Typescript agents

Production blueprint for building SaaS with Claude: prompts, theme system templates, and the workflow that prevents looping. Distilled from a 3-month real-world build.

Football chat bot build with NestJS framework

LeetCodeGPT is a Chrome extension that integrates GPT (Generative Pre-trained Transformer) into LeetCode.

Библиотека - готовый каркас для голосового/текстового чата с OpenAI Realtime (WebRTC + DataChannel) в React Native.

A sophisticated AI-powered voice assistant that handles incoming phone calls and provides a web-based chat interface. Built with TypeScript, Fastify, and OpenAI's Realtime API, this system integrates with Twilio for telephony services and includes advanced features like memory management, calendar integration, and webhook-based data processing.

A demo of OpenAI o1 and Next.js, used to automate the import of user-provided contacts file.

A sophisticated Node.js application that analyzes YouTube videos for legal compliance. It transcribes the audio content of the videos using the Deepgram API and then compares it against predefined legal rules using the GPT-4 language model.

Exploring research papers has never been easier!

A minimal and cutting-edge AI project template for validating business ideas

AI models all in one!

Using KAG and RAG Approaches to Enhance an AI-Powered Cryptocurrency Trading Agent

An app that shows you how to build a conversation search experience, using Typesense's built-in RAG pipeline

Production-ready TypeScript SDK for MCP servers: auth, multi-tenant, observability. Build enterprise AI agents fast.

The sourcemap of claude code, the best coding agent of the world

Run `npm i -g socrate` to install a discussion room for using GPT personalities with internal monologues to debate problems. Provide a problem to start, or customize the settings of the debate room. Custom agents incoming!

Ollama function calling demo

PULSE Framework: CLI (pulse) + MCP Server (pulse_*) for controlled agentic development. Features 30-min rule, 5 safeguards, loop detection, Git checkpoints, and escalation workflows.

This project has been created to make AI accessible and easy for everyone. Whether you are a beginner with no prior experience or an experienced developer, this starter kit is designed to help you incorporate AI into your apps quickly and easily.

On-chain economy stack for autonomous AI agents — ERC-8004 identity, ERC-8128 signing, X402 payments, XMTP messaging

Local-first control plane for running Claude agents in real Telegram and WhatsApp chats

HTTP/HTTPS proxy with real-time monitoring for Agent traffic. Designed for debugging and monitoring Claude Code, Anthropic API calls, and other AI agent communications.

MCP server that lets AI agents execute code instead of calling tools directly.

An AI personal assistant done the right way.

Real-time Google Search API for AI Agents & RAG pipelines. Get structured SERP data instantly using remote browsers.

My personal website and blog.

Multi-agent AI orchestration framework

Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts

Advanced graph-based code analysis for AI-assisted software development

Multi-platform Agent Skill aggregation and archive (skills.sh + SkillsMP + ClawHub)

Multi-agent swarm framework. Seven autonomous agents. 30 skills. One shared mesh. Zero infrastructure.

Desktop Git diff reviewer with inline commenting for AI coding agent workflows

A lightweight tool that simplifies switching between different oh-my-opencode configurations with ease.

Cloudflare-native AI agent — 13 tools, codemode, 5-layer memory, self-learning, multimodal I/O. Telegram, Discord & WhatsApp bots. Web search, image gen, TTS, document RAG, calendar, task delegation. 100% serverless on Workers + Durable Objects.

Enhanced statusline for Claude Code — see your 7d/30d spend at a glance

AI superpowers you own. Sila is an open alternative to ChatGPT where you own AI assistants, chats and data.

Refactored fork of the sourcemap-leaked Claude Code CLI

The coding agent you can walk away from. Text it a voice note from your phone and it builds while you are out; a second AI reviews every job before you see it. Desktop app for Mac and Windows, on the AI plan you already pay for.

🪄 Ordine: reliable orchestration for autonomous multi-agent systems.

