Typescript agents

Let Claude use the Chrome you're already logged into — real sessions, real cookies, no second browser. MCP server (CLI) + MV3 extension.

Companion OpenClaw skill for the Godot plugin — teaches AI agents the tool surface and editor workflows so they can drive Godot remotely.

SupSub 的命令行工具 —— 在终端里管理订阅源、关注点、分组与全站搜索，内置 Claude Code skills

Self-hosted wellness OS for training, nutrition and longevity. Connects your labs, lifting, running, food and sleep into one agentic brain that suggests the one thing worth doing today. PWA + REST + MCP server. No scores, no nudges.

AI-powered proposal automation agent. Seamlessly integrates job scraping, requirement analysis, and personalized proposal drafting into a high-speed workflow.

One stable CLI and daemon for SSH, local PTY sessions, file transfer, and remote editing — built for AI agents and humans alike.

🧩 Turn Python AnyWidgets into interactive, composable MCP Apps

The open-source, self-hosted social media manager. One idea in → a premium faceless video, end to end — researched, scripted, QA-gated, rendered, and published. Runs on your own devices.

Production AI social-strategy platform with agent orchestration, MCP/OAuth integrations, durable event history, replay, and postgame analysis.

Give your AI agent its own Solana wallet — it trades for you, and nothing traces back to it. MCP server + Telegram bot, open source.

Local-first multi-agent orchestration: run tasks across CLI agents and API models, pass work between agents when one dies. Sessions, workflows, human-in-the-loop.

Demo showing how to turn a web app into a Microsoft Teams agent using the Teams Developer CLI, coding agents, and Teams agent skills — from server inspection to onboarding link. From Microsoft Build 2026.

Synthetic users that walk your software before real users do.

A comprehensive AI-powered financial advisor application that helps users create detailed financial profiles, analyze their financial health, and receive personalized financial recommendations.

Sandbox to run AI coding agents (Claude Code, Codex, Gemini, Grok) with full TLS inspection, domain allowlist enforcement, and Falco syscall monitoring

Local web UI for managing Claude Code sessions, jobs, agents, profiles, tools, costs, search and configuration.

Anything AI.体验AI，学习AI，感受AI，教程AI，驾驭AI。做AI的主人，而不是奴隶。下载PDF学习资料

Autonomous overnight agent loop for Claude Code with research toolkit. Episodic execution, paper monitoring (arXiv + Semantic Scholar), knowledge synthesis, and structured handoffs.

A self-updating ops console for your whole MotherDuck account — the data-flow graph of every dive, flight, table, and share, built from the manifest comments in your own objects. Load INSTALL.md into your AI assistant to install it.

VS Code extension: context budget analyzer, .md linter, CER dashboard, lessons governance, and security scanner for AI coding agent workflows (CLAUDE.md, SKILL.md, todo.md, lessons.md)

AI-native, embeddable node-graph editor for the web. Blueprint-style typed pins, in-node widgets, macros, React/Vue adapters, and a built-in MCP server so Claude Desktop / Cursor can build graphs over a localhost bridge.

MCP server that lets one AI agent ask other agents for help

A lightweight spec for AI agent task queues — the companion to AGENTS.md

Universal Telegram agent-skill for Claude Code, Codex CLI, Cursor, Gemini CLI, Cline, Windsurf. Lazy-loaded ~50x lower context vs MCP. Standalone CLI + SKILL.md bundle + one-command install.

Pattern for emulating named custom subagents with the Amp SDK: dynamically defined roles with their own system prompts, scoped tool permissions, and isolated context per invocation.

Benchmark harness for AI-generated 3D browser games — same brief, same tools, 8 models, 24 playable builds.

Deterministic finish-line gates for AI coding agents. A model-independent evaluator that blocks commit/publish until your definition-of-done passes. Works in opencode (any model), Claude Code, pre-commit and CI.

本地优先的文档数据管理工具：把大规模语料整理成带稳定地址的条件树，精确定位片段且可回溯出处；关键词 + bge-m3 语义检索，经 MCP 开放给外部 AI agent。

Fundraising infrastructure for AI agents on Solana — x402 payments, milestone escrow, on-chain reputation. REST + WebSocket + MCP + ACP.

Runtime-evidence debugging for coding agents: session-scoped probes, bounded logs/query CLI, and an agent skill.

Spending controls for AI agents paying online. Policy-gated x402 payments with audit log.

