Typescript agents

Translate any webpage bilingually in Chrome, Edge & Firefox (Manifest V3). Side-by-side bilingual reading via any OpenAI-compatible LLM — DeepSeek, OpenAI, Ollama. Optional self-hosted Go caching proxy cuts LLM cost up to 90%. Zero telemetry, Apache-2.0.

Lightweight Bun + Elysia proxy for OpenAI-compatible APIs with Langfuse telemetry

Deterministic, agent-authorable motion graphics engine with a CapCut-style browser editor. Preset-driven and multi-renderer across HTML, Three.js and video, with no AI model in the render path.

An embeddable AI dev agent for your running app — chat, page control, and live tests, injected into the page via a Vite plugin.

CLI, MCP and TS library that turns source code into a map of files, symbols, references, and dependencies using tree-sitter.

Apply V4A context-anchored diffs from any LLM model and get structured line-by-line diff output with built-in instant rollback capability.

Real-time AI assistant for PokerNow Texas Hold'em — get GPT-powered suggestions overlaid on your game as you play.

Local-first live dashboard, CLI, and Windows widget for your subscription quotas plus local token spend. Silent updates, zero telemetry.

Local-first MCP server for video: download any video from almost any URL, or get a transcript plus scene-aware deduplicated keyframes. YouTube, TikTok, Instagram, X, WeChat Channels, MP4/HLS. No cloud, no API keys.

⚡ Competitive multi-wallet NFT auto-minting agent for OpenSea/SeaDrop & direct contracts — low-latency fast-mint (raw EIP-1559, multi-RPC fan-out, RBF), scheduled drops, browser fallback & listing. Runs as an MCP server, an AI-agent skill (Hermes/Claude), or a CLI. Security-hardened, multi-chain EVM.

DeepSeek Desktop application with Chat and Harness modes;deepseek-harness桌面端应用，集成网页端chat能力，可手动切换。

Multi-tenant SaaS AI agent platform: MCP, WhatsApp, billing — Next.js + TypeScript

A minimal Coding Agent Harness inspired by Pi, built to study and validate Agent Runtime/Harness abstractions through executable demos and real LLM experiments.

Portable doc bridge for AI agents — OKF + Self-Describe + AgentHandoff. CLI, MCP, Fumadocs/Docusaurus adapters.

Spawn silent-boot codex/omx coder teams — a maw plugin + charter. Each coder on its own account & worktree, zero trust prompts.

A local-first, governed agent harness: high autonomy inside structurally-enforced boundaries (Autopilot, not YOLO).

DeepSeek Harness 插件：确认改动的代码行真的被测试覆盖到，结论绑定代码指纹，代码一变自动过期

WeCom AI Bot text and image bridge for DeepSeek Harness

Standalone Agent Client Protocol (ACP) server for DeepSeek Harness with real-time streaming, reasoning trace, MCP tools, and session recovery.

Unofficial Model Context Protocol server for Alza.cz — read-only catalog browser for AI agents. Uses Playwright to defeat Cloudflare bot protection.

An AI agent that drives a real browser, audits any web app against UX/functional/conversion rubrics, and shows evidence-backed findings. Works with any OpenAI-compatible LLM.

Generate PDFs from JSON — declarative, serverless, no Chromium. TypeScript-first with professional typography.

Jeomwon (점원) — agent kit that turns one domain interview into a working reservation SaaS: AI storefront clerk chat, admin dashboard, and lifecycle emails on Convex + Next.js

6 ajanlı otonom multi-agent orkestrasyon sistemi — TypeScript, pgvector hafıza, öğrenen yönlendirme. Kendi sunucunda çalışır, BYOK (OpenRouter/OpenAI/Gemini/Ollama).

Native Claude Agent SDK with Harness specialized become as team member.

Multi-agent DeepSeek Harness workbench with switchable Pi, OpenAI Codex, Claude Code, and native DeepSeek Agent Loops.

Open-source agentic AI for social media planning, scheduling, approval, and browser-based publishing.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

Fix context rot & pollution in long AI agent sessions. Subagents run in isolated processes — main agent stays read-only. Context isolation via process isolation.

Open-source, local-first AI workspace with 20+ providers, agents, MCP, browser Python, and an in-browser Linux environment. BYOK and self-hostable.

⚡ The Ultimate AI Relay Forensics & Benchmark Suite. Calibrated for GPT-5.6, Claude Fable 5, Gemini 3.7 & Grok │ 4.6. Cryptographic Thinking Signature Checks, Native Stream Forensics & Anti-Ban Batch Key Testing.专治大模型中转站掺水：官方私钥签名验真 / 原生思考流鉴伪 / TTFT·TPS 流式基准 / API Key 批量检测

Your habits shape him — a virtual owl that turns screen habits and study progress into something you can see and care about.

