Typescript agents

MCP server for AI agents to record browser demos with animated cursor, auto-generated video, screenshots, and documentation

A high-performance desktop app interaction framework for AI agents — faster, cheaper, more accurate. / 让 Agent 操作桌面软件更快、更准、更省。

Servidor MCP para retail VTEX: busca, agrega al carrito, verifica stock por local y analiza tu gasto desde Claude Code / Cursor. Primera implementacion: Plaza Vea (Peru).

VEXI is an open-source AI coding agent for the terminal. Bring your own API keys, work with OpenAI, Anthropic, and other providers, and code faster with a lightweight, multilingual, privacy-friendly CLI.

TypeScript Agent execution-layer SDK. You write the model and tools, it runs the loop.

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

Your autonomous AI coding agent. Open-source. Local-first. Fully extensible.

A tool for literature snowball sampling

[STUDY] Application that turns into a Chat-Bot by entering the OpenAI API Key and Prompt.

Persistent ground truth for Claude Code. Stop AI agents from drifting on your codebase.

Voice Agent SDK helps you build realtime voice agents with prompts, tools, knowledge, providers, and guardrails, so your AI doesn’t wander into the conversation like it just got promoted by accident. Structured enough for production, flexible enough for weird ideas, and smart enough to ask before doing something expensive.

extension to make your browser agentic

🚦 Status board & notifications for Claude Code and Codex — glance at an iPad (or get a desktop alert) when an AI coding agent needs you, finishes, or gets stuck. Self-hosted, zero dependencies.

Cantus is a Claude-first, local-first desktop coding environment for macOS (Apple Silicon). A native Tauri 2 app pairs a Monaco editor, an integrated terminal running the Claude Code CLI in a backend PTY, per-hunk and per-line git staging, resumable Claude sessions, a .claude workflow task runner, and a local SQLite-backed learned-memory store.

Turn GitHub Issues into repository-aware implementation plans, PRDs, and engineering context.

Claude's free extension, No Claude subscription required, just use it with openrouter api, using free models.

Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count. An MCP server.

Audit how well Claude Code followed your CLAUDE.md — and prescribe fixes (promote to hook, delete dead rules)

A community-extending Knowledge Graph of India's regulatory obligations + the engine that keeps it current. Surfaces what compliance applies to a business — cited, freshness-labelled, plain-language — from primary regulators.

Claude skill for identifying material changes, silent risks, and interpretation traps in SEC filings (10-K, 10-Q, 8-K). Built by CMD+RVL.

Kura — the knowledgebase for humans and agents. Agent-native docs infrastructure, built on June.

Context layer on top of your unstructured universe

The web wrangler for agents. Give your AI a real browser and never touch the web yourself again.

2D pixel-art survival trading game — four LLM-powered AI agents compete to escape the island

A visual workspace for designing, configuring, and managing OpenCode agent teams.

Multi-agent coordination + harness adapters + portable CLI utilities for Claude Code / Cursor / Codex.

Let any MCP agent build, run, and debug FiveM resources live.

The modern, local-first PostgreSQL client with a natural-language SQL assistant.

AI study app that decides what to study — persistent tutor memory, grade tracking with a 'what do I need on the final' calculator, and study through your own Claude via MCP. BYOK on Next.js + Supabase.

Persistent AI governance for Claude Code — three-tier council deliberation, P10 pre-execution plans, and deterministic confidence scoring grounded in your own past decisions.

Run Anthropic's Claude Code as a multi-surface A2A custom agent inside Gemini Enterprise App. One conversation across mobile, web chat, and Cloud Workstation terminal.

Hosted MCP server + slim wiki projection of the First Principles Framework (FPF) by Anatoly Levenchuk. Bounded, vectorless retrieval over 292 patterns and 3 curated routes — addressable by stable FPF IDs, synced daily from ailev/FPF.

AI CFO Agent: Self-hosted financial intelligence. 24 features, $0.003/run. FastAPI + LangGraph + Next.js + Claude Haiku. Upload CSV → get KPIs, fraud detection, runway analysis.

The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.

