node editor for chaining AI models and scripts into automated processing pipelines. It distinguishes itself with a breakpoint-aware execution model that allows users to pause and resume long media tasks from specific points in the workflow. Additionally, it in

LazyLLM is a multi-agent framework and orchestration engine designed for building complex AI applications. It provides a system for chaining large language models into sequential or parallel pipelines, utilizing a tool registry to convert standard functions into discoverable tools that models can invoke via reasoning. The project features an application deployment kit that enables hosting model workflows as web services with integrated chat interfaces and API gateways. It includes an infrastructure abstraction layer that allows users to switch between bare-metal servers, clusters, and public

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project

该项目是一个用于构建、评估和连接自主代理系统的综合框架。它提供了一个标准化架构模式库，用于实现复杂的代理工作流，包括多代理编排、迭代推理和内存管理。通过为模型提供者提供统一接口，该框架允许跨不同人工智能服务进行一致的代理执行。 该框架通过专注于严格的基准测试和确定性控制脱颖而出。它包括一套用于根据标准化任务和质量指标评估代理性能的工具，从而能够比较不同的设计模式。为了确保可靠性，该系统结合了确定性路由门和自校正循环，在外部执行前验证代理操作并根据质量标准优化输出。 该架构支持广泛的功能，包括用于现实世界任务完成的工具集成、用于上下文感知响应的检索增强生成，以及用于跨会话维护信息的模块化内存管理。这些组件通过标准化的执行契约链接，确保无论底层模型或特定架构配置如何，行为都保持一致。 该存储库结构化为一系列演示这些模式和基准测试方法的 Jupyter Notebooks。