ATV Design — the GitHub Copilot-native AI design agent for your desktop. Prompt → prototype, slides, PDF with your Copilot subscription via OAuth+PKCE. Local-first, BYOK for other providers, MIT-licensed. Electron + TypeScript + React.

Provider manager for Pi coding agent — add/edit/test providers with adaptive capability self-check

Fixes broken prompt-caching for Claude Code and the Anthropic API - 8.2x cheaper

Personal AI memory system / ambient AI companion

Local, AI-native visual editor for single-file HTML — point at an element, say the change in plain language, review the diff + safety check, then write back. Never regenerates the page.

Train (from scratch) tiny GGUF language models on WebGPU

面向中国用户的开源 Grok Bot 替代方案，默认简体中文，支持 Claude、Codex、GPT、Grok、Gemini 与 API 中转站。

A custom fork of oh-my-openagent focused on advanced agent routing, workflow safety, and project-aware automation.

Deeptop, a lightweight native desktop client for DeepSeek Harness.

Always-on, self-hosted AI agent runtime — multi-LLM, parallel sub-agents, Telegram/Web/CLI, skills, memory, MCP.

Agent Skills for working with Hookdeck products — Event Gateway (webhooks/events) and Outpost (outbound delivery). Follows the Agent Skills specification.

Multi-chain AI agent economy: 5 agents across Hedera, 0G, and Base. Orchestrated by the obey daemon. Built with fest.build

Private AI on premise

Self-hosted, browser-based orchestrator for AI coding agents — real terminals, a kanban board that routes attention, review with real diffs. Access from anywhere. AGPL, no telemetry.

See what every plugin puts into the model.

Amazon DynamoDB storage backend for the Strands Agents SDK (TypeScript and Python): sessions, agent memory, semantic search over DynamoDB vector indexes, and S3 offload behind one Storage interface.

Transform prompts into professional diagrams (Thinking Maps, mind maps, concept maps). Vue 3 + FastAPI stack with PostgreSQL, Redis, Qdrant RAG, WebSocket collab, Workshop Chat, and Qwen/DeepSeek/Kimi/Doubao LLMs.

Cortex is a decentralized sovereign elastic memory layer built on the Sui stack that lets people, agents, and applications store, share, and act on durable encrypted intelligence.

TypeScript and Rust monorepo: Claude Code and Pi coding-agent plugins, a minimal MCP stdio server framework, custom oxlint plugins and a pluggable Rust linter, policy-aware git tooling, core TS libraries, Wayland desktop apps (GTK4 file manager, Slint terminal, true-peak music player), OpenTofu infra automation, and a personal site.

Hosted email MCP server for AI agents. Connect Gmail, Fastmail, iCloud, or IMAP to Claude, ChatGPT, Cursor, and any MCP client.

The reference app for AI-written enterprise software: a complete CRM in typed ObjectStack metadata — business logic under 100k tokens. Small enough to hand an agent in one context window.

Agent harness / control-plane around a stateless LLM: deterministic policy floor on PreToolUse/PostToolUse hooks, secret redaction, injection fencing, tool-result compression, code-graph memory, orchestration. Five plugin modules for Claude Code (Tier 1) or any MCP host (Tier 2). MIT.

It lets you scan local agent skill folders, bundle multiple skills into a reproducible skill pack, publish that pack to GitHub Releases, install other people's packs, and keep editable workspaces synced across machines.

A presentation layer for AI responses. It keeps Markdown and structured response metadata separate from the visual treatment, so the same AI output can appear as a readable document, a compact assistant message, or a handwritten sketch.

Reference agentic application combining Angular, A2UI, generative UI, and human-in-the-loop workflows.

IDE for authoring, deploying, and monitoring BDI-based AI agents that run as automated cron jobs. Transform agent definitions (AGENT.md with beliefs/schema, desires/goals, intentions/constraints) into persistent, self-executing AI agents.

One workbench for AI coding agents—run locally or remotely, review every task, and keep memory and Markdown knowledge.

An internship full stack challenge from unthinkable - An LLM based health diagnosis tool

SerenAI is a self-hosted AI chatbot platform that turns your documents into intelligent conversational assistants. Upload PDFs, Word docs, or text files—and instantly create chatbots that can answer questions about your content using RAG (Retrieval-Augmented Generation).

CLI tool for OpenRouter

Production-ready full-stack template for building AI agents with LangGraph, LangChain & DeepAgents — FastAPI + Aegra backend with JWT auth and a Next.js 16 frontend.

deepseek harness 纯牛马 —— 多智能体数字员工指挥台插件

one coordination board for your team's coding agents. claude code, cursor and codex share a job board and take a lock on a file before editing it.

