AI research agents
Agents that do the reading for you: they search, screen sources, extract findings and write a report with citations.
By weekly package downloads, the leaders are Kosmos (13.5K), GPT Researcher (13.1K), STORM (329). By GitHub stars, the leaders are BettaFish (42.3K), STORM (31.6K), GPT Researcher (29.9K). The fastest grower over the last 30 days is Kosmos, with downloads up 48%. As of Oct 6, 2026.
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 68 |
ConsensusConsensus |
43 | — | — | — | — | — | — | Free + $20/mo | ||
| 73 |
BettaFish666ghj (community project) |
43 | — | — | — | — | 42.3K+8/day | 3.0.09mo ago | Free (OSS) | — | |
| 97 |
SciSpace AgentPubGenius Inc. |
37 | — | — | — | — | — | — | Free + $20/mo | ||
| 102 |
ElicitElicit |
36 | — | — | — | — | — | — | Free + $49/mo | — | |
| 141 |
GPT ResearcherAssaf Elovic and contributors |
28 | 13.1K | up 42.4% | down 41.5% | — | 29.9K+28/day | 3.7.010d ago | Free (OSS) | ||
| 152 |
KosmosEdison Scientific |
26 | 13.5K | up 10.2% | up 48.1% | — | — | — | Free + $200/mo | ||
| 199 |
STORMStanford OVAL |
14 | 329 | up 21.0% | down 50.5% | — | 31.6K+9/day | 1.1.020mo ago | Free (OSS) | ||
| 215 |
UndermindUndermind |
7 | — | — | — | — | — | — | Free + $20/mo | ||
| No agents match that filter. | |||||||||||
Ranks are overall positions by Pulse Score. Click a column to sort by what matters to you. Methodology.
Two kinds of research agent
- Academic research agents (Elicit, Consensus, SciSpace, Undermind, Kosmos) search scholarly databases, screen papers, extract data into tables and write literature reviews. Some support systematic-review workflows.
- Open-source deep research agents (GPT Researcher, STORM) run on your own machine with your choice of model and search provider and write reports from web or local sources.
General assistants also have research modes; see AI agents for research.
Using them well
A research agent saves the gathering step, not the checking step. Open the citations for every claim you will rely on, ask what the sources disagree about, and say which kinds of evidence you trust.
Head-to-head comparisons
Related guides
Questions about AI research agents
What is the best AI agent for research?
For academic literature, look at the agents built on scholarly databases, which cite papers rather than web pages. For general web research, deep-research modes of general assistants and the open-source agents here work well. By the public signals tracked here, Consensus currently ranks first.
Can AI write a literature review?
Several agents here draft literature reviews with citations and extract data from papers into tables. Treat the result as a first draft: check that each cited paper says what the review claims.