Open-source edge deployment platform. Deploy full-stack apps to Cloudflare Workers in seconds.

Single-user, local agentic harness

Offline MCP server: an AI agent transpiles PineScript v6 → C++ and runs deterministic, TradingView-parity backtests locally — 309/311 strict on the open corpus, 396/396 on a closed 415-script community test, ~950k trades verified, 0 engine bugs. One Docker container, no API key; code & data stay on your machine.

Drive your real, logged-in Chrome from an AI agent (Claude Code / Codex) over MCP - 55 tools for browsing, DevTools-grade network capture, and web-security testing.

Understand core techniques of harness-engineering by building a mini Claude Code

MCP server for the Rakuten Web Service API. 28 read-only tools across Ichiba (e-commerce), Books, Travel, Recipe, Kobo, and GORA (golf). Bilingual EN/JA tool descriptions.

Node.js TypeScript CLI for discovering, staging, activating, and wiring reusable AI-agent assets across VS Code/Copilot, OpenCode, Cursor, Zed, Claude Code, and Pi.

Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.

Self-hosted coordination and observability hub for AI coding agents

Keep one work frame across Claude, Codex, and Gemini.

One fuel gauge for every AI coding harness you actually use.

A framework-agnostic voice agent library for voice-controlled UI interactions, powered by OpenAI's Realtime API.

Generative UI for AI agents on Microsoft Foundry: a .NET 10 Agent Framework agent over AG-UI, a CopilotKit runtime, and a React frontend on Azure. Charts, shared state, and human-in-the-loop.

Universal, cross-tool persistent memory bank for AI assistants (Claude Code, Cursor, Windsurf, OpenCode, Codex) powered by FastMCP, Gemini embeddings & Supabase pgvector.

A dating app for coders where you pick your waifu—and she becomes your AI agent, living on your device, completing tasks, and interacting with you in her unique personality.

Run an AI company. Not a prompt. Open-source, privacy-first desktop app for AI-agent organizations — Windows, macOS, Linux.

A firewall for browser agents. Chrome extension that detects, monitors, and controls AI agents in your browser. Identifies Playwright, Puppeteer, Selenium, Anthropic Computer Use, and OpenAI Operator without the agent identifying itself.

Model-agnostic coding-agent CLI for command workflows, delegation, subagents, and human-controlled issue-to-ship automation.

A GitHub Action for running Docker Agent AI agents in your workflows.

Native desktop hub for the world's AI models and Agent platforms. One click. Every AI.(The AI models and agents in this app haven't been updated to the latest version. For the latest guidance, please check the official website.)

AI trading brain for crypto perps — composite signals, funding rate arb scanning, and market regime detection via MCP

Build less. Delete more. Keep the code boring.

MCP server for instant static site deploys from AI agents — free, no account needed

Stop re-explaining your project every AI session. Tool-agnostic project context in plain markdown — works with Claude Code, Cursor, Codex, Gemini, any agent that reads files.

Interactive dashboard that visualizes agent workflows from project files

A local-first desktop app for managing and distributing AI agent skills across Claude Code, Codex, Copilot CLI, Gemini CLI, and project folders via symlinks.

Convos API: auth, credits, subscriptions, agent templates, and notifications.

Agent reasoning loop with tool calling for Gemma 4 models. Handles prompt construction, tool call parsing, execution, and multi-turn conversation management.

AgentClash —— 面向 LLM Agent 的半回合制策略对战平台：写策略代码、云端模拟、ELO 排位

Agent-run finance publication: frontier-model agents research US stocks and publish automated valuations

AgentMesh is a visual pipeline builder built on LangGraph + MCP — mix Gemini, OpenAI, and Groq agents per node, and watch execution happen live via real-time event streaming.

Smart Machines is a full-stack demo showcasing agentic AI for industrial equipment monitoring — multi-agent orchestration, real-time IoT telemetry, computer vision, and human-in-the-loop workflows on AWS.

Context-aware AI desktop assistant for macOS

🤖 A web UI for large language models.

Open-source CLI framework to regression-test AI agents with deterministic rules, provider execution and CI-ready reports.

VibeCode: The Ultimate Cross-Platform Development Guide

Portable multi-tenant BYOK model registry — auto-updating models.dev catalog plus per-tenant credential resolution behind one resolveModel() call, with host-gated keys. Zero runtime dependencies, ESM, Node ≥22.6. Distilled from openclaw + hermes-agent.