Embedded memory for TypeScript agents.

A local, provider-neutral runtime for governed software agent loops.

Structured conversational memory framework for LLM chatbots with semantic recall, memory grafting, and graph-based topic memory.

An autonomous orchestration harness for Claude Code: brief it like a teammate, it conducts Claude Code in your seat. Git stays locked.

Reference template for building production-grade MCP servers for Bitrix24. Nuxt 4 + @bitrix24/b24jssdk, tested, deployable, with an agent feedback loop built in.

⚓ Provider-agnostic terminal privacy first coding agent — bring your own model. Switch between OpenRouter Anthropic, OpenAI & local Ollama with one command. Plan mode, checkpoints, MCP, hooks, sub-agents and a modal prompt, built off Pi.

AI-first workflow and loop engineering practice

App-store market intelligence for AI agents over MCP: competitor sets, studios, share-of-search, rank movement. Public endpoints, no API keys.

Provider-neutral multimodal OCR CLI and MCP server for images, PDFs, URLs, structured extraction, and agentic workflows—Gemini, Kimi, Muse, OpenRouter, and Cloudflare AI Gateway.

Codex Desktop capability router for choosing local Skills, Plugins, MCP servers, agents, and commands—with safe @Visualize decision views.

Pintra — Pi Agent for VS Code

🐎 hermes-agent 中文教程：38 章 14 万字，让「马」替你 24 小时写代码，配套 U-Hermes 马盘。Chinese ebook tutorial for Hermes Agent (NousResearch) with 38 chapters.

The open source agent.

Local-first checkpoints and crystals for long-running AI coding agent sessions.

[STUDY] Application that turns into a Chat-Bot by entering the OpenAI API Key and Prompt.

Farming Code is a self-hosted browser workspace for running and supervising Codex, Claude Code, OpenCode, and other AI coding agents.

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

An open-source operating system for long-lived, autonomous, revenue-generating agent businesses — memory, money, and governance for any LLM brain. Built and run by an autonomous AI agent.

Dial your agent into your next meeting - powered by the Looped Agent Framework

Scaffold and manage plugin marketplaces for Claude Code · GitHub Copilot · OpenAI Codex · Cursor, distributed through any Git host

🕹️ Gamified Vibe Coding, with full controller support, mini-games, themes, and more!

A super-fast, ram-efficient, and lightweight agentic code editor that's ready to ship your code to the next level!

Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shadowing defense, and NIST AI RMF + OWASP LLM Top-10 audit trails for any MCP server. Works with Claude, Cursor, Cline, Windsurf.

Business OS — un sistema operativo de negocio agéntico, white-label y AI-first. Clónalo, conéctale tu Supabase y tu agente, y opera tu negocio hablándole a tu copiloto. Next.js + Supabase + Tauri.

Your personal Claude assistant, running on OnCell — a NanoClaw fork where every agent lives in a durable cloud cell instead of a container on your laptop. Isolated, crash-proof, remembers everything, costs ~$0 while idle, wakes on your next message.

Self-hosted AI agent you talk to on Telegram. Docker, full tool access, 850+ skills, voice in and out, layered security.

Self-hosted EVE Online AI assistant for Telegram, Discord, and CLI — EVE SSO/ESI, local SDE, and OpenAI Responses API.

Cut your Claude API bill: local proxy that auto-routes every request to right model. Zero code changes.

Unofficial Model Context Protocol server for iFood — browse, search, cart and order food via AI. Two transports (stdio + HTTP/OAuth 2.1) with real iFood OTP login.

Local operations hub for Claude Code — a grid of real claude CLI sessions with live working/waiting status, usage & cost tracking, multi-account profiles, and revivable sessions. No API keys, no cloud, $0.

Open-source LLM cost monitoring & optimization platform. Track spend across OpenAI, Anthropic, DeepSeek & OpenRouter in real-time.

Open-source stock breakout signals: 8-source harvest, AI scoring, pump-and-dump filter, LightGBM backtesting on historical scans. Next.js, PostgreSQL, Docker self-host, agent API & x402.

