Typescript agents

Multi-agent AI career operating system for ATS-optimized job applications. Built with FastAPI, Next.js, LangGraph, Gemini, ChromaDB, and RAG-based semantic retrieval for resume optimization, evaluation loops, cover letter generation, and intelligent application workflows.

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, text-to-music, answers from your own documents, and voice. GGUF on llama.cpp, MLX on Apple Silicon. macOS, Windows, Linux. No account, no cloud, no telemetry.

An automated, Cloudflare based, SEO agent for large scale content sites.

Monorepo of Pix, Distro of PI Coding Agent

Lightweight agentic coding environment

AI 电商视觉创作助手 > 用一句中文描述你的产品，30 秒拿到一张专业电商图。上传参考图 换场景/姿态/风格 。ecom-details-image skill的web agent版本，利用 EdgeOne Makers 免费服务器，免费model api（deepseek）,利用Agnes api 免费，识图免费，生图免费

Self hosted Wiki + Jira-style AI native issue tracker on Cloudflare Workers

Claude Code 的桌宠与本地工作台 · A desktop pet & local workbench for Claude Code — 实时动画、权限卡片、Token 看板，兼容 codex-pet / cc-switch ⚓

Agent registry for Eve and Flue

Agent-native way to access any website. Bridging agent CLI and web GUI through API.

Optimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.

Your Own Autonomous Computer Agent

oh-my-dsh：面向 DSH (DeepSeek Harness) 的插件生态——700+ 插件，只通过扩展接缝注册，不修改 agent-loop 骨架

Agent-ready SEO for JavaScript — schema.org JSON-LD graph builder with an Astro integration.

Bridgic Agent turns what you want into workflows that actually work — and keep working. `/build` It. Run It. Evolve It.

Convex Skills for Agents

AICMS — the AI-native CMS built for AI agents. AICMS lets an agent run 100% of your website: chat-driven editing, typed block content, beautiful starter themes. Open source, Next.js + Astro + Postgres. https://AICMS.one

Apps small enough for AI to hold whole. ObjectStack turns the whole app — data model, UI, workflows, permissions — into typed metadata: a complete CRM in under 150k tokens, one context window. Agents read it whole, reason it whole, refactor it whole.

An Open Source Intelligent Codebase Visualizer for you and your agents for javascript, typescript, reactjs, nextjs, python, java, go and rust for easy PR review, fast Onboarding and deep architectural understanding

In-app feedback with first-party session capture and Cursor cloud agent dispatch.

USL is the storage-first reference implementation of the Agent Session Protocol (ASP). ACP handles the live present (editor↔agent interaction); ASP handles the durable past and cross-runtime migration; USL is the storage engine behind ASP.

Anvia is a TypeScript runtime for building provider-agnostic agents, tool workflows, and structured extraction inside your application code.

Human-in-the-loop planning extension for the Pi coding agent. Turns rough change requests into versioned Markdown plans, stores them in a configurable artifact root, refines them through reviewer/criticizer subagents, and gates implementation behind tracked execution and explicit approval.

A visual editor for the browser to communicate with your coding agent.

A desktop app for the fx coding agent, built on libfx and GPUIX.

Max is a federated data connectivity layer that puts searchable data next to your deployed agent

A trustworthy context layer for AI that remembers, plans and acts — free text into typed commitments, decisions and memories, each with its evidence, in a SQLite file you own. MCP, HTTP, library and typed client.

Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.

This repository provides a reference for the tasks extensions to the MCP protocol, allowing for long-running operations, such as Agent communication, in MCP.

Free, open source, realtime task manager. Issues, boards, sprints, projects and docs that sync instantly. Keyboard-first, self-hostable, with an MCP server for AI agents. No pricing, ever.

AI 八字 + 紫微斗数排盘与综合印证 Skill（基于 mingpan + iztro 开源库）：算法精准排盘（不靠 LLM 猜），三种分析模式，一键生成水墨风 HTML 命盘海报。兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent。

Bridge Claude Code/Codex sessions to a Feishu (Lark) bot

Developer tools to debug and build realtime voice agents. Supports multiple models.

🤖 Multi-Agent MCP Server - Let Claude Code / Windsurf / Cursor orchestrate GPT, Claude, Gemini to work as an AI dev team

A Claude-Code-like CLI coding agent scaffold (TypeScript + oclif)

Plura is a powerful tool for creating, managing, and deploying AI agents. Built with TypeScript, it helps you develop intelligent agents that integrate with mini services, interact across platforms, maintain consistent personalities and knowledge, and automate tasks seamlessly.

A Cloudflare Page showing how to do semantic search

Refiner improves your writing by correcting grammar and style, adjusting tone, and offering formatting options. It is useful for non-native speakers and professionals who communicate with text.

GitHub Search, powered by OpenAI, through an intuitive chat interface.

An AI-Powered documentation generator for legacy codebases

This is a reference agent blueprint for AI-powered quantum device calibration. It provides an intelligent agent interface for discovering, executing, and analyzing quantum calibration experiments with support for automated workflows and vision-based analysis.

