Browse free open source JavaScript AI Agents and projects below. Use the toggles on the left to filter open source JavaScript AI Agents by OS, license, language, programming language, and project status.

  • Ship Agents Faster Icon
    Ship Agents Faster

    Transform your applications and workflows into powerful agentic systems at global scale.

    Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
    Start Free
  • Our Free Plans just got better! | Auth0 Icon
    Our Free Plans just got better! | Auth0

    With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

    You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
    Try free now
  • 1
    Lemo-Opuscar

    Lemo-Opuscar

    Claude Code skill for short films with no video model

    Lemo-Opuscar is an open-source Claude Code skill for creating animated short films entirely through programming rather than generative video models. It provides 51 cinematic and artistic styles, each accompanied by a reusable prompt, demonstration film, and production guidance. Users can describe a story, choose a visual style, and have an AI coding agent develop the complete film. The system renders animation frame by frame using Canvas, WebGL, and other code-driven techniques. It also supports original music, text-to-speech narration, scene composition, and audio mixing. Built-in directing guidelines help coordinate storytelling, camera movement, pacing, and visual consistency. Users can customize existing styles, preview storyboards, and export finished videos through FFmpeg.
    Downloads: 289 This Week
    Last Update:
    See Project
  • 2
    AnythingLLM

    AnythingLLM

    The all-in-one Desktop & Docker AI application with full RAG and AI

    A full-stack application that enables you to turn any document, resource, or piece of content into a context that any LLM can use as references during chatting. This application allows you to pick and choose which LLM or Vector Database you want to use as well as supporting multi-user management and permissions. AnythingLLM is a full-stack application where you can use commercial off-the-shelf LLMs or popular open-source LLMs and vectorDB solutions to build a private ChatGPT with no compromises that you can run locally as well as host remotely and be able to chat intelligently with any documents you provide it. AnythingLLM divides your documents into objects called workspaces. A Workspace functions a lot like a thread, but with the addition of containerization of your documents. Workspaces can share documents, but they do not talk to each other so you can keep your context for each workspace clean.
    Downloads: 168 This Week
    Last Update:
    See Project
  • 3
    Codex Dream Skin

    Codex Dream Skin

    Give the Codex desktop a breathing face

    Codex Dream Skin is an unofficial theming tool that changes the appearance of the Codex desktop application. It injects external styles through a local Chrome DevTools Protocol connection instead of modifying the official application package. Users can apply custom images and visual themes while retaining the native sidebar, project selector, suggestion cards, and input controls. The project provides platform-specific scripts for macOS and Windows. A restore process returns Codex to its original appearance with minimal effort. It binds its injection service to the local loopback interface and leaves API provider settings untouched. The repository also includes verification, recovery, and contribution guidance for safer customization.
    Downloads: 50 This Week
    Last Update:
    See Project
  • 4
    DS Bot

    DS Bot

    A team of long-lived bots for DeepSeek Harness, with main bots & more

    DS Bot is a free, open-source, multi-agent AI assistant platform that enables users to create, manage, and collaborate with persistent AI bots powered by DeepSeek Harness. The application allows users to build personalized AI assistants with individual memories, configurable language models, dedicated capabilities, and permissions for performing different tasks. DS Bot includes a main supervisory bot that manages other agents, coordinates group conversations, delegates assignments, and oversees complex workflows involving multiple AI assistants. Users can connect their bots to services such as GitHub, Gmail, Slack, Telegram, Discord, and other messaging platforms while extending functionality through Model Context Protocol (MCP) servers and reusable skills. The platform supports computer automation, local coding agents, document creation, scheduled workflows through connected tools, and collaborative task execution with human approval controls.
    Downloads: 48 This Week
    Last Update:
    See Project
  • Save Up to 91% on Cloud Compute With Spot VMs Icon
    Save Up to 91% on Cloud Compute With Spot VMs

    Automatic sustained-use discounts. One free VM per month. No negotiation needed.

