Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

Local AI filmmaking studio — skills, canvas, timeline — driven from your coding agent.

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

28 plugins and MCP servers for Claude Code — TDD, multi-agent orchestration, iterative refinement, binary RE, structured decisions. Install any skill in one command.

CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 185 skills, 280 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

The agent that grows with you

Curated list of AutoResearch use cases with optimization traces and open source implementations

A curated list of research-oriented skills usable in OpenAI Codex, covering writing, literature review, evaluation, and research workflows.

Architecture Deep Research: deep research for strategic system design decisions.

MCP server for enabling LLM applications to perform deep research via the MCP protocol

Research that compiles.

Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server.

Claude Code Plugin for Self-maintaining research knowledge graph for Claude Code + Obsidian

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

AIPOCH Open-Science is an open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, with scientific agents, Python/R notebooks, data connectors, and reproducible provenance.

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

An MCP server for public & prediction markets research. Ask natural-language questions and get structured, source-backed answers across SEC filings, earnings transcripts, company financials, stock & crypto market data, and prediction markets news & research. Built for investors, analysts, and researchers who need fast, cited intelligence.

README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations.

13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents.