Autoresearch
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…
Пакет плагинов · от Frad LEE
Коротко
Autoresearch: пакет плагинов для ИИ-инструментов разработки, издатель Frad LEE. Витрин, которые мы читаем и где он опубликован: 1 (Community GitHub marketplaces). Последнее изменение мы зафиксировали 2026-10-20. Данные нашего прохода по витринам на 2026-10-24.
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 measurability, artifact, evaluator, bounds) before iterating: cheap sequential rounds that escalate to a parallel GAN tournament when they plateau
Что просит
- Ставится как пакет плагинов
- Хуков: 1
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 fradser/dotclaude
/plugin install autoresearch@frad-dotclaudeГде опубликован
| Витрина | Статус | Версия | Числа | Проверен | Впервые замечен |
|---|---|---|---|---|---|
| Маркетплейс сообщества fradser/dotclaude (Открыть исходники на GitHub) | Опубликован | 0.9.2 | Форки (GitHub): 51 Звёзды (GitHub): 596 |
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) |
|---|---|---|
| frad-dotclaude | fradser/dotclaude | 596 |
Как менялись числа
- 2026-10-2051
- 2026-10-2451
- 2026-10-20596
- 2026-10-24596
Каждая точка: день, когда мы прочитали другое число; ровные участки: дни, когда число не менялось. Числа разных витрин никогда не складываются.
Что входит в пакет
Так опубликовано на витрине Community GitHub marketplaces.
Команды: 3
cancelhelpstart
Хуки: 1
Stop
Что менялось
- Стал продуктом, за которым мы следим
- Community GitHub marketplaces: появился
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.
-
Apply Karpathy's autoresearch loop (goal + mechanical fitness + mutable surface + keep-or-revert iteration) to ANY measurable workflow - code, content, sales, research, design…
-
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 prompt optimization using Karpathy's autoresearch pattern. Editable file + fixed eval metric + autonomous improvement loop.
-
lazy-developer
Orchestrates autoresearch across a prioritized sequence of optimization goals — with configurable phase order and optional ralph-driven execution
-
Set up autonomous goal-driven optimization — creates a GOAL.md fitness function and runs an improvement loop
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
Reviewable ML research: literature, planning, methodology review, bounded runs, sweeps, implementation verification, ablations, retrospectives, Kaggle, and setup
-
Autonomous experiment loop — modify, test, keep/discard, repeat forever
-
Drop-in agentic loop skills (autoresearch, literature & writing, data, optimization, red-team, power analysis). Skills install namespaced as agent-loops:<name>.
-
Autonomous SKILL.md improvement via Karpathy autoresearch-inspired iterative eval hill-climbing with force iteration, NEUTRAL mutation judgment, mutation exclusions, L1/L2/L3 eval…
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 prompt optimization using Karpathy's autoresearch pattern. Editable file + fixed eval metric + autonomous improvement loop.
-
Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor…
-
Autonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…
-
Multi-agent deep research pipelines for Claude Code. Runs internet research, repository analysis, schema-driven structured research, and media research (via NotebookLM) using…
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…
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
-
Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams
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…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
Есть на витрине Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
Есть на витрине Community GitHub marketplaces (5)
-
Apply Karpathy's autoresearch loop (goal + mechanical fitness + mutable surface + keep-or-revert iteration) to ANY measurable workflow - code, content, sales, research, design…
-
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…
-
lazy-developer
Orchestrates autoresearch across a prioritized sequence of optimization goals — with configurable phase order and optional ralph-driven execution
-
Set up autonomous goal-driven optimization — creates a GOAL.md fitness function and runs an improvement loop
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
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…
-
Premium planning, thrifty implementation
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working automation scripts. Supports narrated…
Есть на витрине Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
Есть на витрине Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
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.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
Есть на витрине Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
Real-time web search, reasoning, and research through Perplexity's API
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Tools for interacting with Hugging Face models, datasets, research papers, and more.
Есть на витрине Official MCP Registry (5)
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
openpaper-mcp io.github.federicodeponte/openpaper-mcp
Autonomous research engine: auto research from a prompt to a fully-cited academic paper via MCP
-
forkmind io.github.Medhovarsh/forkmind
Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.
-
agentic-research io.github.TheAiSingularity/agentic-research
Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.
-
Create, launch, and analyze user research studies, AI interviews, and AI tests from your AI agent.
Есть на витрине PyPI (MCP servers) (5)
-
Search Lacuna's ML research graph for papers, directions, authors, venues, and hypotheses.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
hypermnesia-mcp io.github.cdeust/hypermnesia-mcp
Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
parallel com.mcparmory/parallel
Search the web, extract content, and run distributed tasks with AI-powered automation
Есть на витрине npm registry (MCP servers) (5)
-
review-assist-mcp io.github.uditk2/review-assist-mcp
Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.
-
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
-
google-surf-mcp io.github.HarimxChoi/google-surf-mcp
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
-
gitmem io.github.gitmem-dev/gitmem
Persistent institutional memory for AI coding agents. Memory that compounds.
-
Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
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.