Hive Agents gateway localfirts

A Node.js OAuth Agent, providing API driven OAuth and OpenID Connect for SPAs

Soulscript is a framework-agnostic standard for defining rich agent personalities that evolve over time.

Build safe on-brand voice and chat agents with structured flows, guardrails, and compliance

Open source CLI agent that generates complete lesson bundles in your teaching voice. 48+ tools, zero-touch 9-file output, local-first privacy.

One Skill for all repos. Give your agent access to the source code and docs of all open-source libraries

Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON

📧 MCP Mail Tool - AI-powered email management tool | 基于 MCP 的智能邮件管理工具

Allows LLM agents to control a local chrome instance without taking screenshots

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

Crawl any website with Tavily, embed the content, and deploy the RAG on MongoDB Atlas vector search.

A vibe coded Sora JSON Prompt Crafter for curious humans and prompt engineers

Writing companion for AI content generation.

A remote, phone-first console for your tmux — agent-agnostic, no database. Spawn and watch coding agents in parallel worktrees, or anything else you run.

CLI for AI-assisted manual code review

Install agent skills and MCPs with one API

LLM integration into Crusader Kings 3

CLI for Beeper Desktop API - unified messaging from your terminal. Give your AI agents the power to chat across all your messaging platforms.

Coordination protocol for agent-first teams. No UI. No sprints. No Jira. Just state sync.

A cross-platform desktop AI assistant that lets you translate, rewrite, summarize, and brainstorm with just a hotkey.

An autonomous claude code development team orchestrated by a hook-driven deterministic code workflow. An example repo to inspire your own workflow

Durable Cloudflare computers for agents: run repos, steer live workspaces, verify results, and return receipts.

Bring your own AI environment to Obsidian. For note/doc creation, refinement, search, organization, management, you name it!

Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.

Self-hosted & federated platform for AI IDE/Tools Rules and Commands via WebUI & CLI - Generate, browse, store, share AGENTS.md, CLAUDE.md, and more

Sora 2 Storyboard

Customer Chatbot Solution Accelerator empowers organizations to build intelligent, conversational customer service experiences by leveraging Microsoft Foundry's agent framework.

Self-improving behavioral files for AI coding agents. Analyzes session transcripts for correction patterns and makes surgical edits to prevent recurrence.

A beautiful, native macOS desktop application for transcribing audio and video files using whisper.cpp

✨ A programmable content review harness for AI agents. The slop filter your agents are missing.

A team of AI agents that runs your job search — self-hosted, on your own LLM subscription. MIT.

sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 25 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (103 tools, 11 plugins). Eve

Zotero MCP server: search, citations, add by DOI, safe writes, semantic search and PDF page images for Claude, ChatGPT and any MCP client. TypeScript, local-first.

Semantic diff review for coding agents

Loop-native agent workspace — put your AI coding agents on a canvas, wired into loops that run themselves.

Zero-dependency TypeScript secret and PII redaction for any SDK, logs, HTTP, LLM prompts, and scoped MCP tool boundaries.

A good invisible interface to agents

Ollama Cloud plugin for Pi coding agent (API Key based)

The open-source agent platform to build, distribute, and optimize AI agents — on infrastructure you own.

Every local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.

Mintlify Index: retrieval engine and MCP server. Install: npx mint index

Render LaTeX from any CLI agent directly in Kitty-compatible terminals

Conversational code review on macOS: review a PR or local branch together with a codex agent, and ask about any line instead of just reading its findings.

Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.

让 Agent 安全常驻桌面的独立 dsh 客户端：官方 Web UI 原封不动，长任务常驻托盘，精选插件先审查、再安装。Independent dsh desktop client: the official Web UI untouched, long tasks alive in the tray, curated plugins reviewed before install.

Control mobile devices from OpenCode — live TUI sidebar screen, resilient UI hierarchy dumps, touch gestures, and deep links.

多agents协作平台

ARCHIVED. See https://github.com/ephemeraHQ/xmtp-agent-examples instead.

Web search, deep research and fetch content tools for Pi Agent, powered by Exa

PON Sovereign Agent is an autonomous AI treasury that continuously evolves its intelligence and allocates protocol-generated revenue across crypto and tokenized real-world assets.

优化拓展pi-agent，在Terminal-Bench 2.0 评测体系，任务完成率约48%。

Your logo, as your agent's loading animation. Bake any SVG into a dot cloud and play it as seven AI loading states.

🎓 校招网申智能体 - AI驱动的网申表单自动填充Chrome插件

Agent-ergonomic CLI for task/backlog management with pluggable backends (markdown, sqlite, remote trackers)

Stellar-aware execution runtime for AgentLily autonomous finance agents — TypeScript task runner, typed tools, and Stellar payment preparation for Lily Protocol

Pivot (T3.14): T3 Code fork pivoted to omp — remote-ready agent control surface.