Self-hosted AI agent living inside Zalo (personal account). Multi-account, 15 tools + external MCP servers, web dashboard, scheduler, durable memory, rich-text messages. Provider-agnostic: any OpenAI-compatible endpoint or Anthropic. TypeScript + SQLite. MIT.

An Effect-native agent execution kernel: sessions, runs, turns, steering, follow-ups and typed lifecycle events on top of Effect AI.

The full-stack TypeScript framework for AI agents. An agent is a file: drop it in agents/ and it gets an HTTP route, token streaming, human-in-the-loop approvals and a typed client. React pages with file routing and SSR, OAuth sessions, Postgres, WebSockets, cron, and nine deploy targets. Apache-2.0.

An AI-powered web application for generating customized novels by blending genres, tropes, and narrative elements. Features simple and advanced creation modes, an inspiration library, real-time cost estimation, and a personal book library for managing generated content.

Engineering incident intelligence platform — correlates GitHub & Sentry signals for evidence-backed root-cause analysis and AI postmortems.

Open-Source Prompt Engineering Workbench: LLMs complete tasks and score results based on prompts, and automatically iterate to generate higher-quality prompts through Q&A cycles.

Open-source macOS control room for running local AI agent teams with Claude Code, Codex, Gemini, and BYOK runtimes.

An end-end Financial Modeling Agent system

TypeScript mirror of the Maida trace contract. Emit and validate Maida-native agent traces from Node. Deliberately narrow -- not at feature parity with the Python package.

AI creative coding studio for p5.js, GLSL, Three.js, music, video, and model-agnostic generative art workflows.

Orion Code is a multi-agent orchestration system that acts as a virtual Tech Lead, coordinating specialized AI agents to collaborate on software projects.

zx fork with native Pi AI — shell scripting with AI agents (π text, Π coding agent, α any ACP agent), user-defined letter tags as plugins, JSONL run traces, and a local result cache

Canopy IDE

基于官方 Deepseek Harness 打包的桌面客户端，方便直接安装使用

Pack a repo into one AI-friendly file — or keep only the lines that matter for one task, with a verification receipt.

Teach once, replay anywhere — harness-agnostic Teach-by-Demonstration engine (Record → Compile → Replay → Verify) with OpenMausBot and DeepSeek Harness integrations.

MCP server that turns text prompts into premium iOS mobile UI mockups (PNG + HTML). Powered by Claude (Opus 4.7) + Playwright. Two backends: local CLI or Anthropic API. MIT.

Local MCP gateway with progressive tool discovery, description compression, and controlled access to large results.

An infinite canvas your local LLM draws on. Typed widgets, BYO model (Claude/OpenAI/Ollama), MCP-native, local-first, MIT.

A terminal coding agent that shows every edit as a diff before it writes, and asks before running a shell command it cannot vouch for

Air-gapped enterprise RAG workstation — local inference, zero cloud egress. Built with Microsoft Foundry Local.

Open-source AI intelligence platform for private equity — cited RAG chat over your data room, portfolio analytics, AI model builder, meeting transcription & LP inbox. Self-hosted in your own AWS (full Terraform). AGPL-3.0 alternative to Rogo / Hebbia.

Sovereign Agentic OS — self-hostable, EU-sovereign agentic data platform on Kubernetes (pre-beta). One Helm chart, runs in your own cluster.

🍳 Vibe Cook — 跟着做就会。把 HowToCook 做成沉浸式一步步烹饪 App。

青简 QingAgent — 让 AI 和你默契写作。本地优先的 AI 写作客户端：对话起稿、逐条审改、排版导出，文档只存在你自己电脑上

An Obsidian plugin that enables configuring and exposing agentic resources based on the Agentic Resource Discovery Specification

Evidence and verification for AI coding agents: map code, reuse concepts, finish migrations, and gate diffs.

File-first knowledge base for humans and AI agents — self-hosted Markdown notes with a web editor and a built-in MCP server.

Context-cheap SerpApi search for AI agents: a CLI + Claude skill that costs ~0 standing tokens vs an MCP server (measured).

Local-first npm supply-chain security scanner: static + optional LLM analysis, CLI/CI gates, desktop app, and AI-agent skills.

DSH 完整移植版 DietrichGebert/ponytail — 懒惰 senior 模式，hook注入

Open, causal evaluations for content-addressed semantics and multi-agent coordination.

MCP server for social media — fetch tweets, transcribe videos, extract frames, download Instagram posts. 29 tools across Twitter/X, YouTube, Instagram, and any video URL. Local Whisper transcription.