6 个仓库
Awesome GitHub RepositoriesLLM Plugin Orchestrators
Systems that route tasks to different large language models and wrap custom algorithms as reusable plugins for agent execution.
Distinct from Plugin Orchestration: Distinct from generic Plugin Orchestration: focuses on orchestrating LLM-specific plugins and model routing, not general application extensions.
Explore 6 awesome GitHub repositories matching development tools & productivity · LLM Plugin Orchestrators. Refine with filters or upvote what's useful.
Awesome LLM Plugin Orchestrators GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- codelion/openevolve
codelion/openevolve
6,608在 GitHub 上查看OpenEvolve 是一个进化算法框架，使用大语言模型来自主发现和优化编程算法。它作为一个算法发现引擎和代码搜索工具，进化候选程序群体以找到高效的实现和特定于硬件的加速。 该系统将代码和系统指令都视为可进化的实体，利用自动提示优化器迭代地改进模型性能。它通过基于生态位的群体管理来保持搜索稳定性以维持多样性，并采用闭环反馈机制，将运行时错误和日志注入回生成过程中以进行自主错误修复。 该框架还包括一个代理编排器，使用加权逻辑和回退策略聚合来自多个模型 API 的响应。为了支持科学计算，它通过管理所有随机组件的一致随机种子来实现确定性执行。 该项目提供了一个用于可视化进化进度和实时性能指标的交互式仪表板。
Implements a system to route tasks across multiple LLM APIs using weighted logic and fallback strategies.
Python - open-llm-vtuber/open-llm-vtuber
Open-LLM-VTuber/Open-LLM-VTuber
5,946在 GitHub 上查看Manages multiple AI characters in a group chat by coordinating their responses through a plugin system.
Pythonaiai-companionai-vtuber - wenda-llm/wenda
wenda-LLM/wenda
6,173在 GitHub 上查看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。
Utilizes JavaScript plugins to manage conversation flows, trigger external API calls, and automate task sequences.
JavaScriptchatglm-6bchatrwkvrwkv - microsoft/taskweaver
microsoft/TaskWeaver
6,115在 GitHub 上查看TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the
Routes tasks to different LLMs and wraps custom algorithms as reusable plugins for agent execution.
Pythonagentai-agentscode-interpreter - cs-lazy-tools/chatgpt-on-cs
cs-lazy-tools/ChatGPT-On-CS
4,115在 GitHub 上查看ChatGPT-On-CS 是一个智能客户服务自动化平台，利用大语言模型实现跨社交媒体和电子商务平台的交互自动化。它作为一个连接这些模型与外部服务的桥梁，为管理来自多个网络和在线商店的聊天提供统一界面。 该平台具有自定义知识库引擎，允许创建基于上传公司文档训练的私有领域 AI 代理。它还包含一个插件框架，使 AI 代理能够访问实时互联网数据和本地操作系统功能，以扩展其能力。 该系统处理多模态内容，包括文本、语音和图像数据，以满足多样化的沟通需求。它通过检索增强生成（RAG）获取领域特定答案、外部插件以及用于频繁交互的静态预设模板的组合来支持响应生成。
Wraps custom algorithms and external resource access as reusable plugins for agent execution.
TypeScriptaiautohotkeyautomation - justicerage/gepetto
JusticeRage/Gepetto
3,362在 GitHub 上查看Gepetto is an IDA Pro plugin that integrates large language models directly into the reverse engineering workflow. It functions as a multi-provider LLM client, allowing users to explain decompiled functions, rename variables, and add comments to pseudocode, all while supporting multiple language model backends and a localized interface. The plugin distinguishes itself through a plugin-based architecture that abstracts multiple LLM providers behind a unified interface, enabling hot-swapping between providers and models without restarting IDA Pro. It also features a command-line interface bridg
Wraps multiple LLM providers behind a unified interface, allowing hot-swapping without restarting the host application.
Pythongpt-5-apiida-proopenai
