Projects sharing features with OpenAGI

Nanoclaw is an LLM agent orchestrator and multi-platform chat gateway designed to deploy and manage isolated AI agents. It provides a containerized runtime that executes agents within sandboxed Linux containers, ensuring filesystem and state isolation through dedicated workspaces and host bind-mounts. The project distinguishes itself through a unified routing pipeline that connects agents to diverse messaging platforms, including WhatsApp, Discord, Slack, Telegram, Signal, and iMessage. It integrates the Model Context Protocol to extend agent capabilities via managed external data and functio

This project is a comprehensive framework for building, evaluating, and connecting autonomous agent systems. It provides a library of standardized architectural patterns for implementing complex agent workflows, including multi-agent orchestration, iterative reasoning, and memory management. By offering a unified interface for model providers, the framework allows for consistent agent execution across different artificial intelligence services. The framework distinguishes itself through a focus on rigorous benchmarking and deterministic control. It includes a suite of tools for evaluating age

Gemma is a family of open-weights large language models based on a decoder-only transformer architecture. These models are designed for text generation and multi-modal conversations, capable of processing and generating responses based on both textual and visual input sequences. The project provides a fine-tunable AI model that supports weight adjustment and low-rank adaptation to specialize performance for particular tasks. It includes support for quantized weights to reduce memory usage and increase inference speed on limited hardware. The capability surface covers multi-modal AI integrati

Superagent is a framework for AI assistant orchestration and agent security. It provides the tools to build intelligent assistants that integrate external APIs and maintain conversation memory to automate complex tasks. The project focuses on AI agent security through adversarial testing, red teaming, and the detection of prompt injections and malicious tool calls. It includes automated vulnerability patching, which scans codebases and configurations for security flaws and generates pull requests with fixes. The platform supports retrieval augmented generation by connecting language models t

CrewAI is a multi-agent orchestration framework and autonomous agent workflow engine. It provides a system for coordinating autonomous AI agents with specific roles and goals to solve complex tasks through collaborative intelligence. The framework distinguishes itself through a collaborative AI agent system that enables multiple language model instances to share intelligence and execute multi-step objectives via role-playing. It incorporates human-in-the-loop mechanisms, allowing for manual review checkpoints to validate decisions and refine outcomes within autonomous execution paths. The pl

2025/05/23 See our preprint paper in ArXiv.

🧠 Societies of Mind & Economy of Minds

Visual-ChatGPT is a visual orchestration framework and multimodal AI pipeline designed to coordinate large language models with visual foundation models. It functions as an integration layer that enables the exchange of text and images between different AI models to automate image analysis and editing tasks without requiring additional model training. The system differentiates itself through model-chain orchestration and prompt-based task dispatching, allowing natural language instructions to trigger specific vision models or tools. It utilizes coordinate-based region mapping and iterative ma

Voyager is an autonomous embodied agent and lifelong learning framework that uses a large language model to explore virtual environments. It functions as a code-based action controller, translating natural language instructions into executable scripts to interact with its surroundings. The system features an automatic curriculum generator that creates sequences of exploration goals to discover new items and behaviors without human intervention. It maintains a skill library manager that stores learned behaviors as reusable code fragments, which can be composed to execute complex tasks. The fr

This project is a toolkit for interacting with large language models through a command line interface, an integration library, and a workflow orchestrator. It provides a framework for embedding language model logic directly into scripts and managing automated sequences of AI tasks. The system utilizes a plugin framework and a provider-agnostic interface to route requests across different model providers. This architecture allows for the addition of custom capabilities and the ability to switch providers without altering the core logic. The project covers several functional areas, including A

Now the official Code for MultiagentBench has been moved to MARBLE

Code for the paper "Evaluating Large Language Models Trained on Code"

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

ToolBench is an open platform for training, serving, and evaluating large language models that retrieve and call real-world APIs to complete user instructions. It provides an API-aware inference engine that selects relevant tools from a large corpus and generates sequences of tool calls to produce final answers, along with a custom API registration system that lets users add their own REST endpoints for the model to discover and invoke. The platform includes a complete instruction-tuning pipeline for training models on curated tool-use data, a multi-tool execution engine that coordinates sequ

XAgent is an autonomous agent system that decomposes complex goals into sequential subtasks for execution via a planner and actor model. It functions as a collaboration framework that integrates human-in-the-loop workflows, allowing users to provide real-time guidance and missing information during the automation process. The system features a containerized tool sandbox to isolate the execution of shells and browsers, ensuring system safety and consistency. It includes a state-based execution recorder that captures snapshots of agent runs to enable the exact reproduction of specific task sequ

This project is a computer control framework that uses multimodal vision models to simulate mouse and keyboard inputs for automating desktop tasks. It functions as an autonomous agent and vision-based orchestrator that interprets screen visuals to interact with user interfaces. The system employs vision language models and object detection to locate and click interface elements. It utilizes visual grounding to overlay numerical markers on UI components and uses optical character recognition to map on-screen text to precise pixel coordinates. The framework supports voice-controlled computing

Figure 1: Natural Swarm Intelligence Inspiration and SwarmBench Tasks.

Auto-GPT is an autonomous agent framework that uses large language models to decompose complex goals and execute multi-step tasks without human intervention. It functions as a workflow automation tool that chains language model tasks and manages memory to achieve specific objectives. The project features a visual agent designer that allows users to define behaviors and goals by connecting functional blocks through a graphical interface. It employs a vector database memory system to recall information across different sessions and a sliding-window buffer for immediate short-term context. The

Multi-agent simulation library in Python

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Chemcrow

Yeager.ai Agent is the first Langchain Agent creator designed to help you build, prototype, and deploy AI-powered agents with ease. With an emphasis on flexibility, interactivity, and seamless integration, Yeager.ai Agent is the perfect tool for developers, researchers, and AI enthusiasts alike.

This is a framework for building autonomous agents that use large language models to plan, execute, and refine their own tasks. It functions as an autonomous task orchestrator and agent framework, utilizing a function registry to manage the code-based tools and plugins the agents use to achieve complex goals. The system is distinguished by its ability to perform autonomous code generation, where the agent analyzes requirements to write new reusable functions on the fly. It employs a recursive loop-based planning model to continuously update its goal list and refine its performance based on ex

An Autonomous AI Agent that works

EasyEdit is a framework and toolkit designed for updating, inserting, or erasing specific factual information within large language models without requiring full retraining. It functions as a parameter modifier and knowledge editing system capable of performing targeted weight updates across diverse model architectures. The project distinguishes itself by supporting both text-based and multimodal model editing, allowing for knowledge updates across image and text modalities. It provides utilities for model steering to adjust personality and reasoning patterns in real time via activation inter

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

The implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4"