Typescript agents

Just code, nothing else. A community VS Code chat extension on the Claude Agent SDK

Pier Code is a terminal-native agentic coding tool that understands your codebase and helps you move faster by handling routine tasks, explaining complex code, and managing git workflows through simple natural language commands.

Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.

Mythos-class autonomous vulnerability discovery from any strong coding model (Opus 4.7, GPT-5.5, DeepSeek V4, Gemini). Long-running, email-driven, self-distills skills, mutates its own code.

祈愿博客模板 · 基于 Astro 的全功能博客模板：AI 问答(RAG)、文章朗读、评论、网盘、短链、资源站，EdgeOne Makers 一键部署

Kimi Code-style agent orchestration harness for the Pi coding agent — Swarm, Goal, Plan, Permission, Task, Hooks, Skills, TUI

Add an agent with one CLI command. Source lands in your repo as real TypeScript — prompts, tools, and runtime you can edit and own.

Multi-tenant AI customer support platform, businesses upload docs, FAQs, PDFs, or a website URL and get a RAG-powered assistant that answers customers 24/7.

A Model Context Protocol (MCP) server that builds rich code graphs to provide deep contextual understanding of TypeScript codebases to Large Language Models.

A personal substrate for agent packages that ship their own screens. One manifest declares the agent, its verbs, and its UI.

Give life to an AI agent with a single command.

User Interface for Prime-Agent

Community GitHub Action for DeepSeek Harness — AI Code Review · CI Diagnosis · Auto Fix · Issue → PR

Cyberpunk multi-agent command center for DeepSeek Harness — Chinese-first conversation, code execution, VS debate and trajectory workbenches.

MCP server for Asterisk and FreeSWITCH. Lets AI assistants inspect channels, SIP registrations, trunk status and dialplan on a live PBX.

MusePi — desktop-first AI coding assistant: Electron GUI + TUI/CLI + daemon + desktop companion. Native video understanding, MCP, advisor, memory, multi-domain skills; own update channel.

Statewave use case in TypeScript: a grounded product advisor and support assistant, with an Ops Assistant that tracks and closes content gaps.

문서만 주면 데이터 생성·학습·평가까지 알아서 도메인 LLM을 만들어주는 Agentic LLMOps 에이전트 — 자연어 지시 + Human-in-the-Loop, 로컬 구축. Chat-driven LLMOps agent that builds domain-specific LLMs from your documents.

Eden Agent — local-first Rust agent runtime with React, Vite, and Electron clients

A Next.js multi-provider AI workspace for chat, search, reasoning, image and video generation, and browser voice interaction.

A runnable multi-agent process with a built-in evaluation system — repeated rollouts scored on the git diff, not the agent's self-report. OpenAI & Anthropic.

Local-first AI workspace for creators — browser-based, privacy-first, multi-agent collaboration

macOS workbench for running many Claude Code sessions side by side: session cards, fork DAG, kanban, tiered notifications, Git worktrees. 码头：Claude Code 多会话桌面工作台

开源校园智能助手：课表、成绩、考试、通知、日历、文件与记忆，一句话搞定。欢迎共建更多学校。

Herdr World — a multi-surface web experience for Herdr

Measurement for coding agents building UI: extract a contract from the reference page, check the implementation, get numbers back

F.R.I.D.A.Y — a secure self-improving personal AI agent. Local-first, with memory, tools, voice, MCP, automation, and verified self-extension.

🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain.

Crisp 智能客服助手的自部署版

Use GPT (ChatGPT Plus/Pro), DeepSeek, Kimi, Grok and 400+ models in the Claude Desktop Code tab and Claude Code while staying signed in to your Claude subscription — no third-party gateway (3P) mode. Several ChatGPT accounts that take over when one runs out; Claude inside Codex too. Not affiliated with Anthropic or OpenAI.

Pi Skill Orchestrator is a Pi extension for people who use a lot of Agent Skills. It keeps Pi's normal skill autocomplete, but it stops the complete skill catalog from taking space in the LLM system prompt on every turn.

