huggingface.co
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
Directory
Search results
Published directory entries matching your search.
Filters
huggingface.co
A Hugging Face Space by bstraehle that uses a team of AI agents to write code. Users enter an OpenAI API key and describe a programming task, and the app returns the needed code as formatted text. It is built with Microsoft AutoGen.
huggingface.co
Multi-Agent AI - Coding is a Hugging Face Space created by harry85, duplicated from the bstraehle/multi-agent-ai-autogen-coding space. It uses the Microsoft AutoGen multi-agent AI system, allowing users to input an OpenAI API key and programming task to generate formatted code solutions via a team of AI agents. The space is currently sleeping due to inactivity.
github.com
Uses AI agents to complete tasks, coordinate tools or automate multi-step workflows.
github.com
Notte is the fastest, most reliable Browser Using Agents framework.
github.com
Ombre is an open-source AI infrastructure layer. It runs eight specialized agents on every request to handle security, caching, memory, hallucination detection, and tamper-proof audit trails. It is installed with one line of code, and user data never leaves the user's server.
github.com
Typed graph database where agents branch and merge like Git. S3-native, Rust, traversal + vector + BM25 in one runtime.
github.com
onUI is a browser extension for Chrome, Edge and Firefox with a local MCP bridge, used to annotate or draw on any web UI and export structured context for AI agents. Annotations require no app code changes; per-tab control is off by default.
github.com
Open-source project that supports AI agents, automated workflows, orchestration, or delegated tasks.
github.com
An Open Platform for Language Agents in the Wild.
github.com
Open-source project that supports AI agents, automated workflows, orchestration, or delegated tasks.
github.com
OpenLIT is an open-source agent harness engineering platform built on OpenTelemetry. It provides tracing, evaluations, guardrails, prompt and context management, and cost and GPU monitoring for the harness around AI agents and coding agents. It is free to self-host under Apache 2.0 and is described as working with many models, frameworks and harnesses.
openwork.bot
Openwork describes a system where AI agents called Claws execute tasks while human Pilots oversee them, forming Crews that complete missions. Mission rewards are escrowed on-chain on Base with a 7-day submit deadline and 3-day verify period. Pilots set oversight levels and approve checkpoints; participants earn $OPENWORK tokens, with a stated 3% platform fee.
github.com
Orkas is an open-source, local-first AI desktop app. A commander LLM directs specialist sub-agents and runs installed coding CLIs including Claude Code, Codex, OpenCode, OpenClaw, and Hermes as local sessions. Its agents self-evolve via reflection and skill crystallization, supports bring-your-own keys, and is compatible with macOS, Windows, and Linux.
osaurus.ai
Osaurus provides AI agents that run locally on a computer rather than in a cloud. Agents work from files, keep memory on the computer, and request approval before editing files. A privacy filter can remove identifying details before cloud use. Osaurus is free and MIT licensed; Workspaces starts at $20 per workspace per month.
github.com
Ouroboros is an open-source, general-purpose AI agent whose identity, durable memory, and history continue across tasks and restarts. It coordinates a live swarm of specialist agents, works on external projects, and can rewrite its own code, architecture, prompts, tools, and dependencies. It runs as a native desktop app or a headless CLI, keeping its repository, memory, and history on the local machine.
github.com
Open-source project that supports AI agents, automated workflows, orchestration, or delegated tasks.
github.com
Open-source project that supports AI agents, automated workflows, orchestration, or delegated tasks.
playwright.dev
A web automation and testing framework for apps, scripts, and AI agents. It offers a test runner with auto-waiting and assertions, browser automation across Chromium, Firefox, and WebKit, and a Model Context Protocol server for AI agents.
github.com
Flappy is an SDK for building applications and agents that use large language models, organized as a monorepo with libraries in several programming languages. The repository was archived by its owner on Jun 13, 2024, and the project was described at the time as still under development.
potpie.ai
Potpie is an AI-native SDLC automation platform. It maps how systems work into a context graph and runs AI agents on it inside the user's own VPC, according to the page. The documentation page describes creating and updating documentation from connected product knowledge.
publish7.com
Publish7 is a marketing tool offering AI agents for tasks such as backlink ideas, competitor landscape analysis, company research, community engagement ideas and content ideas. The site states that a free trial is available without a credit card. Paid plans list credit allowances and features such as analytics, priority processing and email support.
pydantic.dev
Pydantic AI is a Python-focused AI development framework documented by Pydantic. It supports building agents, realtime voice tools, image generation, and embeddings, with end-to-end typed interfaces for all supported models and providers.
github.com
Pydantic AI is a Python AI SDK described as a typed, extensible agent loop that works with any model. It covers agents, realtime voice, image generation and embeddings. Separate packages include Pydantic Evals, Pydantic Graph, genai-prices and Monty. The repository is MIT licensed.