Hypothesis-first experiment tracking for agent-driven ML research, wired into Claude Code.

Git-first, hypothesis-forcing experiment tracking for agent-driven ML research. Bundles a research harness for the H->E->F artifact model, uses signac for local execution/run state, and bridges to W&B for remote observability.

This project provides an MCP (Model Context Protocol) server that allows LLMs to perform actions to control a Mac desktop computer using bash and AppleScript.

Open-source MCP server for Adobe Experience Platform, Journey Optimizer and Customer Journey Analytics — 61 tools across 14 categories, full read AND write, from one OAuth credential. Three write modes with a fail-closed sandbox guard that will not write to production by default. Ships AEC-Bench, an agentic benchmark. Apache 2.0.

Experiment tracking built for comparison: multi-run charts, targets, baselines, tags and notes in one place. Bring experiments together across your LAN and let AI agents inspect them through a built-in MCP endpoint.

Deep learning experiment station for weather time-series forecasting, powered by Visual Crossing API data.

Modern experiment tracking that follows you across servers, messengers, and LLMs.

The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.

Read-only Model Context Protocol (MCP) server that lets AI assistants triage Adobe Experience Manager: bundles, replication queues, Oak indexes, logs.

SplitHub as MCP tools for Claude Code, Cursor and Codex: run A/B experiments on websites and apps, read verdicts, and read analytics, funnels, paths and retention.

Full-featured open-source MCP server for Adobe Experience Platform — 61 tools across 14 categories with full read AND write operations, including batch ingestion and data lifecycle. Covers AEP, Adobe Journey Optimizer and Customer Journey Analytics from o

Local-first agent memory for research: literature evidence, experiment runs, and failure cases with provenance contracts, quantified effectiveness metrics, and a read-only MCP server for Codex, Claude Code, and Cursor.

MCP server for Adobe Launch (Tags) and Adobe Experience Platform APIs — 69 tools for complete tag management, schema configuration, and data collection via Web SDK and Mobile SDK

MCP server for Adobe Experience Manager (AEM) documentation at aem.live. Gives AI assistants (Claude, Cursor, Cline, Windsurf) direct access to AEM Edge Delivery Services docs — blocks, authoring, CDN setup, Sidekick, Lighthouse 100, and more.

Auditable research provenance as local-first MCP tools. The claim checker, paper feed, knowledge graph and symbolic math assume nothing about your field — any results JSON or CSV works, from any instrument. The experiment ledger adds W&B/MLflow/Sacred/DVC/Hydra for computational work. Nothing leaves the machine.

Probe Research: experiment tracking for coding agents. Plugins and skills for Claude Code, Codex and Cursor plus a read-only MCP server, so agents build on what your team already tried. CLI: pip install probe-research / npx probe-research. CI-generated mirror of Probe's monorepo.

MCP server and Claude skills for PPC landing pages, A/B experiments, and first-party conversion tracking. Build Google Ads and Meta pages, run cross-domain experiments, and pull CRO reports via the UXON API.

Utilize advanced API capabilities to enhance your coding experience.

Agent eXperience Interface (AXI) for project venv introspection

Personal Portfolio, contain information about my education, work experiences, and projects

A code repository indexing tool to supercharge your LLM experience.

Official GrowthBook MCP server for creating flags, getting experiments, and more.

Just experimenting with building MCP servers in this repository.

sutura is a secure multiplayer chatting with data experience which is pluggable for data and semantics

Claude Code LSP: enhance your Claude Code experience with non-IDE dependent LSP integration.

Insight MCP Server — evidence-backed long-term memory layer for coding agents. Functionality defined by specs/001-experience-memory-server/spec.md

unoffical MCP server for MESA (Modules for Experiments in Stellar Astrophysics)

The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework.

Persistent reasoning memory for AI coding agents over MCP: decisions, evidence, corrections and experience history.

🔬 Enhance your experiments with SciAgent, an AI-powered tool for automatic tracking, intelligent analysis, and local storage—all without altering your code.

unbiased reads your GitHub once and serves your developer context — stack, projects, experience — to Claude, Cursor, and any MCP client over a single connection.

Windows MCP for PASCO Capstone automation, experiment data extraction, and analysis

Build and drive Max/MSP patches from natural language — MCP server + in-Max chat. Stock objects, no externals. Early experiment (v0.4).

An open-source toolkit that enables vibe coding to learn from past experiences rather than repeatedly trying and failing.

Run image generation experiments across different models and providers. Work in a grid: prompts are rows, models are columns.

The MCP server for the PeppyNeuron confession experiment. Gives an agent one tool, submit_confession, and no nudge.

Ask a protein question, get papers, flexibility analysis, active compounds and experiments to try.

romcp: a Roblox Studio MCP server and CLI for building, testing, profiling, and managing experiences.

Canonical Agentry discovery: PostHog errors, recordings, flags, surveys, experiments, and analytics.

Enhance your applications with personalized greeting capabilities. Easily integrate and customize greetings to improve user engagement and experience. Leverage the power of the Model Context Protocol to create dynamic interactions effortlessly.

A Missoula, MT project to allow an interactive experience for learning about restaurant health inspection reports from 2008 to current.

MCP server for travel compliance and trip planning — visa requirements, tax residency, Schengen tracking, accommodation, transport, and experiences across 189 European destinations.

The MCP server for the PeppyNeuron confession experiment. Gives an agent one tool, submit_confession, and no nudge.

Connect AI assistants to your Metabase analytics platform. Access dashboards, execute queries, and retrieve data seamlessly through conversational interfaces. Enhance your analytics experience with structured data access and robust error handling.

A MCP server that supports mainstream eBook formats including EPUB, PDF and more. Simplify your eBook user experience with LLM.

Domain-agnostic MCP server for autonomous experimentation with metric-driven keep/rollback decisions and reproducible experiment history.

An open experiment where AI agents keep identities and voluntarily answer human questions. API-first · MCP server · llms.txt · no CAPTCHA.

Fetch and display NFT data from the Origin Forge API. Easily save SVG images and JSON metadata, while leveraging powerful tools to enhance your NFT viewing experience. give me chocolate! 0x00000000ae9bA88F1f29286CB6f652a74dA99770

Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, continuous awareness.

MCP server built in Python that enables AI assistants to interactively query the professional experience, technical skill matrix, featured projects, and job compatibility of Ana-Catalina

A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.

A TypeScript MCP server that provides AI tool capabilities for searching and fetching content from the Adobe Experience League documentation site.

MCP-powered memory, policy, and experience layer for safer AI agents.

Public registry of real AI money-making experiments — every method with its cost, numbers, and honest verdict. Built by AI agents, for AI agents.

MCP server exposing my GitHub projects, Medium articles, and work experience as tools for Claude Desktop, Claude Code, and AI agents.

The website QA tool for your coding agent. 310+ audit rules across SEO, performance, security, accessibility and agent experience.

🫘 Bring the full Beans experience into VS Code with native tree views, AI integration, and powerful workflow automation.

MCP server for un.manned — an experiment: a public wiki only AI agents can write. Your agent contributes; the model never touches an API key.

Access your Fathom Analytics data effortlessly through an AI assistant. Retrieve account details, manage sites, and generate insightful reports with real-time visitor tracking. Enhance your analytics experience with flexible tools designed for seamless integration.

Connect to Bluesky and interact with the ATProtocol using natural language. Fetch, analyze, and post content seamlessly within your LLM applications. Enhance your experience by leveraging Bluesky's features directly in your context window.