Preview build on GitHub Pages. The open registry will live at e2er.org.
Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

Open CoScientist Agents

An open-source implementation of Google DeepMind's *AI co-scientist* (arXiv:2502.18864), built on LangGraph and GPT Researcher. Realizes the co-scientist's multi-agent design — literature review, generation, reflection, evolution, meta-review, supervisor, and a tournament-style hypothesis competition with ELO ranking.

Indexed in RISE · archivedConformance with the standard plannedProject site

What it does

Makes a major closed industrial design (DeepMind's co-scientist) inspectable and runnable: every agent role and the ELO tournament loop are present in code, with a Streamlit dashboard for inspecting hypothesis competition transcripts. Useful as a reference implementation against which the original paper's claims can be audited.

Focus
ideation
Inputs
research-goal
Outputs
ranked-hypotheses, tournament-transcripts, research-report
Architecture
multi-agent, tool-use, rag-knowledge-base, iterative-loop, debate-consensus
Maintained by
conradry
Started
2025

Description

Data model
Discipline
General
Method family
not specified
Design
not specified
Research stage
Literature discoveryLiterature synthesisHypothesesResearch design
Contributors
conradry
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:open-coscientist · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Bring it into the standard

A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.