AI Agents Directory

The world's first fully autonomous AI software engineer, capable of handling complex multi-step programming tasks, environment configuration, and bug refactoring remotely.

An autonomous coding agent that runs inside VS Code. Cline can read/write files, edit settings, install packages, and execute terminal commands with user permission.

A popular command-line AI coding agent that allows programmers to edit code in local git repositories, automatically generating git commits on edit completions.

Anthropic's official terminal-based coding assistant. Claude Code executes CLI commands, inspects local directories, writes files, and performs fast semantic code searches.

An AI-first code editor branched from VS Code. Features composer multi-file editing, chat workspace commands, and autocomplete.

An AI IDE designed around the concept of a 'FlowState', allowing seamless transitions between autonomous editing, interactive chats, and terminal executions.

Formerly OpenDevin, OpenHands is a highly autonomous open-source agent platform executing complex coding workflows within sandboxed Docker containers.

Anthropic's collaborative enterprise agent. Integrates directly into slack workspaces and dashboard portals to review team documentation, draft releases, and execute workflows.

OpenAI's assistant agent, utilizing custom GPT tools, python code executors, and search engines to manage workflows, files, and queries autonomously.

An autonomous web agent capable of using a browser to log in, fill forms, execute shopping carts, and fetch data from web portals.

An autonomous business helper designed to handle daily administrative tasks, email management, meeting coordination, and CRM updates.

Microsoft's enterprise platform for building custom, conversational agent copilots connected to internal corporate databases, SharePoint repositories, and CRM platforms.

An advanced data analysis agent capable of writing Python scripts, generating graphs, cleaner data sheets, and building regression graphs automatically.

An AI search engine that acts as a research agent, scanning over 200 million academic papers to synthesize scientific findings and deliver consensus consensus reports.

Snowflake's warehouse-native AI platform, enabling users to execute natural language database queries (Text-to-SQL), perform classification, and run sentiment analyses directly inside secure database tables.

An enterprise search-driven business intelligence tool that uses generative AI to translate natural language queries into SQL database lookups and generate interactive business dashboards.

An open-source library built by LangChain to compile stateful, multi-agent systems with cyclic execution parameters, perfect for complex autonomous behaviors.

A popular developer framework for building collaborative multi-agent workspaces where agents are assigned specific roles (e.g. Writer, Researcher) and coordinate to execute projects.

Microsoft's framework for orchestrating multi-agent conversations. Supports customizable conversation rules, Python code execution, and human-in-the-loop triggers.

A data framework designed to connect private data sources to LLMs, featuring advanced RAG tools, semantic vector database loaders, and data parsing agents.

The pioneer framework for building LLM applications, offering standardized abstractions for prompts, models, vector databases, memory, and chain structures.

A workflow automation platform with a node-based visual editor, incorporating specialized AI nodes for prompt chaining, vector databases, and agent memory.

An open-source LLM app development platform combining visual workflow design, RAG management, and monitoring dashboards inside a unified developer UI.

Formerly known as Vext, Gumloop is a powerful visual workflow automation builder that allows developers to run complex web scraping, file parsing, and bulk prompt jobs visually.

An open-source visual node tool built on LangChain, letting developers build LLM pipelines, prompt trees, and RAG systems through simple drag-and-drop actions.

LangChain's production platform for tracing, debugging, testing, and evaluating agent behaviors, providing complete visibility into prompt histories and token counts.

An open-source AI evaluation and observability platform, enabling developers to run local trace databases, audit RAG queries, and detect hallucinations using standard OpenTelemetry protocols.

An open-source evaluation framework for unit testing LLM applications. DeepEval acts like a 'pytest' for AI systems, evaluating toxicity, accuracy, and hallucination scores.

An enterprise-grade software stack for evaluating, logging, and optimizing AI applications, helping teams test prompts and track logs in unified dashboard systems.