    Run batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
    Start Free
  • 5
    Open Claude Cowork

    Open Claude Cowork

    Open Source version of Claude Cowork built with Claude Code

    Open Claude Cowork is an open source desktop chat application that brings the power of autonomous, agent-style AI workflows to your local machine by combining the Claude Agent SDK with the Composio Tool Router, enabling developers and power users to build intelligent assistants that can interact with a vast array of external tools and services. It offers a native Electron-based interface for macOS, Windows, and Linux that feels familiar and modern, supporting persistent, multi-session conversations that maintain context across multiple turns and workflows while you focus on higher-level goals rather than low-level prompts. With support for over 500 integrated tools—including Gmail, Slack, GitHub, Google Drive, and more via the Composio Tool Router—Open Claude Cowork lets agents execute complex tasks that span multiple platforms and APIs, effectively acting as a cross-service productivity layer.
    Downloads: 40 This Week
    Last Update:
    See Project
  • 6
    ego (lite)

    ego (lite)

    The fastest browser for AI agents to run web automation

    Ego Lite is a macOS browser designed for people and external AI agents to work in parallel. Each agent receives an isolated Space, allowing several browser tasks to run simultaneously without taking over the user's active tabs. Optional Chrome data migration carries over logins, cookies, extensions, and bookmarks so agents can use authenticated sessions with less setup. The ego-browser skill connects tools such as Codex, Claude Code, Cursor, and custom agent CLIs to the browser. Agents interact through JavaScript tools for navigation, snapshots, form entry, clicks, waiting, and captures. Browser data remains on the device, and users can observe, stop, or take control of an agent's Space. Windows and Linux versions are listed as future work rather than currently supported releases.
    Downloads: 32 This Week
    Last Update:
    See Project
  • 7
    Agent Skills

    Agent Skills

    Skills for AI coding agents

    Agent Skills by Vercel Labs is a curated collection of modular “skills” designed to extend the capabilities of AI coding agents by packaging human-ready instructions, workflows, and optional scripts that tell an agent how to perform specific development tasks. In this repository, each skill adheres to the Agent Skills specification, meaning they’re defined as folders with a SKILL.md file (containing task descriptions and step-by-step guidance) and can include helper scripts and reference material that the agent can execute or consult when invoked. The goal of the project is to make it easy for AI assistants like Claude Code, OpenCode, Cursor, Codex, and others that support this open ecosystem to automatically apply best practices or perform concrete actions when a relevant user intent is detected. For example, some skills guide the agent in applying React and Next.js performance best practices, auditing UI and accessibility standards.
    Downloads: 18 This Week
    Last Update:
    See Project
  • 8
    PenEcho

    PenEcho

    Think with AI beyond the chat box

    PenEcho is an open-source shared canvas that makes handwriting, equations, diagrams, and spatial context part of an AI conversation. Users can draw with pressure-sensitive ink, erase, pan, zoom, type formatted text, and arrange ideas across a large virtual workspace. The application sends focused visual regions to an API, Codex CLI, or Claude CLI and converts model responses into editable canvas commands. AI output can include text, formulas, plots, mixed drawings, erasures, and declarative animations. Sparse tile rendering keeps the 20,000-by-20,000 logical canvas efficient without allocating one enormous bitmap. Local snapshots, undo and redo, lasso selection, PNG export, and manual or automatic AI modes support iterative work. PenEcho is available as a desktop application or Node.js package and supports configurable models, reasoning levels, request retention, and plugins.
    Downloads: 16 This Week
    Last Update:
    See Project
  • 9
    Steel Browser

    Steel Browser

    Open Source Browser API for AI Agents & Apps

    Steel Browser is a privacy-focused web browser built with security and performance optimizations, designed to minimize tracking and enhance user control.
    Downloads: 13 This Week
    Last Update:
    See Project
  • Patching and Endpoint Management for Under $1/Endpoint Icon
    Patching and Endpoint Management for Under $1/Endpoint