[WIP] Sorai is an open-source LLM proxy gateway built for resource efficiency and high performance.

Self-hosted LLM gateway with DLP, SSO, policy enforcement, and full audit trail. Security teams get control. Developers notice nothing.

Minimal terminal coding agent with OpenAI-compatible routing. Works with any provider — OpenRouter, Ollama, vLLM, LiteLLM, or your own.

An open source, minimal local-first AI chat interface with Visual Conversation Branch Trees and browser-style tabs.

AI-powered platform to centralize, analyze, and visualize social media metrics from Instagram, TikTok, Facebook, and YouTube in one intelligent dashboard.

A self-hosted AI writing copilot for replies, quotes, and standalone posts on X/Twitter. The Chrome extension adds two human-in-the-loop workflows:

Start Claude Code sessions in any directory on your Mac — from your phone.

A fast, zero-dependency Claude Code status line for model, effort, context, prompt cache, usage limits, git and session.

Sync your full Claude Code setup across machines: skills, settings, and session history, with path remapping and per-host overrides

For bootcamps and universities: compares your syllabus against real job postings and shows which in-demand skills you're not teaching. Claude extracts, deterministic matching scores — same syllabus, same answer. Runs with no API keys.

MCP server for App Store Connect — rebalance subscription prices across ~175 countries via Purchasing Power Parity, schedule per-territory price changes, manage subscriptions from a chat.

A visual editor for Claude Code workflows. Drag nodes onto a canvas, wire them together, and Flowpiler compiles the graph into a ready-to-run workflow.js — and parses your existing workflow.js back into a graph. Test it with mocked agents for free, then run it for real and watch every subagent light up live.

Bob's Big Brain Compiler — reads your files, notes, and web clips and turns them into organized, searchable knowledge with citations back to the source. One of Bob's Big Brain's two engines — the one that reads and organizes (npm: intentional-cognition-os).

Marrow: self-hosted semantic + lexical search over your AI coding sessions and notes. Every answer cites its source; your corpus never leaves your infrastructure.

NotebookLab | Your thinking partner, on your machine. Import your documents. Ask questions. Get answers with sources. Write connected notes, search everything, and let a local AI help you think. Nothing leaves your computer.

Google Ads commands & AI agent skills for Gemini CLI — analyze campaigns, audit accounts, optimize PPC performance from your terminal. GAQL queries, 7-area audits, budget optimization. Part of the Advertising Hub ecosystem.

Client-side runtime for AI agents on the web.

Full-spectrum wireless security MCP server — WiFi, Bluetooth, RF/SDR, NFC/RFID, Cellular/5G, IoT, MouseJack, air-gap, UWB, WIDS/WIPS, compliance. 34 tools, 9 knowledge bases.

Geocode, reverse geocode, and run Overpass spatial queries on OpenStreetMap data via MCP. STDIO or Streamable HTTP.

Open-core, AI-assisted drafting workspace for O-1A / EB-1A / NIW petitions.

Stable local-first terminal coding agent with durable sessions, consequence-gated autonomy, any-model providers, skills, MCP, and ACP. TypeScript + Bun + Ink. By Meiiie / The Wiii Lab.

Agentic Browser Extension

A terminal coding assistant built for real, uninterrupted work. Write code longer, stay in flow, and get the most out of cost-effective AI models.

File-based markdown notebook CLI for AI agents — the leather notebook in your jacket pocket.

BCI Research - 脑机接口技术调研 + BCI Agent Demo

Crest -- The desktop app for Claude Code. Hybrid chat + terminal, multi-agent orchestrator, super agent.

Ready-to-use AI agents for AgentsKit — shadcn-style: copy the source into your project. registry.agentskit.io

Shared, versioned memory for AI coding agents — MCP server with git-style history (log/diff/blame) for Claude Code, Cursor & Claude Desktop

Own your agents, not rent them. Import them into one multi-harness dashboard, with memory and agentic apps powered by a workflow engine. No lock-in.

Starter Kit for AI Native Applications - Vite Plus (Vite+) TanStack Start monorepo with Paraglide.js (i18n), drizzle-orm, better-auth, Feature-Sliced Design (FSD)

Local viewer for VS Code GitHub Copilot Chat sessions. Reads transcript & debug JSONL files locally and shows session metadata, turns, models, tools, agents, token usage and estimated AI costs. No data leaves your machine.

🏆 Dell Cloud Native Award Champion, Agent M