Research, science & education

Deep research agents

705 agents · most starred first

Deep research agents, page 4 of 8

clawdbot-skill-parallel★ 21

High-accuracy web research via Parallel.ai API - outperforms Perplexity and Exa on benchmarks. Rich excerpts, citations, source filtering, batch search, agentic mode. OpenClaw skill.

Multi-Agent-Research-Assistant-Langgraph★ 21

Autonomous multi-agent system built using LangChain and LangGraph that orchestrates collaborative agents—Supervisor, Researcher, Writer, and Critiquer—to automatically gather information, generate detailed research reports, refine output, and visualise the workflow as a graph. Includes a Streamlit web UI and optional Graphviz visualisation.

caesar-agent★ 21

Caesar — autonomous AI research agent with graph-based deep web exploration and adversarial answer synthesis. Open-source alternative to ChatGPT Deep Research, Perplexity, and Gemini Deep Research.

enoch-agentic-research-system★ 21

Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated paper packaging.

wheat★ 20

Archived: Evidence and research sprints are now maintained in grainulation/grainulator.

deep-research-agent★ 20

A2A agent implementing OpenDeepResearch

ai-worldcup-2026★ 20

AI WorldCup Arena 2026: AI agents compete to predict the 2026 World Cup with virtual points, leaderboards, reports, and transparent sports analytics.

nullius★ 20

An evidence-first harness for agent-assisted research

deepresearch★ 19

DeepResearch Agent with LangGraph, using any LLM models, search engine, RAG retrieval. 基于LangGraph构建的DeepResearch Agent,可以搭配任意搜索引擎、OpenAI接口兼容的模型。

AMBER-ICI★ 19

AMBER ICI v5: local-first Ollama investigative command center with case-scoped evidence, agent chains, hybrid retrieval, streaming analysis, graph and timeline views, OCR, controlled web research, and GPU telemetry.

AI-Research-Assistant★ 19

gradio region:us

ai-ledger★ 19

Evidence-grounded AI daily for reviewed Digests and cited Research.

opencli-Razormind★ 19

做研究的人都有这种时刻:资料堆了一桌,结论还在雾里。opencli-admin 是一条自托管的研究与情报流水线——可视化编排工作流,采集、AI 处理、证据关联依次就位,数据全程留在自己手里。它做的不是信息的搬运,而是让散落的证据彼此相认。

perplexity-agent-skill★ 18

A agent skill that leverages the Perplexity CLI for web research, deep reasoning, and independent validation.

sample-agentcore-deep-research★ 18

🔬 Agentic deep research application template on AWS

unisearch★ 18

UniSearch 是一款基于 AI 的多平台公开内容采集与调研桌面工具。 通过自然语言描述调研目标,由 AI 自动规划任务流程,并发调度底层连接器进行公开数据采集与清洗。

vibe-science★ 17

🏛️ ACM EASE '26 / VibeX full paper · DOI 10.1145/3816483.3816631 · Adversarial agent loops for verifiable vibe researching. Falsification-first research runtime.

ResearchCopilot★ 17

gradio agent-demo-track multi-agent research perplexity claude openai region:us

Multi-Agent-Research-Assistant★ 17

Developed a Multi-Agent Research Assistant that coordinates specialized AI agents to search, analyze, summarize, and synthesize information from multiple sources, delivering comprehensive, citation-backed research reports and actionable insights.

deep-research★ 16

A Deep Research replica built with LangChain and LangGraph.

The-Living-Agent★ 16

P2PCLAW Research White Paper Series II — 16x16 chess-grid autonomous research agent with evolutionary memory and self-improving capabilities.

enoch-agentic-research-system★ 16

Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated paper packaging.

