Directory
AI agents and automation covers projects that let software plan tasks, call tools and run steps on its own. The listings span agent frameworks, browser automation tools, workflow builders and reference projects that show what is possible. Some are open repositories you run yourself, and others are hosted services or demos. The details that matter are the access each tool needs, how it handles failures and whether you can review each step before it runs. Because an agent can act with your accounts and data, review permissions carefully and test anything new in a safe setting before you give it access.
Boston Dynamics Spot is an agile mobile robot product from Boston Dynamics. It is designed to help organizations monitor and operate worksites, improving team safety and operational efficiency. Spot can be equipped with various payloads and add-ons for use cases including industrial inspection, safety and response operations, and digital twin data capture.
BrainSoup supports AI agents, automated workflows, orchestration, or delegated tasks.
Building Effective Agents is an Anthropic engineering publication that details the company's approach to developing reliable large language model (LLM) agents. It covers research on agent capabilities, safety considerations, technical frameworks, and practical guidance for developers, noting that simple, composable patterns are more effective than complex frameworks for successful agent implementations. It also references Anthropic's Claude Managed Agents.
CAJAL is a local scientific paper generator that runs entirely on the user's machine, connecting a local Ollama or LLM backend without hosted API calls. It produces seven-section papers from a research idea using an Ollama-compatible model.
AI based calling agents for outbound and inbound phone calls.
Camel Agents is a Hugging Face Space developed by camel-ai that launches an AI agent system capable of concurrent task processing. Users must provide an API key and specify the number of tasks to run at the same time to use the system.
Career assistant that combines intelligent job searching, resume matching, and cover letter generation using an agent-based architecture.
Cate is an infinite zoomable canvas for coding that places editor, terminal, and browser panels in a spatial workspace. It supports running agent CLIs in terminals, with panels shown on a canvas or dock and git worktrees for parallel branches.
ChatBotKit is a managed platform for building and running AI agents, described as usable from ready-made solutions without code. Agents can run on schedules and triggers, connect to tools, and operate across channels such as Slack, WhatsApp, web widgets and Zendesk. It also offers a Python SDK, integrations and product documentation.
Web framework to create vertical AI agents. FastAPI based, plugin system inspired to WordPress, admin panel, vector DB included.
Official plugin resources and examples for extending Claude-based workflows.
ClaudeClaw is a Claude Code plugin presented as a persistent agent orchestrator. It provides an always-on message loop, routing messages from Slack, WhatsApp and Telegram to Claude agents in isolated sandboxes, with structured memory, webhook triggers, per-group agent configuration and cost tracking. It is built on NanoClaw and uses a pluggable extension system.
Open-source project that supports AI agents, automated workflows, orchestration, or delegated tasks.
Auto-Magical CI/CD to streamline your ML workflow.
Open-source project that supports AI agents, automated workflows, orchestration, or delegated tasks.
ClevAgent is a pre-launch workspace for running and guiding AI agents. It is designed to manage efficiency and safety for agent operations, but is not yet open for public purchase or use.
Codel is a self-hosted autonomous AI agent that performs tasks and projects using a terminal, browser and editor. It runs in a sandboxed Docker environment, detects the next step automatically, can fetch web information through a built-in browser, and saves command history and outputs in a PostgreSQL database.
OpenAI’s platform for agentic coding workflows and automated software development tasks.
Codex CLI is a lightweight coding agent from OpenAI that runs locally in the terminal. It can be installed on Mac, Linux and Windows via standalone installers, npm or Homebrew, and can be used with a ChatGPT account or an API key.
Cognition operates Devin, described as an autonomous software engineer that plans, writes, tests, and ships production code inside existing workflows. The company also publishes FrontierCode, a benchmark intended to measure whether a model writes code a maintainer would merge. Cognition builds tools for software creation.
CompozyOS is an operating system for AI agents that plugs in existing agent CLIs such as Claude Code, Codex, Gemini CLI, and Cursor. The agents split work, hand tasks to each other, run automated jobs and loops, and share one project memory, steered from the browser. The v0.3 line is in beta, and the v0.2.15 product is deprecated.
ConnectOnion is a command-line agent harness. Its co command gives an AI agent access to accounts and tools including Gmail, Outlook, a logged-in browser, files, chat apps and other agents. A co rem feature links context from mail and coding sessions into local Markdown pages. Selected source content is sent to the configured model during investigation.
Contexto is a context engine plugin for long-running OpenClaw and Hermes agents. It stores full episodes and retrieves relevant context after the context window fills, instead of losing constraints to summaries. It separates topics with semantic clustering and surfaces explainable paths. Managed hosting is available, and a fully local setup is documented.
ContextQA is an AI test automation platform for enterprise applications and AI agents. It generates test cases, repairs broken selectors automatically, and supports web, API, cross-browser, and cross-device testing. It also offers MCP integration with Cursor and Claude Code.