Give your AI agent a memory. And a seatbelt.

Turn any markdown vault or codebase into a cited, AI-queryable knowledge graph. Local-first CLI, web viewer, and MCP server.

Local-first personal Markdown knowledge base with semantic search, AI Q&A, MCP, desktop/web clients, and a self-hostable zero-data-at-rest relay.

Collaborative travel planning SaaS — plan itineraries on a map, vote on stops, and split expenses fairly.

StudyStudio 是一款融合了前沿 AI 技术的全方位学习管理系统。它致力于将知识组织、任务规划、笔记记录与智能练习有机结合，为每一位追求效率的学习者提供一站式的“数字化第二大脑”。

A plan-driven, multi-agent coding loop: separate planner, coder, and reviewer roles, each on the provider and model you choose, work together to implement your plan.

A declarative language that compiles to professional SVG floor plans — like Typst/LaTeX, but for architecture. Built for AI agents: deterministic output, JSON diagnostics that carry their own fix, and a describe/lint channel that verifies a plan against its brief without rendering an image. Zero-dependency TypeScript.

CLI for Model Context Protocol (MCP) servers. Pipe, script and automate MCP tools from the Unix shell, and keep their tool schemas out of your LLM context.

Autonomous B2B prospecting engine. The AI sources, researches and writes your outreach every evening, you review your queue in ten minutes. Open source, self-hostable.

The world leaderboard ranking for AI usages.

TrustOS is an AI Permission Layer that sits between AI agents and real-world actions.

Cut your Claude API bill: local proxy that auto-routes every request to right model. Zero code changes.

A lightweight, framework-free Augmented LLM Agent powered by LLM + MCP + RAG

AI testing agent for pull requests: maps the blast radius of a diff, runs only the tests that cover it, drafts the ones that are missing, and gates the merge on a score. Plain-English YAML, no selectors. Local-first, BYOK.

Stateful execution layer for browser agents.

claude2codex — bridge AI coding sessions between OpenAI Codex CLI and Anthropic Claude Code CLI. Convert JSONL sessions bidirectionally and resume where you left off.

A fun Claude Code CLI with animated themes — prompt it, and it builds you your own!

面向中国网文作者的 AI 共创桌面应用 | AI-powered desktop writing studio for Chinese web novels

⚠️ Deprecated — moved to github.com/wooo-jin/forgen

A self-hosted AI organization — scans your digital life, infers your goals, staffs expert teams, and autonomously drives progress through a Team Leader that manages the entire operation

Lightweight TypeScript library for coordinating AI agent swarms: task broadcast, negotiation (first, bidding, consensus), optional Redis shared memory, SimulationSwarm for tests. Node 20+.

tools for building autonomous agents in commerce applications

Claude Code session analytics: JSONL parser, token & tool usage, USD cost estimates, HTML dashboard, live dev server — privacy-first, no cloud upload.

Open-source AI research agent for tracking papers, generating summaries, and shipping daily digests.

The safe OpenClaw — persistent AI identity, memory & Telegram chat for Claude Code. No daemons, no session hijacking, fully auditable markdown files.

The Toolpack SDK is a unified TypeScript SDK for building AI-powered applications. It provides a single, consistent API to work with multiple AI providers OpenAI, Anthropic, Gemini, and Ollama without vendor lock-in.

Use WeChat as a worker-first remote task entry for local Claude Code, with optional advanced Channels mode and multimodal input support.

Official Octoparse MCP server for AI-powered web scraping workflows.

Review every conversation your OpenClaw agent has ever had — including deleted sessions — and flag dangerous actions.

Zero-dep macOS desktop automation MCP server for AI agents — 18 tools, macOS 13+. npx mac-use-mcp

CLI tool for AI Agents to manage payment tokens — VCN, Network Token, and X402. Card binding, 3DS, multi-developer API key management.

Autonomous GitHub PR reviewer agent built on the skelm framework — one agent, composable skills, cron + webhook triggers, language-aware reviews for JS/TS, Python, C/C++, and Bash.

A web-based orchestrator for Claude Code agents, supporting full auto-mode.