Browser-native agent · profiles · tools — by aratech | Zero installs, isolated, secured and self-evolving agent.

Open-source AI design studio. Multi-variant canvas, inspect & edit in code. Powered by Claude / GPT. 本地优先的 AI 设计工作台。

Ultimate Telegram Bot API MCP server — full v9.6 coverage, meta-mode, rate limiting, circuit breaker. TypeScript.

🇬🇧🏦 MCP server for UK Companies House API - Search companies, retrieve detailed information, filing history, officers, and charges data through the Model Context Protocol

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.

The transparent, composable harness for TypeScript agents. The same code runs the full agent loop on a local 4B model or a frontier API, with tool-call healing, verification, and a signed evidence receipt for every run.

Run multiple Claude Code, Codex and Gemini subscriptions side by side — shared skills/agents/memory, isolated logins, live 5h/7d limits in one view

Terminal UI toolkit inspired by Claude Code — 25+ React components for building rich CLIs, AI agents, and dashboards

Your personal AI team that gets things done. Shared memory. Any model. Local or cloud. Run. Rest. Dream. 🐨

A browser extension that allows you to highlight, tag, annotate, and export the best parts of your favorite YouTube videos and summarize these snips with the power of AI. Winner of Boost Hacks

Self-adapting, Tool-enabled, Extensible, Multi-agent System

Open-source GUI for Claude Code, Codex, and GitHub Copilot CLI. Run coding agents in one workspace with live sessions, code diffs, and a shared browser.

Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-ready.

Tandem lets you connect and control any coding agent—including Claude, Codex, or Hermes—across different devices. It allows all your agents to coordinate with each other seamlessly, whether you're working from a browser, a terminal, or any other client.

Herdr and tmux sibling AI sessions: pi, Claude Code, Codex, Copilot, OMP and Antigravity can message and spawn each other while keeping their own auth, tools and transcripts.

Open & nano reimplementation of Sakana Fugu. A repo-native, multi-agent coding loop powered by 9+ LLMs (isolated via Claude Code) and an independent Codex reviewer. Lightweight, bounded, and self-improving (Self-Harness)—no coordinator training required.

A persistent cognitive workspace that manages information flow for knowledge workers

Unofficial mobile PWA for Hermes Agent — installs as a plugin in your Hermes Dashboard (web UI) and adds a Mobile tab. Chat, approve actions, and watch your agent from your phone.

纯本地 AI 编程桌面工具 · 由 DeepSeek 驱动 · 一个 API Key 即用

Open-source local agent runtime for CTRL NODE — the CLI bridge that pairs your machine with Claude Code, Copilot, Gemini, Cursor and more, and executes tasks from the CTRL NODE dashboard.

Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

Mission control for every Claude Code session on your machine.

Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.

AI diagram generator for software architecture - the open-source Eraser.io alternative. Describe your system in plain English, get editable system design, sequence, ERD & cloud diagrams on an Excalidraw canvas. Self-hostable, bring your own key. Vibe diagramming for engineers.

Consort keeps AI-written code clean and correct: a coordinated ensemble of role agents, spec-first and test-driven, driven by a deterministic state machine against live branches of a real Lakebase database. Engineering discipline is no longer left to the whim of a model. Consort enforces it.

You're the boss. Claude and Copilot are your employees. Give them desks, assign them work, and watch them build — in a pixel-art office.

Native OpenCoven workspace for familiars, agent sessions, memory, tools, workflows, and local-first development.

对Godot开发游戏适配的Agent客户端，基于Pi开发。The Agent client for adapting games developed with Godot, based on Pi

Terminal coding agent with browser UI, MCP, Obsidian memory, and live office floor. Any model via OpenRouter. MIT.

A multi-agent platform for transforming enterprises into AI-ready organizations — built on Amazon Bedrock AgentCore, powered by AWS.

AI-powered Obsidian plugin for semantic search, vault auditing, note discovery and AI writing

The desktop home for your coding agent — Claude Code or Codex. A persistent chat, a real browser it drives on your own logins, your phone in the loop, and routines on a schedule. Local, on your own subscription, open source. macOS.