    OS and third-party patching, vulnerability insights, and remote control included

    Splashtop AEM gives IT teams automated patching, monitoring, and unattended remote access for Windows and macOS. No long setup, no paying extra for key features.
    Start Free Trial
  • 10
    dsh-our-free-model

    dsh-our-free-model

    Simply install this plugin in your dsh

    dsh-our-free-model is a plugin and developing standalone service that connects dsh to multiple publicly available or account-backed AI model gateways. It discovers available models dynamically instead of relying on a fixed local catalog. The plugin can expose models through an OpenAI-compatible local endpoint for use by other software. It includes model availability checks, regional-status handling, configurable reasoning budgets, and local performance measurements. A dashboard tracks tokens, latency, generation speed, success rates, and recent requests while keeping usage statistics on the local machine. Built-in updating supports integrity checks, rollback, and hot reload. The project advertises several no-key model channels, although availability, privacy terms, and access conditions ultimately depend on the upstream providers.
    Downloads: 9 This Week
    Last Update:
    See Project
  • 11
    NemoClaw

    NemoClaw

    NVIDIA plugin for secure installation of OpenClaw

    NVIDIA NemoClaw is an open-source tool designed to simplify the deployment and management of always-on AI assistants using the OpenClaw ecosystem. It installs and configures the NVIDIA OpenShell runtime, which provides a secure environment for running autonomous AI agents. NemoClaw enables users to launch sandboxed agent environments that control network access, file permissions, and inference requests through policy-based security. The platform integrates with AI models such as NVIDIA Nemotron and supports multiple inference backends including cloud APIs, local NIM deployments, and vLLM. Through its command-line interface, developers can deploy, monitor, and manage AI assistants running inside isolated sandboxes. By combining sandbox orchestration, agent management, and AI model integration, NemoClaw provides a secure foundation for building and operating autonomous AI assistants.
    Downloads: 8 This Week
    Last Update:
    See Project
  • 12
    chrome-cdp

    chrome-cdp

    Give your AI agent access to your live Chrome session

    chrome-cdp-skill is a specialized integration that enables AI agents to control and interact with web browsers through the Chrome DevTools Protocol (CDP). It allows agents to perform tasks such as navigating pages, extracting data, interacting with elements, and executing scripts in a browser environment. The project is designed to extend the capabilities of AI systems beyond static knowledge by giving them real-time access to web content and interactive interfaces. Its architecture likely abstracts CDP commands into higher-level operations that are easier for agents to use. This makes it particularly useful for automation tasks such as web scraping, testing, and dynamic data retrieval. The system emphasizes precision and control, allowing agents to operate browsers programmatically with fine-grained actions. Overall, chrome-cdp-skill acts as a bridge between AI reasoning and real-world web interaction.
    Downloads: 6 This Week
    Last Update:
    See Project
  • 13
    Huashu Design

    Huashu Design

    Huashu Design · HTML-native design skill for Claude Code

    Huashu-design is a framework focused on designing and optimizing conversational scripts, particularly for persuasive or structured communication scenarios such as sales, marketing, or customer interaction. The project emphasizes the creation of “huashu,” or structured dialogue patterns, that guide interactions toward specific goals. It provides methodologies and tools for organizing conversation flows, ensuring that responses are consistent, effective, and aligned with intended outcomes. The system is designed to be adaptable, allowing users to customize scripts for different domains or audiences. It also encourages iterative refinement, enabling continuous improvement of conversational strategies based on feedback and performance. The framework can be applied to both human-driven and AI-driven interactions, making it versatile across use cases. Overall, huashu-design offers a systematic approach to crafting and managing effective communication patterns.
    Downloads: 5 This Week
    Last Update:
    See Project
  • 14
    OpenClaw Chinese Translation

    OpenClaw Chinese Translation

    Open source personal AI assistant Chinese version

    OpenClawChineseTranslation is a community-driven effort to provide translated resources and documentation for the OpenClaw project in Chinese, making it easier for native Chinese developers to understand and implement the agent framework. It focuses on producing accurate and up-to-date translations of tutorials, API references, configuration guides, and explanatory materials so that learners don’t struggle with language barriers when working with the original project. The repository organizes translated articles, diagrams, and examples in a way that mirrors the structure of the original codebase, helping users correlate documentation with the actual implementation. It also includes localized explanations of conceptual topics such as agent reasoning, message handling, workflow design, and best practices.
    Downloads: 5 This Week
    Last Update:
    See Project
  • 15
    DeepSeek Harness Desktop