Istara★ 16

Agentic Research Orchestration for UX Research and Product Development. Vibe and handcoded by a social and data scientist with background in many research domains and open-source

Multi-Agent-Research-Assistant★ 16

Developed a Multi-Agent Research Assistant that coordinates specialized AI agents to search, analyze, summarize, and synthesize information from multiple sources, delivering comprehensive, citation-backed research reports and actionable insights.

cn-company-research-agent★ 16

中文公司调研 Agent

Volt-Deep-Research★ 16

Volt Deep Research is a sophisticated multi-agent orchestration system built on VoltAgent that automates complex research workflows. It combines specialized AI agents, semantic memory, intelligent tooling, and custom web scraping to conduct comprehensive research, verify facts, analyze data, and generate publication-ready reports.

digmore★ 16
Polyagent-Research-Intelligence★ 15

A modular, multi-agent AI research and report generation platform. Enter any topic, and PolyAgent Research Intelligence orchestrates multiple AI agents to retrieve literature, analyze data, and generate a polished report. Built for researchers and AI/ML engineers, leveraging LangChain, FastAPI, PostgreSQL, advanced LLMs, and a Next.js front-end.

architecture-deep-research★ 15

Architecture Deep Research: deep research for strategic system design decisions.

Open-Co-Scientist★ 14

An open-source recreation of AI Co-Scientist: a multi-agent scientific research harness.

Multi-Agent-AI-Researcher★ 13

Multi-Agent-AI-Researcher-Powered-by-DeepSeek-R1-main

claude-adaptive-research★ 13

Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.

polyagent-research-intelligence★ 13

A modular, multi-agent AI research and report generation platform. Enter any topic, and PolyAgent Research Intelligence orchestrates multiple AI agents to retrieve literature, analyze data, and generate a polished report. Built for researchers and AI/ML engineers, leveraging LangChain, FastAPI, PostgreSQL, advanced LLMs, and a Next.js front-end.

Faraday-Web-Researcher-Agent★ 13

Faraday: An Autonomous Web Research Agent (LangGraph/Streamlit). 🕵️♀️ Investigates queries using dynamic tools (Tavily, Google, NewsAPI, etc.), gathers multi-source info, and synthesizes structured reports in a Streamlit UI. Features agentic workflow & source tracking.

SummativeInfoResearcherAgents★ 12

This project is an automated research and summarization tool that allows users to conduct research on a specific question and summarize the information found and present it as a blog post.

digital-war-room★ 12

Multi-agent platform using OSINT tools to create geopolitical analysis

J.A.R.V.I.S★ 12

J.A.R.V.I.S: An AI-powered Open Source Intelligence (OSINT) system. It orchestrates deep web scraping and local LLMs to autonomously generate comprehensive intelligence dossiers.

Noesis★ 12

Self-hosted multi-agent platform — deep research, knowledge-base QA, fault ops and sandboxed tool execution

shandu★ 12

Open-source deep research agent. Ask a question and LLM agents search the web, read pages and PDFs, score source credibility, and write a cited markdown report. CLI and web GUI, runs locally with any LiteLLM model.

palamedes★ 12

Local-first goal discovery engine: compares candidate missions against evidence before planners act (Research Alpha)

AI-Agent-based-Deep-Research★ 11

Deep Research AI Agent is a dual-agent system that conducts web-based research and generates structured summaries. It uses Tavily for data collection and OpenRouter for drafting, offering a user-friendly Streamlit interface with PDF report downloads.

agent-deep-research★ 11

Deep research (CLI and agent skill) via the Gemini Interactions API. Automatic RAG grounding from local files (optional), cost estimation (--dry-run), adaptive polling, structured output, and agent onboarding. No Gemini CLI dependency. Universal AI agent skill for Claude Code, Amp, Codex, Clawdbot, and 30+ agents.

eviback★ 11

EviBack: Reinforcement Learning Search Agents via Evidence-Constrained Teacher Backoff

Tigriden★ 11

Fast, tiny end-to-end research workbench: per-folder terminals for AI coding agents, change tracking with one-click rollback, and LaTeX/PDF/Markdown read as typeset pages.

project-thoth★ 10

An advanced AI-powered research assistant system built for flexibility, extensibility, and user control. Thoth combines intelligent automation with comprehensive customization — every prompt, schema, and source can be tailored to your workflow.

Kallisto-OSINTer★ 10

Public intelligence done by artificial intelligence: an LLM-based OSINT tool designed to perform deep web searches by orchestrating multiple web agents

deepr★ 10

Build persistent AI domain experts from bounded, auditable research. Durable beliefs, confidence, contradictions, provenance, and cost guardrails.

youtube-free-deep-research-cli★ 10

Production-ready Python 3.13+ CLI/API system with Adaptive RAG, multi-engine TTS, OpenRouter key rotation, FastAPI backend, and Next.js dashboard

hermes-autoresearch★ 10

Reusable Karpathy-style autoresearch harness for Hermes Agent.

