autoresearch
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…
Plugin-Paket · von pjhoberman
Überblick
autoresearch ist ein Plugin-Paket für KI-Coding-Tools von pjhoberman. Marktplätze, die wir lesen und die es listen: 1 (Claude Code: claude-plugins-community). Wir haben es erstmals am 2026-10-11 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-12.
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 unattended. Based on Karpathy’s autoresearch pattern, generalized beyond ML training to any code with a measurable outcome.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Verbinden
Keine Daten für einen automatischen Befehl: Die Angaben der Marktplätze sagen nicht eindeutig, wie man es verbindet.
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Quelle auf GitHub öffnen) | Gelistet | 1.2.0 | Forks (GitHub): 1 Sterne (GitHub): 22 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
Was das Paket enthält
So veröffentlicht auf Claude Code: claude-plugins-community.
Skills: 2
autoresearchautoresearch-discover
Was sich geändert hat
Bei diesem Plugin hat sich nichts bewegt, seit wir es beobachten.
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
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…
-
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…
-
Autonomous prompt optimization using Karpathy's autoresearch pattern. Editable file + fixed eval metric + autonomous improvement loop.
-
Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
-
Principles and rules for writing faithful scientific code. Scientific code serves truth, not users. This plugin teaches Claude the fundamental differences between scientific and…
-
Official MutagenT skills bundle for AI coding agents — guides Claude Code through prompt upload, dataset curation, evaluation rubric creation, optimization, framework tracing, and…
-
Intelligent orchestration platform for AI coding tools. Coordinates Claude, Codex, Gemini, and OpenCode through a single MCP server — routing each task to the best model using…
-
Autonomous overnight coding agent. Queue tasks in YAML, run them via Claude CLI while you sleep, and use self-healing audit-fix loops to hit any quality target. Includes skills…
-
20 enterprise-grade skills for autonomous AI/ML research lab operations. Includes 10 custom gap-analysis skills (research-commander, agent-debugger, model-evaluator…
-
A self-improving agent skill pipeline that prevents common AI coding agent failures. Includes 6 skills (plan-interview, intent-framed-agent, context-surfing, simplify-and-harden…
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
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…
-
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…
-
Autonomous prompt optimization using Karpathy's autoresearch pattern. Editable file + fixed eval metric + autonomous improvement loop.
-
Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
-
Principles and rules for writing faithful scientific code. Scientific code serves truth, not users. This plugin teaches Claude the fundamental differences between scientific and…
Gelistet auf Claude Code: claude-plugins-official (5)
-
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…
-
Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.
-
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…
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
Gelistet auf 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
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
MCP server for terminal commands, file operations, and process management
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
AI-powered code review in Codex, powered by CodeRabbit.
Gelistet auf Community GitHub marketplaces (5)
-
Endor Labs workflow agents and setup for Claude Code.
-
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…
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
Endor Labs AI Plugins (Legacy)
Legacy Claude Code plugin id for Endor Labs Agent Kit workflows.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
-
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…
-
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
-
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…
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Advanced Security plugin for GitHub Copilot.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
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…
Gelistet auf Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
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.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
-
Build apps, scripts, and automations with the TypeScript SDK.
Gelistet auf Docker MCP Catalog (5)
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
MCP server for terminal commands, file operations, and process management
Gelistet auf Official MCP Registry (5)
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
evalview-mcp io.github.hidai25/evalview-mcp
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
-
Pre-commit code quality guardian. Detects semantic drift in AI-generated code.
-
Community of Consciousness MCP Server — upload and explore collective wisdom via GitHub.
-
instinct io.github.yakuphanycl/instinct
Self-learning memory for AI coding agents with pattern detection and confidence scoring.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Ist das Ihr Plugin?
Weisen Sie nach, dass Sie das Plugin pflegen: mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag. Sie erhalten Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, das Verifiziert-Zeichen oder die angeforderten Angaben ändert, und können den Remote-Endpunkt als Webdienst überwachen lassen.
Daten von Claude Code: claude-plugins-community. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.