A lightweight, inspectable TypeScript coding agent for local software-engineering work.

Local-first desktop AI agent platform built with TypeScript, Electron, React, and SQLite.

Built an AI SaaS Platform that enables users to access multiple AI-powered tools through a unified dashboard, including content generation, document analysis, chat assistants, and workflow automation with secure authentication and subscription management.

Tiledesk is the open source AI agent builder, written in Node.js and Angular. This repository is dedicated to the WebApp dashboard to manage Tiledesk: open-source alternative to Voiceflow, enabling easy creation of advanced LLM-powered Agents with seamless human-in-the-loop (HITL).

🦞 OpenClaw AI Agent Scenario Workshop — visually install, configure & manage OpenClaw agents in 5 minutes. No terminal needed.

Una aplicación para interactuar con el contenido de tus archivos PDF y poder hacer tu estudio más sencillo.

Relational memory substrate for AI agents with MCP tools, identity continuity, and self-hosted persistence.

Self-hosted dashboard for OpenClaw AI agents. Cost tracking, budget enforcement, session replay, config safety.

A framework to connect APIs with AI agents

TypeScript few-shot learning for LLM agents: semantic example retrieval, SQLite/Postgres stores, Vercel AI SDK.

An AI assistant runtime for coding and team workflows, with DingTalk AI Cards, sub-agents, memory, and scheduled events.

A Model Context Protocol (MCP) server that provides AI assistants with access to Microsoft OneNote. This server enables AI models to read from and write to OneNote notebooks, sections, and pages.

AI-powered platform that verifies supplier ESG claims using autonomous web agents, detects compliance risks, and generates actionable reports under EU CSRD regulations.

Deprecated split repo; AtomicMemory SDK now lives in atomicstrata/atomicmemory/packages/sdk.

A TypeScript framework for building interactive MCP applications that work seamlessly with both MCP Apps and ChatGPT (OpenAI Apps SDK) from a single codebase.

Self-hosted Codex, Your Codex in Your Container

Direct AI agents to build production apps at unprecedented speed with this edge-first Next.js + Convex + Cloudflare starter template designed for agentic development workflows.

SylvaDeck is an agent-native presentation workbench for turning structured thinking into editable decks. A local-first, HTML-based AI presentation Creator

Chatbot for The Carbon Almanac book or a climate change related topic

Supercharge your workplace productivity with collaboration enabled AI. Data is fully secured.

AI-powered architecture documentation generator with RAG, hybrid retrieval (semantic + structural), and multi-agent workflows using LangChain

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

a research agent that should make you go viral

A CLI application that uses AI to process natural language commands and execute them in the terminal.

GemAI - A Free RAG CLI ChatBot 🤖

small parser to create more interesting language/sentences

AI API service to enable your apps with powerful AI models for free. (Deprecated Sorry, its not me its Google lol !)

💬 Rapidly build Facebook Messenger apps in Node.js

NetGPT is a natural language assistant for network engineers.

ReMind — для всех. Даже для тех, кто ещё не понял зачем.

typescript wrapper for gpt-3 api

An AI chatbot SaaS developed using Next.JS, Vercel AI SDK, Open AI and TypeScript.

AI-powered GitHub profile & repository analyzer with tech stack insights and project health scoring.

An opinionated hybrid boilerplate with python backend and react-ts frontend, dockerized for deployment. Uses language model chaining to sequentially generate multi-modal (images and text) content from micro prompts.

A revolutionary AI-powered platform to help you solve doubts instantly, make learning easy, and achieve academic success.

ai-validator is a powerful library that helps to extract and validate structured data from the output text of language models.

Next.js B2B quote builder with server-side pricing (Prisma + Postgres), live line-item breakdown, PDF export, and optional AI chat. Supabase-friendly.