Agentic-AI-Scientist★ 10

An open-ended, agent-driven research loop: proposes ideas, runs real experiments, and writes up the paper — end to end, unattended.

Multi-Agents★ 10

A multi-agent AI research pipeline built with LangChain and GPT-4o-mini. A search agent gathers sources via Tavily, a reader agent scrapes the most relevant page, a writer chain drafts a structured report, and a critic chain scores it, all wrapped in a Streamlit UI. Built for learning multi-agent orchestration

EasyResearch★ 10

EasyResearch is an open-source AI Research Team designed to automate the journey from ideas to validated scientific knowledge — enabling researchers to discover, reproduce, improve, and create scientific breakthroughs with autonomous agents.

dsh-research-graph★ 10

DSH Research Graph · 研图 — DeepSeek Harness plugin for research topics, traceable knowledge cards, and reusable AI discussions.

Agent--deep-research-Workflow-Skills★ 10

A general-purpose reasoning and deep-research workflow for AI agents with semantic state, traceable evidence, validation, and change control

ARES★ 10

Autonomous Research & Evidence System — Multi-source discovery, hybrid vector/lexical RAG with RRF, 4-tier cognitive memory, and deterministic claim verification.

vitruvius★ 10

Vitruvius is an engineering research agent.

markgitup-research-desk★ 10

Autonomous hourly research desk: a local LLM picks a fresh angle from 24 standing AI/policy/markets topic families, SearXNG gathers the evidence, and nothing publishes without 2+ independent sources. Static site, zero dependencies, built with Hermes Agent.

autoresearch-agent★ 10

🤖 Modular AI Research Agent. Scours scholarly & web sources via LangChain to compile deep-dive research reports.

projectcarfcynepic★ 9
shrimp-oracle★ 9

🦞 SHRIMP Oracle — Open OpenClaw Research Oracle | Tracking AI agents ecosystem, Moltbot evolution, and the gap to AGI

glite-arf★ 9

Glite Autonomous Research Framework - a template repo to fork for your research

am1★ 9

AM1 – A personalized web application for conducting DeepResearch with any Multi-Agent Framework and LLM, designed to run seamlessly on production servers or your local machine.

grounded-research★ 9

A Claude skill that enforces citation-first research discipline. Classifies claims, verifies before writing, signals confidence levels, and audits output for hallucinations. Works with Claude.ai, Claude Code, Cursor, Codex, and Gemini CLI.

crewai-research-assistant★ 9

The CrewAI Research Assistant is a powerful tool designed to help users explore any topic using AI Agents. Built with CrewAI, Exa, and Streamlit, this assistant supports multiple large language models (LLMs) and offers advanced answering capabilities through Exa. It visualizes the research process in real-time, generates structured research reports

langchain-apps★ 9

The project features two applications: a *Research Assistant* that generates research reports using LangChain, OpenAI's GPT-3.5, DuckDuckGo Search API; and a *Chat With Video* app that allows users to upload videos, transcribe audio with OpenAI's Whisper, and store the embeddings in Pinecone vector DB.

proof-engine★ 9

AI agent skill that creates formal, verifiable proofs of claims — every fact computed or cited, never asserted

scholar-agent★ 9

Knowledge agent for LLMs — online research + local accumulation, gets smarter over time. MCP-ready.

manus-js★ 9

An intelligent web research and analysis tool powered by OpenAI GPT models and browser automation. Manus JS streamlines the process of gathering, analyzing, and synthesizing information from web sources.

ARI★ 9

ARI — Autonomous Research Infrastructure: end-to-end autonomous scientific research pipeline

ergodic-pipeline★ 9

Multi-agent AI pipeline that transforms random noise into emergent research ideas through recursive critique and synthesis.

Awesome-Auto-Research★ 9

Tracking the systems that automate scientific research — from literature scrapers to full paper-writing pipelines

briefloop★ 9

本地多运行时 Agent 工作台:围绕材料研究、生成可编辑报告、独立复核、追溯证据,并从人工反馈持续学习。

SAGE★ 9

SAGE: self-correcting autonomous research via Multi-Hypothesis Failure Attribution (MHFA). Diagnose many causes of a failed experiment, verify the most critical, and route the fix to the right level.

ideaforge★ 9

AI-powered research idea generation through adversarial debate. Trains a calibrated judge on 50K real reviews, then uses a 3-agent (Critic-Proposer-Judge) loop to generate and stress-test novel research ideas to publication quality.

xogito★ 9

🔭 Xogito | Your reasoning, unbroken.

