explaingit

bettyguo/awesome-research-agents

Analysis updated 2026-05-18

7Audience · researcherComplexity · 1/5Setup · easy

TLDR

A curated, opinionated list of 44 AI tools and MCP servers that machine learning researchers actually use, organized by research workflow stage.

Mindmap

mindmap
  root((research agents list))
    What it does
      Curates 44 tools
      Organized by workflow stage
      Honest pros and cons
    Discover and read
      Elicit
      AI2 Scholar QA
      arXiv MCP server
      Zotero
    Code and evaluate
      Semantic Scholar MCP
      Hugging Face MCP
      Marker PDF tool
      GROBID
    Use cases
      Pick a literature tool
      Wire up agent MCP servers
      Convert PDFs to text
    Audience
      ML researchers
      Grad students
      Labmates

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Find vetted MCP servers and agents for literature search, reading, and experiment tracking.

USE CASE 2

Compare tools like Elicit and AI2 Scholar QA before choosing one for a literature review.

USE CASE 3

Pick a PDF to Markdown tool such as Marker or GROBID for processing scientific papers.

What is it built with?

Markdown

How does it compare?

bettyguo/awesome-research-agentsadguardteam/ruleseditorbaiyuetribe/serverstatus-theme
Stars777
LanguageTypeScriptCSS
Last pushed2026-07-012019-07-21
MaintenanceActiveDormant
Setup difficultyeasyeasymoderate
Complexity1/52/52/5
Audienceresearcherdeveloperops devops

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

In plain English

Awesome Research Agents 2026 is a curated list built for machine learning researchers, not another giant directory of every AI tool that exists. The author reviewed the space and picked 44 entries, organized by the stages of a real research workflow: discovering papers, reading and annotating them, running experiments, writing code, evaluating results, writing papers, sharing work, and staying current with new releases. That structure matters because a junior researcher usually knows what task they need to finish, but not whether the right tool for it counts as an agent framework, a skill, or an MCP server. What sets this list apart from typical roundups is that every entry includes a short "Why we recommend it" note explaining something the tool's own documentation would not say, plus a one line "When not to use" warning. So instead of just listing options, the project states the tradeoffs plainly: which tools are actually maintained, which are thin wrappers around something else, which have a free tier worth using, and which only make sense in narrow situations. Examples from the README include Elicit for structured literature review, which is closed source but has a real free tier, AI2 Scholar QA for open, citation backed literature synthesis, small focused MCP servers for searching arXiv and Semantic Scholar, and Hugging Face's official MCP server for giving an AI agent live access to models and datasets. On the reading side it covers Zotero for reference management, a Better BibTeX plugin for stable citation keys, and PDF to Markdown tools such as Marker and GROBID for turning scientific papers into structured, searchable text. Entries are checked again every quarter. Tools that stop being maintained get cut, and stronger alternatives take their place. The project accepts pull requests but holds them to a high bar, since the entire point of the list is judgment, not coverage. This is a reference for researchers choosing tools, not a piece of software you install or run yourself.

Copy-paste prompts

Prompt 1
Which tool in this list is best for searching arXiv from an AI agent, and why?
Prompt 2
Compare Marker and GROBID for converting scientific PDFs to Markdown based on this list's recommendations.
Prompt 3
Suggest which tools from this list I should combine for a full research workflow, from paper discovery to writing.
Prompt 4
Explain why Elicit is recommended over other literature review tools according to this list.

Frequently asked questions

What is awesome-research-agents?

A curated, opinionated list of 44 AI tools and MCP servers that machine learning researchers actually use, organized by research workflow stage.

How hard is awesome-research-agents to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is awesome-research-agents for?

Mainly researcher.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.