    DeepSeek Harness Desktop

    Open-source Windows desktop client and GUI for DeepSeek Harness

    DeepSeek Harness Desktop is an open-source AI development environment that brings DeepSeek Harness capabilities to a graphical desktop interface. It supports AI conversations, code editing, project navigation, and Git operations. Users can organize development projects and execute tasks through configurable AI agents. Its extension ecosystem includes reusable skills, plugins, and community bundles. Multi-agent collaboration enables specialized models to coordinate complex workflows. Browser and computer automation tools can perform approved interactions with websites and desktop applications. The application also supports SSH connections, remote access, and importing Claude Code or Codex projects. Additional features include model switching, token usage monitoring, customizable themes, and protected application updates.
    Downloads: 4 This Week
    Last Update:
    See Project
  • 16
    baoyu-design

    baoyu-design

    Run Claude Design locally as an Agent Skill

    baoyu-design is an Agent Skill that lets local coding agents produce polished visual design artifacts. It packages Claude Design-style methodology for environments such as Cursor, Claude Code, Codex, Claude Desktop, and other file-capable agents. The skill can generate UI mockups, prototypes, wireframes, landing pages, dashboards, mobile app screens, and slide decks as self-contained HTML. It keeps outputs inside the local project, so artifacts can be versioned, edited, previewed, and refined without uploading work to a separate design website. The repository includes core design instructions, harness-specific references, built-in skills, starter components, and local preview guidance. It is useful for developers and designers who want agent-assisted product design inside their own editor workflow.
    Downloads: 4 This Week
    Last Update:
    See Project
  • 17
    Agent Skills

    Agent Skills

    Production-grade engineering skills for AI coding agents

    Agent Skills is a collection of production-oriented engineering workflows designed for AI coding agents. It packages senior software-development practices into structured Markdown skills that can be loaded into many agent systems. The collection contains 24 skills spanning project definition, planning, implementation, testing, debugging, review, security, documentation, and delivery. Each workflow includes explicit steps, verification gates, and safeguards against skipping important checks. A meta-skill helps agents identify which workflow best matches the current task. The skills can be installed in supported coding tools or copied into system prompts and project instruction files. The repository is designed to make agent-assisted engineering more repeatable, disciplined, and auditable.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 18
    Archify

    Archify

    Agent skill for beautiful, verifiable architecture, workflow

    Archify is an agent skill and rendering system for turning codebases or system descriptions into polished technical diagrams. It works with coding agents such as Claude Code, Codex CLI, Cursor, and OpenCode. Agents generate typed JSON representations that Archify deterministically compiles into self-contained HTML and SVG. It supports architecture, workflow, sequence, data-flow, and lifecycle diagrams. Interactive viewers provide search, route tracing, upstream and downstream exploration, guided stories, themes, and presentation controls. Built-in validation checks structure, layout, routes, labels, and exports before a diagram is delivered.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 19
    EAC Desktop

    EAC Desktop

    Dedicated to the Harmonious Coexistence of Hundreds of DSH Plugins

    EAC Desktop (Embracing All Creation) is an open-source AI agent workspace built on DeepSeek Harness. It combines conversations, project files, tool execution, and plugins in a unified desktop environment. Users can assign tasks within project directories and inspect or restore file changes. The application bundles its runtime components to simplify installation and setup. Its extension system supports plugin discovery, installation, activation, and management. A protection center provides environment health checks, snapshots, and rollback capabilities. Context compression helps maintain longer AI conversations. Built with Tauri and a modular architecture, EAC Desktop also offers customizable skins, isolated environments, and native system tray integration.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 20
    html-ppt

