Discover AI agents built for Research: Comprehensive directory of solutions with open-source code verified by AI agency professionals focused on the Research sector.

Open-Source AI Agents for Research | AI Agent Store

Dcup is an open-source, self-hostable Retrieval-Augmented Generation (RAG) platform designed to help developers and teams build scalable, AI-powered retrieval pipelines. It enables seamless integration with data sources like Google Drive, Dropbox, and AWS, and supports advanced search capabilities including LLM re-ranking, summary indexing, and hybrid search using OpenAI embeddings and Qdrant vector storage. With its intuitive Retrieval API and modular architecture, Dcup simplifies the process of ingesting, indexing, and retrieving data, making it ideal for AI applications requiring efficient and accurate information retrieval.

Dcup

dcup

An open-source RAG-as-a-Service platform for building scalable, AI-powered retrieval pipelines.

Codex CLI is an open-source, terminal-native AI coding assistant developed by OpenAI. Designed for developers who prefer working directly in the terminal, it integrates OpenAI's latest models (like o4-mini) to perform tasks such as reading, modifying, and executing code within a local environment. Codex CLI supports multimodal inputs, allowing users to pass text, screenshots, or diagrams to generate or edit code accordingly. It offers three distinct approval modes—Suggest, Auto Edit, and Full Auto—providing flexibility in how autonomous the agent operates. The tool emphasizes security by running in a sandboxed, network-disabled environment and ensures that your source code remains on your machine unless explicitly shared. With zero-setup installation and compatibility with macOS, Linux, and experimental support for Windows via WSL, Codex CLI aims to streamline the development workflow by bringing powerful AI capabilities directly to the command line.

Codex CLI

codex-cli

Open-source terminal-based AI coding assistant that reads, writes, and executes code locally with multimodal input support.

Cerebrum is the Software Development Kit (SDK) for AIOS, the AI Agent Operating System. It provides developers with tools to build, deploy, and manage large language model (LLM)-based AI agents. Cerebrum addresses challenges such as scheduling, context switching, memory management, and tool integration, facilitating the creation of efficient and scalable AI agents. The SDK features a modular architecture encompassing LLM, memory, storage, and tool management layers, and includes an Agent Hub for sharing and discovering agents with version control and dependency management.

Cerebrum: AIOS SDK

cerebrum-aios-sdk

An SDK for developing and deploying LLM-based AI agents within the AIOS framework.

The Capability Collaboration based AI Agent (CACA Agent) is an AI system designed to enhance the extensibility and functionality of AI agents by integrating a set of collaborative capabilities. Inspired by service computing, it reduces reliance on a single large language model (LLM) and promotes an open architecture. CACA Agent introduces components such as Planning Capability, Methodology Capability, Tools Capability, Tool Broker, and Tool Service, which work together to provide AI agent functionalities. This design facilitates quick deployment of AI agents and convenient expansion of their application scenarios, allowing for dynamic tool integration and improved planning abilities. A demonstration of the system illustrates its operation and the extension of application scenarios.

CACA Agent

caca-agent

An AI system enhancing agent extensibility through collaborative capabilities.

PC Agent is an AI system developed by GAIR-NLP that facilitates the creation of autonomous digital agents by transferring human cognitive processes. It comprises three key components: PC Tracker, a lightweight infrastructure for collecting large-scale human-computer interaction data; a Cognition Completion post-processing pipeline that converts raw interaction data into cognitive trajectories; and a multi-agent system combining a planning agent for decision-making with a grounding agent for robust visual grounding. PC Agent aims to enable AI to perform complex digital tasks autonomously by learning from human interactions.

PC Agent

pc-agent

An AI system enabling autonomous digital agents through human cognition transfer.

Roo Code is an open-source autonomous AI agent designed to code, debug, and evolve software systems with minimal human input. It mimics a junior developer's workflow, using a cyclic process of planning, editing, running, and debugging code. Roo Code supports multi-turn coding sessions and automatically persists context across iterations. It is built on top of a task memory system, supports integration with your terminal and development environment, and is designed for continuous improvement through natural interactions.

Roo Code

roo-code

An autonomous open-source AI agent that can code, debug, and evolve software with minimal human intervention.

Giselle is an open-source platform that empowers teams to design and deploy advanced AI agents using an intuitive node-based interface. By integrating multiple large language models (LLMs) and data sources, Giselle facilitates the automation of complex tasks such as market research and code reviews. Its visual development environment simplifies the creation of sophisticated AI workflows, making AI accessible to all team members and enhancing productivity through seamless human-AI collaboration.

Giselle

giselle

An open-source platform enabling teams to create AI agents through a visual node-based interface for automating complex workflows.

Gemma 3 is Google's latest open-source AI model, designed to run efficiently on a single GPU or TPU. It supports multimodal inputs, including text, images, and short videos, and offers advanced reasoning capabilities. With support for over 140 languages and a 128k-token context window, Gemma 3 is versatile for various applications. Its quantized versions enhance performance and reduce computational requirements, making it accessible for devices ranging from smartphones to workstations.

Gemma 3

gemma-3

An open-source AI model optimized for single-GPU performance, supporting multimodal inputs and over 140 languages.

BondAI is an open-source tool designed for developing sophisticated AI agent systems. It handles complex implementation aspects such as memory and context management, error handling, and semantic search capabilities. Supporting advanced AI architectures like ReAct Agents and Conversational Agents, BondAI enables both individual interactions and multi-agent collaborations. The framework integrates seamlessly with services like OpenAI models, Microsoft Azure, Google Search, and LangChain, providing a versatile environment for AI development.

BondAI

bondai

Open-source framework for developing AI agent systems with advanced memory management and integrations.

BabyElfAGI is an advanced modification of the BabyAGI series, introducing a Skills class that allows for the creation of new skills, enhancing the agent's capabilities. It features a 'dynamic task list' example with vector search and includes a beta reflection agent, enabling the AI to read, write, and review its own code. With approximately 895 lines of code, BabyElfAGI represents a significant evolution in autonomous AI agent development.

BabyElfAGI

babyelfagi

An advanced AI agent framework introducing a Skills class for dynamic skill creation and task management.

BabyDeerAGI is a lightweight modification of BabyCatAGI, itself an evolution of BabyBeeAGI and the original BabyAGI framework. With approximately 350 lines of code, BabyDeerAGI introduces parallel task execution, enhancing the efficiency and speed of autonomous task management. It operates using OpenAI's GPT-3.5-turbo model, eliminating the need for GPT-4, and incorporates features such as user input tools, query rewriting in web search, and result saving functionalities. This streamlined approach facilitates faster and more efficient task automation.

BabyDeerAGI

babydeeragi

A streamlined AI agent framework enabling parallel task execution for enhanced efficiency.

BabyCatAGI is a lightweight modification of BabyBeeAGI, itself an evolution of the original BabyAGI framework. With approximately 300 lines of code, BabyCatAGI introduces a task creation agent that operates once at the beginning, streamlining task execution. It features an intelligent agent tool combining web search, scraping, chunking, and extraction to enhance information retrieval and processing, resulting in faster and more stable task management.

BabyCatAGI

babycatagi

A streamlined AI agent framework enhancing task automation and execution efficiency.

Open-Source AI Agents for "Research" Industry