AI SDK Provider that makes All models (including Codex) from Github Copilot openai compatible

Create subtitles for your video and traduction in a few clicks with ai

Claude Runner vscode extension

AI assistant for written inquiries of the Berlin House Of Representatives (AGH)

Three packages: @kernel.chat/agent-os (POSIX for AI agents — capabilities, namespaces, quotas, taint, audit, vault, outcomes), @kernel.chat/kbot (terminal AI agent, MCP-native, BYOK), @kernel.chat/kbot-finance (audit-grade AI for regulated industries). Provenance-engineering substrate.

Agent execution layer for biology workflows: batch gene scanning, tumor cohort briefing, target discovery — with structured outputs, resume, and pipeline-ready artifacts

Evaluate LLM agentic capabilities through combat games

Carter is a streamlined platform designed to help users effortlessly organize, share, and manage their links. With a secure interface, it allows users to save, categorize, and retrieve links in a controlled environment. Emphasizing privacy, Carter keeps links accessible and shareable as needed, empowering users with full control.

📓 A web app/PWA for managing and sharing your personal knowledge, daily notes, and reusable prompts, using GitHub Gists + AI

Compare a generic GPT-3 based chatbot with ChatGPT

Real-time token tracking, cost forecasting, and rate limit prediction for the Anthropic Claude API. Self-hosted, open source, free forever.

🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.

Self-contained agent backend with tools, RAG, and durable runs. One binary, no external services.

VideoDB Nodejs SDK

7+1 AI development agents for GitHub Copilot with Chinese philosophy-driven thinking models. Brainstorm, plan, execute, debug, review, mentor, and Mozi autonomous deep worker.

AI agent engine with 22 chat channels, 65 tools, and 15 skills. Self-hosted, local-first, works with any LLM provider.

Aisanity is a secure, hassle-free tool for running AI agents in isolated environments, protecting your host OS from risks while enabling seamless development workflows. It provides sandboxed containers with automatic AI integration, git worktree support for parallel development, and compatibility with any IDE or terminal tool.

Session explorer for Claude Code - find, search, and resume all your past sessions

Local-first agent skill manager for VS Code / Cursor. Manage, browse, and import skills across Claude, Cursor, Codex and more.

This project is a Customer Feedback Analysis AI Agent that do analysis, generates insights and action items based on customer feedback.

AM — autonomous AI agent system. The agent does the work and ships the PR. ⭐ Star to follow along.

Hat-based multi-agent orchestration loops for pi coding agent

Framework for AI agent teams that build real software on GitHub — governance, roles, and CLI included.

Migrate anything text-shaped to WordPress — driven by Claude Code, GitHub Copilot CLI, or OpenAI Codex. Generates a block theme (FSE), Gutenberg blocks from legacy shortcodes, a site plugin replicating every SSG-level plugin, with an autonomous attempt→test→fix loop.

Real-time voice agents with parallel async background sub-agents — conversations continue naturally while tasks run • Join the builders → https://discord.gg/mqxKaN3UKC

💬 WhatsApp AI bot with native replies, smart rate limits, per-chat memory, and a sleek admin UI, powered by Baileys and switchable Gemini/OpenAI models.

Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.

Claude Code plugin — AI-powered autopilot for managing open source contributions. Track PRs, respond to maintainers, discover issues, maintain velocity.

A desktop pet application based on Live2D and AI Agent

A Model Context Protocol (MCP) server for Mount & Blade II: Bannerlord. Gives AI agents access to decompiled source search, XML data browsing, gameplay queries, local mod source indexing, and patch generation tools.为《骑马与砍杀2：霸主》打造的 MCP 服务器，支持源码检索、XML 数据查询、玩法数据浏览、本地 Mod 源码索引与补丁辅助生成。

Multi-lens code review MCP server for Claude Code. 8 specialized reviewers run in parallel and return structured verdicts (security, performance, test quality, clean code, and more).

Live VS Code sidebar for Claude Code — animated pixel-art robot, per-session dashboards, pace-based usage meters, token-rate chart, git + skills + MCP browsers. Auto-matches your VS Code theme.