Research AI Agents
Research AI agents automate web search, literature review, paper summarization, and fact synthesis. They help researchers, analysts, and knowledge workers gather and distill information much faster than manual methods.
198 agents found — updated daily
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowled
A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Framework for orchestrating role-playing AI agents
345 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references,
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents th
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and co
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Mod
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
Machine Learning and Agentic AI Resources, Practice and Research
🇨🇳 OpenClaw中文用例大全 | 50个真实场景 | 国内特色 + 海外案例的国内适配 | 自动化办公·内容创作·运维·AI助理·知识管理 | 新手友好
Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agent
🔬 Harness Vibe Research with Self-evolving AI Scientists
"Paper2Slides: From Paper to Presentation in One Click"
[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers
📡 Comprehensive collection of OSINT tools for cybersecurity professionals, researchers, and bug bounty hunters. Topics:
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently
Surface AI blindspots before you ship. Put up to 8 AI models on every research, design or coding task.
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval t
Cross-CLI skill for Obsidian: turn your vault into a living AI-first second brain across Claude Code, Codex, Gemini, Ope
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and
🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of pap
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inha
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extra
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration t
一个基于 AI 的 Hacker News 中文播客项目，每天自动抓取 Hacker News 热门文章，通过 AI 生成中文总结并转换为播客内容。
Research into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security cla
An open-sourced research agent system deeply rooted in your Zotero library.
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code fo
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to
The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify,
Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat,
A curated list of skills, plugins, tools, integrations, and resources for Hermes Agent by Nous Research
Aria is Your AI Research Assistant Powered by GPT Large Language Models
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan
Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workf
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call
Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice,
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree sea
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, C
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generatio
Thoth - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vi
YC S26 | WUPHF by Nex.ai lets you spin up your personal office of AI teammates who collaborate over shared context. Supp
Open source and self-hostable browser automation library for AI agents
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shippi
Curated list of AutoResearch use cases with optimization traces and open source implementations
This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!
A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-
An AI co-scientist powered by Scientific Agent Skills running on your desktop.
Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-host
MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across p
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge grap
The all-in-one AI agent living in your terminal. Build landing, mobile apps, backends, manages files, deep research, sch
🤖 Automatically collected AI repos, tools, websites, papers & tutorials. 实用AI百宝箱 💎
🔥🔥COLM 2026🔥🔥 CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built fo
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, epi
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on gr
Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful
A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents.
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-h
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.
沁言学术科研论文Skills库 - 177个学术研究Agent Skills的综合集合，涵盖论文检索、科学写作、生物信息、药物发现、临床医学等17个分类
Open-source, local-first AI journal app for iOS and Android. Capture text, photos, and voice — AI agents organize them i
freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scena
The Linux OS for AI Agents — Persistent memory, structured reasoning, and governed autonomy for any LLM. Own the state.
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.
Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack，让 AI 团队各司其职、自主稳定迭代。
ChatGPT-Pro is an advanced application that combines the power of ChatGPT and DALL.E.
The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit tra
An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with determinis
Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP ser
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL
Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.
Your AI Chief of Staff — a personal operating system starter kit that adapts to your role. No coding required.
An autonomous research colleague — from a question to a compiled manuscript, while you sleep.
Practical AI collaboration playbook for research, writing, reading, and coding: article, prompts, agent rules, and reusa
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with
Open Paper is a workbench for managing your research library. Read, annotate, and understand your papers all in one plac
Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)
Documentation that works for both humans and AI systems
[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/
Curated list of LLM-driven trading agents, MCP servers, and agent skills for market research, strategy, and execution.
Automate lead research, qualification, and outreach with AI agents and Langgraph, creating personalized messaging and co
A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent
your notes and research documentation now a local LLM Memory
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24
✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models
ChatClaw: Get OpenClaw-like knowledge base personal AI agent in 5 mins. Sandbox-secured, ultra-small 30MB installer for
A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answe
A curated list of awesome projects and resources related to autonomous AI agents.
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, a
Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code
Prediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket ·
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regressi
A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LL
Awesome AI Agents for 2026 - 300+ AI Agents, Frameworks & Coding • Creative • Voice • Research • Enterprise. Comparison
🤖 AI-powered code generation tool for scratch development of web applications with a team collaboration of autonomous A
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Po
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic mar
Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex,
The memory layer for AI-native development — giving AI persistent understanding of your software projects.