AI-powered SRE agent built on Claude Code channels. Receives SigNoz alerts via webhook, investigates autonomously using kubectl and traces, auto-fixes safe issues (pod restarts, workflow clears), and escalates to the CTO on Slack with full context. Sub-agent delegation pattern keeps the main session alive for days. Incident memory via SQLite.

Karpathy's LLM Wiki pattern as a minimal, agent-agnostic skill

An agentic browser extension: an AI side panel in your own logged-in Chrome, Edge, Arc, Brave or even Firefox run by the agent you already use (Claude Code, Codex, Antigravity). Free, open source, no API key. Also an MCP server.

A desktop workspace for coding agents: browse local session history, chat with agents live, and orchestrate multi-agent threads.

AI-powered Obsidian plugin for semantic search, vault auditing, note discovery and AI writing

An intelligent AI agent system powered by LLM, designed to be a proactive personal assistant.

Self-hosted AI agent platform — chat with any OpenAI-compatible LLM in Chat, Agent, and read-only Plan modes; 58 tools across files, shell, web search, headless browser, Git, and MCP servers, sandboxed to a chosen workspace. React 18 + Vite SPA, Fastify 5 API, Prisma 6 on SQLite (MySQL/PostgreSQL optional).

Agentic chatbot with streaming UI — built on Astryx (React + StyleX design system) with a workspace explorer sidebar; Express backend talks to MiniMax via its OpenAI-compatible Chat Completions API. React 19 + Vite SPA, Express, PostgreSQL 16 + pgvector, MCP-compatible.

MCP server, REST API and typed SDKs for short links. Per-user ownership, bundle analytics. Self-hosted on Cloudflare Workers, free tier.

Multi-agent orchestration for AI coding assistants

Curated Remotion video templates for Claude Code and AI coding agents - captions, visualizers, effects, transitions

Template for building a chatbot using TypeScript and Next.js, powered by the Hugging Face API

An open-source template to get your own chatbots up and ready in under 2 minutes. Authentication and Stripe fully integrated.

A MERN stack app that leverages the power of React to craft stunning UI/UX on the front end, while seamlessly integrating OpenAI's API to enhance the backend functionality.

A starter template to write Fastify APIs for OpenAI GPTs with auth, billing and OpenAPI spec generation.

Generate unique and creative project names in seconds with AI!

Spinup your own LLM powered chat agents for solana actions

Sample dockerized NestJs framework service integration with New Relic Node.js Agent showing how to instrument the app in order to use all the Agent’s features (like Service Maps or Distributed Tracing)

Secure-by-default OpenClaw on Ubuntu, with a verifiable security report

OpenSource Version Of Claude Code (mirrored)

LLM QA, Observability, Evaluation and User Feedback

🛠️ This dashboard allows you to configure & customize my own Discord bot "Clank" without needing to use Discord directly.

A mobile application enabling bank customers to be more climate conscious while strengthening their loyalty to the bank.

A semantic code search tool for intelligent, cross-repo context retrieval.

Storybook GPT is a web application for generating Storybook stories from React components using OpenAI API

A pragmatic approach to continuously vectorize your PostgreSQL tables with the flexibility of your own embedding pipelines.

Vitest for AI agents. Scenario-based testing with simulated users, tool-call mocks, and LLM-as-judge evaluation. Lives in your project like Playwright.

A lightweight, embeddable agent runtime with built-in FSM state machine, SQLite persistence, and tool execution. Designed for bots, CLIs, and any channel that needs autonomous agent behavior.

NextJS,React,Lama,VAPI,Twillio,Retell,Telegram,Sales

Zippy Talking Avatar uses Azure Cognitive Services and OpenAI API to generate text and speech. It is built with Next.js and Tailwind CSS. This avatar responds to user input by generating both text and speech, offering a dynamic and immersive user experience