    html-ppt

    AgentSkill with 24 themes, 31 layouts, 20+ animations

    html-ppt-skill is an AI-oriented skill designed to generate presentation slides using HTML as the underlying structure instead of traditional PowerPoint formats. It enables users to create visually structured, web-based slide decks that can be rendered in browsers or converted into presentation formats. The system focuses on translating structured ideas into clean layouts, combining content organization with lightweight styling. It integrates well with AI workflows, allowing automated generation of presentations from prompts or documents. The approach emphasizes flexibility, enabling customization through standard web technologies like HTML and CSS. It is particularly useful for developers and creators who prefer programmable presentation pipelines. Overall, it bridges the gap between web development and presentation design.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 21
    web-access

    web-access

    Skill for installing full networking capabilities for Claude Code

    web-access is a tool designed to give AI agents structured and controlled access to web content, enabling them to retrieve, navigate, and process information from online sources in real time. It abstracts common web interactions such as page loading, data extraction, and navigation into reusable functions that can be invoked by agents. The system emphasizes safety and control, likely including mechanisms to manage permissions, rate limits, and content filtering. This allows agents to operate within defined boundaries while still benefiting from dynamic, up-to-date information. The architecture supports integration with broader agent frameworks, making it a key component for building systems that require external knowledge. It is particularly useful for tasks like research, monitoring, and automated data collection. Overall, web-access extends the capabilities of AI agents by connecting them to the live web in a structured and reliable way.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 22
    DashiAI PPT Skill

    DashiAI PPT Skill

    An AI-agent skill that generates browser-editable presentations

    DashiAI PPT Skill is an AI-agent skill for generating editable presentation decks from documents, briefs, or plain requests. It creates a browser-based HTML deck that opens locally and includes an editing console on every page. Users can change text, layouts, charts, images, palettes, module counts, and page transitions after generation. The project includes 12 visual themes and more than 1,000 layout pages for reports, pitches, research, technical proposals, and business reviews. It can export decks as offline HTML, PDF, or real editable PPTX files. The skill is designed for local agents that can read files, write files, run shell commands, and use Node.js.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 23
    Tiledesk Server

    Tiledesk Server

    Tiledesk Server is the main API component of the Tiledesk platform

    Tiledesk Server is the backend component of the Tiledesk platform, providing a comprehensive open-source live chat system with integrated chatbot capabilities for customer support and engagement.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 24
    Anatomy

    Anatomy

    Agent skill for creating detailed, interactive isometric illustrations

    Anatomy is an open-source AI agent skill that creates detailed, interactive isometric illustrations of machines, technical concepts, and complex systems. It transforms abstract ideas into visual explanations using carefully constructed mechanical objects. The software generates polished SVG graphics with realistic shading, precise geometry, and animated components. It supports WebGL shaders for effects such as fire, water, lighting, and steam. An experimental 3D mode enables moving parts to rotate and interact in three-dimensional space. Users can export illustrations as standalone HTML pages, SVG files, or React components. Anatomy integrates with Claude Code, Codex, OpenCode, Antigravity, and MiniMax Code, making it useful for technical documentation, educational content, and interactive presentations.
    Downloads: 1 This Week
    Last Update:
    See Project
  • 25
    Codex plugin for Claude Code

    Codex plugin for Claude Code

    Use Codex from Claude Code to review code or delegate tasks

    Codex plugin for Claude Code is an integration layer that connects OpenAI Codex-style capabilities with agent-based coding environments, enabling seamless execution of coding tasks through structured plugins. The project is designed to extend the functionality of coding agents by allowing them to delegate tasks to Codex or similar models in a controlled and modular way. It likely provides abstractions for handling code generation, editing, and analysis while maintaining consistency across workflows. The system emphasizes interoperability, allowing developers to plug Codex capabilities into broader agent ecosystems without rewriting core logic. It may also include mechanisms for managing execution context, permissions, and tool access, ensuring that generated code can be safely applied. This makes it particularly useful for complex development pipelines where multiple agents or tools need to collaborate.
    Downloads: 1 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • 2
  • 3
  • Next