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

CORAL

Infrastructure (arXiv:2604.01658) for *multi-agent autonomous self-evolution* — organizations of AI agents that run experiments, share knowledge through persistent stores, and continuously improve solutions against a user-supplied grading script. Sits in the *autoresearch infrastructure* layer alongside Aviary and MLGym, but emphasizes evolution and self-improvement rather than benchmarking.

Indexed in RISE · activeConformance with the standard plannedProject site

What it does

Treats the *organization* of agents (workspaces, shared knowledge, judges) as a first-class engineering surface, with rubric-based judge packages (race_japan_grader, apex_judge) that themselves spawn Claude Code for evaluation. Natively integrated with Claude Code, OpenCode, Codex, and Cursor.

Focus
end-to-end
Inputs
codebase, grading-script
Outputs
evolved-solutions, shared-knowledge-store, judge-reports
Architecture
multi-agent, persistent-memory, artifact-versioning, iterative-loop, debate-consensus
Maintained by
Human-Agent-Society
Started
2026

Description

Data model
Discipline
General
Method family
not specified
Design
not specified
Research stage
Research designData analysisCode generationReview
Contributors
Human-Agent-Society
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:coral · 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.