ArHub★ 9

Open-source AI research workspace built with Electron and FastAPI, featuring provider-neutral agent workflows for DeepSeek, GLM, and other OpenAI-compatible models.

AI-powered-Research-Assistant★ 9

AI-powered research assistant that retrieves and synthesizes information from ArXiv, Wikipedia, and the web using LangChain and Groq (Llama 3.3 70B), delivering fast, conversational insights through a Streamlit interface

durable-web-research-agent★ 9

Ask a technical question and get well researched answer with citations.

Delve★ 8

AI-powered deep research agent running locally via Ollama. Multi-agent pipeline with persistent memory, RAG, and GraalVM native image support.

Gemini-Claw★ 8

An autonomous research and synthesis agent powered by Google Gemini. Features intelligent deep research, query decomposition, and safe local system control via a native Python loop

research-assistant-mini★ 8

Research Assistant Mini App

Synaptic★ 8

A website where a user enters one seed (entrepreneurial) idea and gets back an explorable, zoomable thought graph with labeled relationships, expandable nodes, critique on initial idea, cross check (across all online sources) whether an idea already exists or not, and one-click one-pager export.

autonomous-multi-agent-deep-research-system★ 8

Multi-agent RAG research assistant with FastAPI, React, FAISS, Redis memory, async agents, streaming, sources, and evaluation.

Research_council★ 8

GraphRAG + 4-agent LLM council for biomedical research. Find contradictions, validate hypotheses, and get confidence-scored answers, cited to real papers. Built on Neo4j, LangGraph, Groq & OpenRouter.

sample-rca-deep-investigations★ 8

Deep Research pattern for root cause analysis using Amazon Bedrock and LangGraph with human-in-the-loop

multi-agent-research-synthesis★ 8

A methodology for conducting comprehensive research using multiple AI research agents, with a CLI AI agent orchestrating phased synthesis of results

Research-Agent★ 8

Autonomous research agent — 10 sources in parallel, self-correcting loop, exports PDF/Word/HTML. Powered by LangGraph + Ollama.

open-research-agent★ 8

Multi-agent research CLI. Plan, search, scrape, synthesize, review -- all from your terminal.

Deep-Research-104★ 8

Production-grade Deep Research AI with web search, reasoning models (OpenAI o3, DeepSeek-R1), and inference-time scaling.

mirofish-ai-skill★ 8

GenPark skill: AI-driven scenario prediction and simulation using Mirofish's graph-building pipeline.

sheldon★ 8

SHELDON is a reasoning harness that searches observations and hypotheses as two separate spaces, focusing on finding unknown observations to generate new hypotheses.

genpark-research-vault★ 8

Terminal-native multimodal AI research assistant.

awesome-deep-research★ 7

Compilation of info on AI `deep research` tools

reach★ 7

How about a CLI for searching PDFs and Web for your Research

capcheck-architecture★ 7

Public documentation for the CapCheck AI fact-checking platform. This repo contains architecture decisions, design patterns, and technical deep-dives without proprietary code.

hermes-researcher★ 7

Autonomous deep-research platform powered by Hermes Agent. Multi-phase pipeline with parallel research, self-critique, iterative refinement, and real-time streaming.

cursor-cli-heavy★ 7

🔬 Parallel AI research orchestration tool - Deploy multiple cursor-agent workers simultaneously to conduct comprehensive research with specialized focus areas and intelligent synthesis.

simple-deep-agent★ 7

Simplified implementation of a deep research agent using LangGraph

elite-strategic-research★ 7

7-layer agentic research engine for Claude Code — McKinsey + BCG + IBISWorld + Harvard + Stanford + MIT + PRISMA 2020. Certified, traceable, board-ready research.

storm-fusion-research-pipeline★ 7

Human-gated perspective-panel research: one question, several seats, one judge. Solo, native panel, or per-seat MoA/Fusion fanout.

More in Research, science & education