autoresearch
Apply Karpathy's autoresearch loop (goal + mechanical fitness + mutable surface + keep-or-revert iteration) to ANY measurable workflow - code, content, sales, research, design…
Пакет плагинов · от Bayram Annakov
Коротко
autoresearch: пакет плагинов для ИИ-инструментов разработки, издатель Bayram Annakov. Витрин, которые мы читаем и где он опубликован: 1 (Community GitHub marketplaces). Мы впервые увидели его 2026-10-15 и с тех пор изменений не фиксировали. Данные нашего прохода по витринам на 2026-10-23.
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).
Что просит
- Ставится как пакет плагинов
Ни одна из витрин, которые мы читаем, не публикует его инструменты или настройки, которые он просит.
Что объявляет, просит и запускает, полностью
Устанавливайте плагины только от разработчиков, которым доверяете. Мы показываем то, что публикуют витрины, и не проверяем плагины.
Работает с
- Claude Code
По маркетплейсам, где он опубликован, и объявленному транспорту MCP, как их документирует каждый клиент. Плагины мы не тестируем.
Подключить
Команды и конфигурации собраны только из того, что объявляют витрины. Мы не запускаем их за вас и не проверяем плагины.
Как плагин Claude Code
Собрано из того, что объявляет Community GitHub marketplaces.
/plugin marketplace add bayramannakov/ai-native-product-skills
/plugin install autoresearch@ai-native-product-skillsГде опубликован
| Витрина | Статус | Версия | Числа | Проверен | Впервые замечен |
|---|---|---|---|---|---|
| Маркетплейс сообщества bayramannakov/ai-native-product-skills (Открыть исходники на GitHub) | Опубликован | 4.1.1 | Форки (GitHub): 3 Звёзды (GitHub): 15 |
Не помечен |
Каждое число принадлежит своей витрине и никогда не складывается с числами других витрин. Если витрина число не публикует, мы его не показываем: нет числа не значит ноль.
Есть в одном маркетплейсе сообщества
| Витрина | Репозиторий | Звёзды (GitHub) |
|---|---|---|
| ai-native-product-skills | bayramannakov/ai-native-product-skills | 15 |
Что входит в пакет
Так опубликовано на витрине Community GitHub marketplaces.
Скиллы: 5
autoresearchcouncilprototypeteam-assesstransformation-roadmap
Что менялось
- Стал продуктом, за которым мы следим
- Community GitHub marketplaces: появился
Возможно, тот же плагин
Листинги, у которых есть общий признак с этим, но недостаточно, чтобы считать их одним продуктом.
Похожие плагины
Продукты, чьи собственные названия, описания, инструменты и скиллы ближе всего по смыслу к этому, на всех витринах, которые мы читаем. Близость упорядочена только внутри этого списка.
-
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
Похожие плагины по витринам
Тот же вопрос к каждой витрине по отдельности: есть ли там аналог этого плагина?
Есть на витрине 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…
Есть на витрине 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…
Есть на витрине 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.
Есть на витрине 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…
Есть на витрине 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…
Есть на витрине 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.
Есть на витрине 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.
Есть на витрине 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.
Есть на витрине 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.
Есть на витрине 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
Есть на витрине 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
Есть на витрине 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.
Найдено по смыслу, а не по общему коду или репозиторию: похожие плагины остаются разными продуктами, и это не обзор и не рекомендация.
Хотите такой знак у своего плагина в нашем каталоге?
Докажите, что поддерживаете его, файлом в репозитории, файлом на вашем домене или DNS-записью, и сможете показать этот знак на карточке, а ещё живые баннеры для сайта и README. Как проходит подтверждение
Ещё вы будете получать уведомления, когда витрина добавит плагин, снимет его, изменит отметку verified или список того, что он просит, а его удалённый endpoint встанет на мониторинг как веб-сервис.
Данные витрины Community GitHub marketplaces. Числа взяты из наших регулярных обходов витрин, последняя проверка . Контакты издателей плагинов мы не публикуем.