A library-science-inspired personal knowledge management system with LLM agents
Official code for the paper "Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity"
The creative suite for character-driven AI experiences.
Autonomous quantitative trading research platform that transforms stock lists into fully backtested strategies using AI
A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings
A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a sour
Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
Open‑source alternative to Perplexity Comet, director.ai and firecrawl combined
Turn topics, links, and files into AI-generated research notebooks — summarize, explore, and ask anything.
Personal OS agent that learns who you are, detects life patterns, and grows smarter about you every day. Memory + Cron +
Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP tools, 6-tie
[NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents & [arXiv 2026] GTA-2
📚 PaperFlow: Dynamic personalized scientific-paper recommendation, reading, and reporting
Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary source
Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI appli
[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on mod
🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strat
A Large-Scale Knowledge Graph for Automated Scientific Research
Drop-in scientific plotting skill for Claude Code, Codex, Cursor, and other coding agents.
Read translation intelligent agent for Google Mail academic paper subscription
Automatically completes the full workflow from requirement research → research review → planning → plan review → develop
A collection of awesome AI-for-research papers and projects, covering all stages of the research process and a wide rang
We believe that every SOTA result is only valid on its own dataset. RAGView provides a unified evaluation platform to be
MOTO Autonomous ASI Deep Research Harness by Intrafere - creative novelty-seeking researcher with autonomous Lean 4 proo
The AI Agent Workflow: Connect Obsidian, Linear, and OpenClaw for a persistent AI teammate. Setup guide + templates.
44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent mem
AI customer support agent, live on your website in 5 minutes
Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel
Embodied AI companion for Minecraft — persistent memory, vision, learning, multi-agent. Built on Hermes Agent.
Codex skill for student project delivery: reports, defense decks, academic writing, and reusable AI-assisted engineering
Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with
Knowledge graph extractor: Markdown (or any format) → knowledge graph with RDFS/OWL ontology
Local-first Chrome extension for collecting, organizing, and exporting X/Twitter posts for research, AI workflows, and p
Harness-enforced AI business research skill for Claude Code and Codex Desktop
AI-powered stock watchlist and daily market report workflow for Claude Code. Track movers, earnings, macro data, and gen
Autonomous AI agent for Crustocean, powered by Hermes Agent from Nous Research
Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard →
The validation layer for solo founders. Research, strategy, and validation on Claude Code - decide before you build. MI
Open Comet is an autonomous AI agent integrated into your Chrome browser. It enables safe, transparent, and multi-modal
AI copilot for product managers. Built for Claude Code and Cursor.
The quantum substrate of the Neura Parse stack — one IR across gate, neutral-atom, photonic-CV and pulse modalities; f
A Multi-modal chatbot with LangChain, that supports RAG, Paperswithcode, and Image generation using Dall-E-3
Welcome to our new Custom WebSearch Agent, now as an easy-to-use Streamlit app! No more sifting through loads of generic
RAG-based internal knowledge copilot for fintech support, providing grounded answers with source citations and safe refu
Autonomous market research agent powered by Gemini 3.5 Flash and google-genai SDK. It runs a ReAct loop using Bright Dat
Génère un rapport société FR complet (13 sections, 9 sub-agents en parallèle) à partir d'un SIRET, URL ou nom. Adapté à
🚀 Discover the latest in AI-generated content with AIGC Weekly, a curated newsletter powered by Agentic AI, offering to
AI research assistant for academic literature review with 200M+ scholarly papers
Academic search engine that answers questions with scientific paper evidence
Neural semantic search API for AI agents and developers building research tools
Autonomous AI SDR that prospects, researches, and sends outreach 24/7
Frequently Asked Questions
What are the best AI agents for research?
Top research AI agents include Perplexity AI, Elicit (for academic papers), Consensus, and open-source tools like GPT-Researcher. For deep web research workflows, tools like Tavily and Exa provide AI-native search APIs.
Can AI agents summarize research papers automatically?
Yes — AI research agents like Elicit, Semantic Scholar, and SciSpace can read, extract key findings, and summarize academic papers. They can compare findings across dozens of papers and highlight methodology differences.
What is the difference between Perplexity and a search engine for research?
Perplexity reads and synthesizes sources in real-time, returning a direct answer with citations rather than a list of links. For research, this saves significant time — it cites sources inline so you can verify each claim, unlike a search engine that only returns links.