Open-source Python toolkit, MCP server, and agent skills for reproducible product and quantitative UX analytics on clickstream and event logs: multiscale interactive user-flow graphs, customer journeys and user flow analysis, behavioral segmentation, A/B tests, process mining, and Markov models
Device Detection and User-Agent parser for Python that detects the device, browser, operating system, and crawlers from the User-Agent and User-Agent Client Hints by reading a data file on your server. An alternative to UAParser.js, DeviceAtlas, and WURFL.
JupyterLab extension that gives the terminal, scripts, CLIs and AI agents on the Jupyter server the passkeys of the user's browser or operating system, moves secrets between the browser and local processes without printing them, and keeps a password vault that a passkey unlocks
Give your AI agent a memory — local-first and cloud-friendly, private, easy to install. Guided setup wizard; works out of the box on your own machine, no cloud required. For everyday agent users, homelabs, and developers alike · 99.2% LongMemEval-S retrieval @ k=8 · Works with Claude · Gemini · Antigravity · OpenCode · OpenClaw · Hermes · any MCP agent (native + one-command plugins) · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 deployment-ready · 100% local (fully offline) or cloud capable
Multi-user MCP management and lazy proxy gateway that makes MCP work like Skills: progressive capability discovery, on-demand server startup, and one stable gateway for every agent.
Local-first personal AI identity and memory for MCP-compatible coding tools — lessons, decisions, playbooks, and project context you can see, edit, and override.
Python framework for AI-ready, per-user micro-services — per-actor MCP servers, OAuth2, and peer-to-peer data sharing over the ActingWeb REST protocol.
Read-only MCP server for Trino: eight tools, writes refused on the SQL tree, queries as the verified user (token exchange or impersonation) or one named identity, bounded rows and time, one audit line per call.
On-device voice input: keep the user's voice, detect speech. No server, no key.
lyra: an MCP server that gives an agent a persistent, logged-in Chromium the user can watch and take over, with every site change, form send, upload and download asked first.
AI Intervention Agent: MCP server enabling real-time user intervention in AI-assisted development workflows.
Agent-first user-level Mihomo manager for shared Linux servers
Gmail for Google Antigravity (MCP server): official Gmail API, Google's tool names, sending only after the user's yes, no permanent deletion
MCP server that exposes the Qvasa user-access agentic API to Claude.
A memory layer for what is still true, what is due, and why it was stored.
Never worry about your AI agent breaking production again. Kill the process mid-flight — the wire transfer is still safely refunded, your database stays clean, and your users never lose trust. agent-saga is the 1-line bulletproof safety OS that turns unpredictable LLMs into crash-proof, enterprise-grade autonomous engines.
Let your AI agent fix the bugs your users hit. An MCP server that gives Claude Code, Codex and KAI (RAD Studio) the errors, slow operations, metrics and versions your apps report to ExeWatch, so they can find the cause in your code and fix it.
The User-Agent request header is a characteristic string that lets servers and network peers identify the application, operating system, vendor, and/or version of the requesting user agent.
The lakehouse as the signed-in user: Lakekeeper catalog browsing, dataset files and previews (shared by the JupyterLab explorer, the agent MCP server and the IDE extension).
AI-first CLI and MCP server for Telegram user accounts over MTProto, with plan-and-apply approval, chat allowlists and an audit log for every outgoing message.
Full-coverage MCP server for Gramps genealogy (Gramps Web API backend): CRUD for all object types, search, merge, timelines, relations, living status, DNA, media, import/export, reports, transactions, users, trees.
Multi-tenant hub server for awewarm: one box, many invited users.
MCP server and library: read/write files, run commands, list files — with strict prompts for user-provided LLMs.
Run synthetic focus groups using AI personas, with an MCP server for Claude Code / Cursor / Windsurf. CLI tool, Python library, any LLM.
MCP server for Discord-based AI agent-user communication. Enables AI agents to communicate with users through Discord.
MCP server for Roxels. Let AI agents control Roxels directly: set up end-to-end AI voice conversations — webhooks, data sources, app embeds, structured-result extraction — and define each conversation's goals. Use Roxels to onboard new customers to your product or gather insights from users by letting them speak or share their screen.
MCP server for safe AI agent runtime upgrades — user-driven regression detection (catalog + pre/post snapshot diff + rollback) AND provider-side regression detection (passive fingerprint of latency/response-shape/model-version drift across hosted Anthropic/OpenAI/etc. calls). Read-only advisor: never executes the upgrade itself; operator retains full agency.
MCP server that lets AI agents ask the user for input via Telegram or a GUI dialog and wait for the answer.
A Model Context Protocol (MCP) server giving AI assistants 78 tools to administer a Jira Cloud site: issues, users, groups, projects, permissions, custom fields, workflows, screens, filters, and bulk operations.
AI Intervention Agent: MCP server enabling real-time user intervention in AI-assisted development workflows.
MCP server that tests ads, prices, emails and sales pitches on simulated buyers and returns a go / iterate / no-go report.
Publish a platform's tools on the Liberrex MCP mesh (peer keys, per-call user identity, permissions), plus the Liberrex AI MCP server.
Klangk: multi-user Pi coding agent — server (klangkd) and client (klangk)
User access reviews for AI agents and MCP servers, with audit evidence and OSCAL output
Multi-user Gmail integration library and MCP server
Distributed, cost-denominated budget enforcement for MCP servers: per-user quotas, per-tool limits, and a global spend circuit breaker backed by atomic Redis counters.
Noeta's official product: a multi-user, server-side agent platform.
MCP server for the Tasklife API — manage tasks, comments, pages, projects, users, and teams from Claude, Hermes, Cursor, and any MCP-compatible agent.
AI agent memory layer (mem0-compatible) powered by Cursor SDK
MCP server for Monite's AI features - enables AI agents to access financial data automation and insights for Monite platform users.