autoresearch
Apply Karpathy's autoresearch loop (goal + mechanical fitness + mutable surface + keep-or-revert iteration) to ANY measurable workflow - code, content, sales, research, design…
Pacote de plugins · de Bayram Annakov
Resumo
autoresearch é um pacote de plugins para ferramentas de programação com IA publicado por Bayram Annakov. Marketplaces que lemos e que o listam: 1 (Community GitHub marketplaces). Vimos pela primeira vez em 2026-10-15 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-24.
Apply Karpathy's autoresearch loop (goal + mechanical fitness + mutable surface + keep-or-revert iteration) to ANY measurable workflow - code, content, sales, research, design, operations. Includes a pre-loop triage that refuses fat-tailed, reflexive, or slow-feedback problems without adapting the mode, and five modes (pure, barbell, via negativa, inverted, human-in-loop).
O que pede
- Instala-se como pacote de plugins
Nenhum dos marketplaces que lemos publica as ferramentas ou as configurações que ele pede.
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Funciona com
- Claude Code
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como plugin do Claude Code
Gerado a partir do que Community GitHub marketplaces declara.
/plugin marketplace add bayramannakov/ai-native-product-skills
/plugin install autoresearch@ai-native-product-skillsOnde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Marketplace da comunidade bayramannakov/ai-native-product-skills (Abrir o código no GitHub) | Listado | 4.1.1 | Forks (GitHub): 3 Estrelas (GitHub): 15 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
Listado em um marketplace da comunidade
| Marketplace | Repositório | Estrelas (GitHub) |
|---|---|---|
| ai-native-product-skills | bayramannakov/ai-native-product-skills | 15 |
O que o pacote contém
Conforme publicado em Community GitHub marketplaces.
Skills: 5
autoresearchcouncilprototypeteam-assesstransformation-roadmap
O que mudou
- Passou a ser um produto que acompanhamos
- Community GitHub marketplaces: apareceu
Possivelmente o mesmo plugin
Listagens que compartilham um sinal com esta, mas não o bastante para tratá-las como o mesmo produto.
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
-
Set up autonomous goal-driven optimization — creates a GOAL.md fitness function and runs an improvement loop
-
lazy-developer
Orchestrates autoresearch across a prioritized sequence of optimization goals — with configurable phase order and optional ralph-driven execution
-
Autonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats…
-
Autonomous SKILL.md improvement via Karpathy autoresearch-inspired iterative eval hill-climbing with force iteration, NEUTRAL mutation judgment, mutation exclusions, L1/L2/L3 eval…
-
Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor…
-
Autonomous research loop inspired by karpathy/autoresearch — give it a plain-language goal; it infers a recommended contract, then grills each decision with you (goal…
-
Drop-in agentic loop skills (autoresearch, literature & writing, data, optimization, red-team, power analysis). Skills install namespaced as agent-loops:<name>.
-
20 enterprise-grade skills for autonomous AI/ML research lab operations. Includes 10 custom gap-analysis skills (research-commander, agent-debugger, model-evaluator…
-
Decision-grade data science: audits, leakage-safe experiments, diagnosis, validation, reproducible handoff.
-
Premium planning, thrifty implementation
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em Claude Code: claude-plugins-community (5)
-
Autonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats…
-
Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor…
-
20 enterprise-grade skills for autonomous AI/ML research lab operations. Includes 10 custom gap-analysis skills (research-commander, agent-debugger, model-evaluator…
-
Research sprint orchestrator for Claude Code. Ask a question, get a decision-ready brief — every finding is tracked as a typed claim, adversarially challenged, confidence-graded…
-
A self-learning development pipeline that gets smarter with every cycle. It calibrates itself against your codebase, dynamically selects the highest-impact tasks, implements them…
Listado em Claude Code: claude-plugins-official (5)
-
Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
-
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to…
Listado em Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
-
Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
AI agent skills that make SaaS products data-ready for product analytics — from codebase scan to tracking plan to working instrumentation code.
Listado em Codex: openai-curated (openai/plugins) (5)
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Answer product and business questions with data
-
Notion workflows for implementation planning, research synthesis, meeting preparation, and knowledge capture.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
Listado em Community GitHub marketplaces (5)
-
Set up autonomous goal-driven optimization — creates a GOAL.md fitness function and runs an improvement loop
-
lazy-developer
Orchestrates autoresearch across a prioritized sequence of optimization goals — with configurable phase order and optional ralph-driven execution
-
Autonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats…
-
Autonomous SKILL.md improvement via Karpathy autoresearch-inspired iterative eval hill-climbing with force iteration, NEUTRAL mutation judgment, mutation exclusions, L1/L2/L3 eval…
-
Autonomous research loop inspired by karpathy/autoresearch — give it a plain-language goal; it infers a recommended contract, then grills each decision with you (goal…
Listado em Copilot CLI: github/awesome-copilot (5)
-
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
MCP server and 12 skills for product analysis, specification writing, strategy, narrative, and stakeholder alignment. Run competitive analyses, write zero-question specs, design…
-
Turn your Copilot sessions into proof of impact — research-grounded HTML reports with effort estimation, skills analysis, and ROI metrics from local session logs.
-
7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps.
Listado em Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Advanced Security plugin for GitHub Copilot.
Listado em Cursor: cursor/plugins (5)
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Skill mapping, practice plans, and learning retrospectives.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
Listado em Docker MCP Catalog (5)
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Real-time web search, reasoning, and research through Perplexity's API
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
Listado em Official MCP Registry (5)
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
pm-claude-skills io.github.mohitagw15856/pm-claude-skills
1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
-
Find the safest first AI workflow before investing in AI agents or automation.
-
bstorms.ai — Free Execution Playbooks + Agent Brainstorming
Free execution-focused playbooks. Brainstorm with other agents. Tip if helpful.
-
Grow your skills with AI: per-skill coaching inside Claude, ChatGPT, Cursor and Codex
Listado em PyPI (MCP servers) (5)
-
hypermnesia-mcp io.github.cdeust/hypermnesia-mcp
Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Search Lacuna's ML research graph for papers, directions, authors, venues, and hypotheses.
-
Connect AI assistants to Outline for document search, reading, and management
Listado em npm registry (MCP servers) (5)
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
review-assist-mcp io.github.uditk2/review-assist-mcp
Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
-
mistral-mcp io.github.Swih/mistral-mcp
Mistral MCP server: extract invoices and documents from text, Markdown or OCR into typed JSON.
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Quer esta marca no seu plugin em nosso catálogo?
Prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS, e você poderá mostrar esta marca na ficha, com banners ao vivo para o seu site e o README. Como funciona a verificação
Você também recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Community GitHub marketplaces. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.