Directory
Published directory entries matching your search.
Agentic Signal is an open source visual AI agent workflow automation platform with local large language model (LLM) integration. It lets users build intelligent workflows via a drag-and-drop interface without requiring cloud dependencies. The repository includes a demo video, feature list, and visual workflow builder documentation.
A research repository examining how agentic AI coding assistants work, covering reconstructed prompt patterns, agent coordination and security classification. It documents design patterns such as system prompts, sub-agent coordination and permission mechanisms, described as approximations based on observation rather than verbatim copies. It aims to help AI engineers and researchers learn from these architectural patterns.
AgenticSeek is a voice-enabled AI assistant presented as a local alternative to Manus AI. It autonomously browses the web, writes code and plans tasks while running entirely on the user's hardware without cloud dependency. It selects agents for tasks and is described as tailored for local reasoning models. The voice and speech-to-text functionality is noted as in progress.
An autoagentic AGI that is self-evolving and modular.
Agentlas-OS is a GitHub project for an agent operating system that maintains a central hub of specialist agents and spins up temporary orchestrators for individual tasks. It is built with a local-first design and works with any AI model.
AgentMail is an email provider built for AI agents. It offers real inboxes through an API, allowing users to create, send, receive, and search email messages via a REST API, intended for autonomous agents and agentic workflows. A free tier is available without a credit card.
AgentPilot is a workflow automation platform for creating, organizing and executing AI workflows, ranging from a single LLM to complex AI-driven workflows. It offers an interface for designing workflows and chatting with them in real time, with branching chats and graph workflows supporting parallel execution. Workflows can be scheduled using natural language expressions of time.
The easiest, and fastest way to run AI-generated Python code safely.
Agents is an open-source framework for data-centric, self-evolving autonomous language agents. It introduces agent symbolic learning, which treats an agent pipeline like a computational graph and uses prompt-based loss, back-propagation and weight updates to train agents. The project also supports optimizing multi-agent systems and was updated to Agents 2.0 with agent learning and evaluation support.
Discover and explore AI agents for various tasks and industries. Find the perfect AI assistant for your business and personal needs.
AGENTS.inc provides autonomous AI agents for enterprise marketing, sales and market intelligence, offered as Agents-as-a-Service. Two deployment models are offered: agents hosted and maintained by the company, or deployed into the customer's own infrastructure. The company states its agents are grounded in customer systems of record and that outputs carry source provenance.
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
Start building LLM-empowered multi-agent applications in an easier way.
AgentSeer is a Hugging Face Space by holistic-ai that helps users understand how AI agents work by showing their decision-making processes as visual diagrams. Users can upload or input AI agent information to see how different actions are represented.
Agentset.ai is an open-source platform for building AI chat and search applications. It provides production-grade retrieval-augmented generation (RAG) capabilities without requiring specialized RAG expertise, and includes features such as multimodal support, automatic source citations, metadata filtering, support for over 22 file formats, and JavaScript and Python SDKs.
AgentsMesh is an AI agent workforce platform for running AI coding agents across self-hosted machines. Runners advertise their capacity, allow agents to be scheduled onto chosen or available runners from a pool, and each agent runs in its own pod with a dedicated Git worktree. All control happens from one console.
AgentVerse is designed to facilitate deployment of multiple LLM-based agents in various applications. It provides two frameworks: task-solving, which assembles multiple agents as an automatic multi-agent system to collaboratively accomplish tasks, and simulation, which lets users set up custom environments to observe or interact with multiple agents.
A newsletter post by Jon Stokes introducing the concepts behind AgentGPT, BabyAGI, LangChain and LLM-powered agents. It covers core agent concepts, how LLMs make plans, chain of thought reasoning, action planning, and example prompt-response pairs.
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
An article by Benedict Evans discussing generative AI, Large Language Models and ChatGPT as a generational change in software automation, and considering what this means for employment and jobs. It compares the current wave with 200 years of past automation and asks whether new jobs will replace those displaced.
A Hugging Face Space created by Agents-MCP-Hackathon that analyzes uploaded artwork images to provide details on artistic style, historical context, symbolic meanings, and technical characteristics. Users can submit optional specific questions to receive more targeted analysis.
A Hugging Face Space created by Agents-MCP-Hackathon that functions as an interactive AI career advisor powered by Gemini. It provides tailored career advice, skill assessments, and personalized learning paths based on user-submitted background information, interests, and uploaded resumes. The space is currently in a sleeping state due to inactivity.
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
A Hugging Face Space created by Sanchay3011 that allows users to upload datasets for AI-assisted data cleaning, visualization, modeling, and automated report generation, providing data insights and automated outputs. The space is currently in a sleeping state due to inactivity.
