Discover AI agents for researchers: Browse our comprehensive directory of intelligent digital assistants and AI automation tools.

AI Agents for researchers | AI Agent Store

Taskade’s AI agents, powered by GPT-4, are designed to support complex project management, research, and workflow automation. Users can assign projects or tasks that these AI agents will autonomously complete, helping with everything from content research to report writing and workflow management. By creating an **AI-powered workforce** that completes tasks independently, Taskade enhances productivity and efficiency across various departments.

Taskade AI Agents

taskade-ai-agents

Custom AI-powered agents designed to automate workflows, enhance productivity, and streamline team collaboration.

QuillBot is a comprehensive AI-driven writing platform designed to assist users in improving their writing through a suite of tools. Key features include a Paraphraser that rephrases text to enhance clarity and style, a Grammar Checker that identifies and corrects grammatical errors, a Summarizer that condenses lengthy texts, and an AI Detector that analyzes content for AI-generated text. QuillBot integrates seamlessly with various platforms, including browser extensions and word processors, making it a versatile tool for students, professionals, and content creators aiming to produce polished and effective written communication.

QuillBot

quillbot

An AI-powered writing assistant offering tools for paraphrasing, grammar checking, summarizing, and more to enhance writing quality and productivity.

SillyTavern is a free, open-source frontend for interacting with LLM backends, popular for character chat and long-form roleplay. It provides a rich chat UI with character cards, prompt controls, and an extensions ecosystem. Core features include “World Info” (lorebooks/memory books) for dynamically injecting context into prompts and STscript/Quick Replies for automation-like macros and scripted actions. SillyTavern is licensed under AGPL-3.0 and is typically self-hosted or run locally, connecting to external model providers or local inference stacks rather than running models itself.

SillyTavern

sillytavern

Open-source LLM chat frontend for power users with character cards, lorebooks, extensions, and support for many model backends.

Bright Data Web MCP is an open-source Model Context Protocol (MCP) server that connects AI assistants to the live public web with built-in unblocking to avoid CAPTCHAs and rate limits. It provides tools for real-time web search, page fetching and scraping (including via Bright Data’s web unlocker), and optional browser automation for navigating and interacting with dynamic sites. It supports a free “Rapid” tier (limited toolset and monthly request allowance) and paid usage-based modes that unlock additional tool groups such as browser control and broader web data tooling. It can be used via Bright Data’s hosted MCP endpoint or run locally via an npm package.

Bright Data Web MCP

bright-data-web-mcp

MCP server that gives AI agents reliable web search, scraping, and browser automation with 5,000 free monthly requests.

Atelier Ruixen is a web-based AI knowledge companion focused on generative knowledge management (GKM). It is positioned as a “librarian” style agent that helps users move from vague questions to clearer, higher-signal queries, then curates and organizes an actionable reading list to support deeper understanding. The experience emphasizes turning exploration into structured insights by guiding query refinement, helping users discover relevant resources, and keeping an evolving knowledge flow for ongoing learning and research.

Atelier Ruixen

atelier-ruixen

AI knowledge companion that refines questions and curates reading lists to turn scattered info into actionable insights.

FLAMEHAVEN FileSearch is an open-source, self-hosted RAG document search engine you can run locally (Docker or Python). It supports multi-format ingestion (PDF, DOCX, TXT, MD) and provides keyword, semantic, and hybrid search modes (with typo correction). Results include source attribution, and the API includes production features like API-key authentication with permissions, rate limiting, audit logging, batch search, and an admin dashboard. It integrates with Google Gemini (via GEMINI_API_KEY) and supports a lightweight local store plus optional components such as Redis caching and Postgres/pgvector for higher-performance deployments.

FLAMEHAVEN FileSearch

flamehaven-filesearch

Self-hosted RAG file search engine (FastAPI) with keyword/semantic/hybrid modes, citations, API keys, and Docker quickstart.

Together Open Data Scientist is an open-source AI data analysis agent built around the ReAct (Reasoning + Acting) pattern. It automates common end-to-end data science workflows: loading and exploring datasets, running EDA, engineering features, training baseline models, creating plots, and writing a structured report. The agent can execute Python code either locally (via Docker/internal execution) or in the cloud using Together Code Interpreter (TCI), and it supports uploading a data directory for analysis. It’s positioned as experimental software—outputs should be reviewed and validated—making it most useful for exploration, learning, and fast first-pass analysis rather than unattended production analytics.

Together Open Data Scientist

together-open-data-scientist

Open-source data scientist agent that runs Python (locally or in the cloud) to explore datasets, build models, and generate detailed analysis reports using the ReAct framework.

ComfyUI is a free, open-source, node-based platform for generative AI. Creators assemble visual workflows to produce images, video, 3D, and audio, extend functionality with custom nodes, and run everything locally for speed, control, and cost savings. The Comfy Org ecosystem includes a desktop app, a registry for custom nodes, continuous-integration testing, and an announced Comfy Cloud beta to run workflows in the browser without setup.

ComfyUI (Comfy.org)

comfyui-comfy-org

Open-source, node-based generative AI platform to build image, video, 3D, and audio workflows locally or in the cloud.

ChatGPT Atlas is OpenAI’s AI-powered web browser that brings ChatGPT into every page you visit. It adds a sidebar for instant answers and summaries, optional memory so it can recall useful context, and an agent mode that can take actions on sites under your control—like researching, shopping, or handling tasks end to end. Atlas is currently available for macOS, integrates privacy controls (incognito, site permissions, history clearing), and is free to download with optional paid tiers for additional features.

ChatGPT Atlas

chatgpt-atlas

AI browser with a ChatGPT sidebar, memory, and agent mode to summarize, search, and act across the web; macOS app, free with upgrades.

Comet is Perplexity’s AI-powered web browser that acts like a personal assistant while you surf. Built on Chromium, it weaves Perplexity into the browser to answer questions, research, summarize pages, shop, book, and automate routine actions. Comet is available for macOS and Windows, with Android listed as coming, and has recently been made free to download for everyone—while optional subscriptions (e.g., Comet Plus, Perplexity Pro/Max) add premium capabilities and benefits.

Comet (Perplexity)

comet-perplexity

AI browser from Perplexity that assists your browsing—search, summarize, automate tasks, and organize online; free with optional upgrades.

Wan2.2 is an open-weights family of large-scale video generative models released by the Wan-Video team as the successor to Wan2.1. It introduces expanded training data and architecture upgrades, offering multiple variants for text-to-video, image-to-video, video-to-video, and even speech-to-video generation. The models produce cinematic, higher-resolution clips with stronger temporal consistency and motion control, and are available under an Apache-2.0 license with runnable repos and Hugging Face checkpoints.

Wan2.2

wan2-2

Open-source video generation model family (5B/14B) for text/image/video-to-video, delivering 1080p clips with improved motion and control.

y2doc is an AI-powered tool that transforms YouTube videos into richly formatted documents in a single click. It processes video content—up to around four hours—into structured notes, summaries, dialogue transcripts, emails, and more, enabling efficient extraction of insights from video content.

y2doc

Converts YouTube videos into structured documents automatically with one click.