Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

Kosmos (jimmc414 implementation)

An open-source implementation of the Kosmos AI scientist architecture (Lu et al., arXiv:2511.02824), adapted to run via Claude Code or the Anthropic / OpenAI APIs. Runs autonomous research cycles: hypothesis generation, experiment design, code execution in sandboxed Docker, validation against an 8-dimension quality framework, and knowledge-graph construction.

Indexed in RISE · research-prototypeConformance with the standard plannedProject site

What it does

Operationalizes the Kosmos architecture as a runnable system on commodity infrastructure, including a built-in 8-dimension validation harness and an explicit knowledge-graph layer that tracks concept relationships across cycles. The validation framework is independently reusable as a methodological scaffold.

Focus
end-to-end
Inputs
research-area, data
Outputs
hypotheses, experiment-results, knowledge-graph, validated-discoveries
Architecture
multi-agent, tool-use, rag-knowledge-base, persistent-memory, iterative-loop, artifact-versioning
Maintained by
jimmc414
Started
2025

Description

Data model
Discipline
General
Method family
not specified
Design
not specified
Research stage
HypothesesResearch designData analysisCode generation
Contributors
jimmc414
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:kosmos · 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.