Eureka39/CARS

Eureka39/CARS

Agent Claude Code

Research blueprint compiler. Converts Supervised Layer 5 convergence insights into structured execution specifications for downstream research modules (Experiment Agent, Code Agent, Paper Writing Module).

Eureka39/CARS

Agent Claude Code

Calls the deepreadpdfs MCP tool in cruncher.py to batch deeply read PDF papers into structured Markdown reports.

Eureka39/CARS

Agent Claude Code

Reads deep-reading Markdown reports output by cruncher.py, parses structured content (including problematization fields), converts it to JSON format (v2.0.0), and stores it in hypotheses/translated/ for downstream Matrix Engine consumption.

Eureka39/CARS

Agent Claude Code

Receives the filtered list of paper IDs, calls the Semantic Scholar batch API to download full metadata, saves individual JSON files, downloads open-access PDFs, and maintains a consolidated metadata file.

Eureka39/CARS

Agent Claude Code

Master control agent of the Literature Scout module. Interacts with the user and coordinates the four sub-agents: querybuilder, seedexpander, relevancejudge, and batchfetch to complete the entire literature search process.

Eureka39/CARS

Agent Claude Code

Extracts keywords from userprofile, generates multi-perspective natural language queries, calls the Semantic Scholar API to search for papers, and outputs a deduplicated candidate paper set.

Eureka39/CARS

Agent Claude Code

Reads candidate paper collections, performs confidence scoring based on the match between abstract content and the user's research direction; high confidence automatically triggers download, while medium/low confidence is shown to the user for decision.

Eureka39/CARS

Agent Claude Code

Reads searchseeds from userprofile, calls Semantic Scholar recommendation API to expand relevant literature based on seed papers, deduplicates, and outputs a candidate paper set.

Eureka39/CARS

Agent Claude Code

Reads structured paper JSONs, extracts problem × method axes, builds a taxonomy-based matrix, identifies research gaps with problematization analysis, outputs matrix.json, and automatically calls MCP tool to export CSV visualization.

Eureka39/CARS

Agent Claude Code

Reads the latest Socratic session and existing userprofile.json, extracts/merges cognitive materials, incrementally updates the global profile, and synchronizes the project README.

Eureka39/CARS

Agent Claude Code

Challenges assumptions at key Socratic dialogue nodes, tests logic chains, and identifies bias. It is a sub-agent called by socraticmentoragent.

Eureka39/CARS

Agent Claude Code

Use Socratic questioning to extract raw cognitive material from the user. Supports both zeroshot (cold start) and supervised (hot start) modes.

Eureka39/CARS

Agent Claude Code

After each user reply, decide whether the dialogue should stay, progress, redirect, or regress. Supports both zeroshot and supervised modes with different layer definitions and exit signals.

Eureka39/CARS

Agent Claude Code

Review question quality before the Socratic mentor asks; ensure questions match layer depth and protocol rules for both zeroshot and supervised modes.