| Machine Learning | 56 |
|---|---|
| Computer Vision | 0 |
| Data Science | 19 |
| NLP & LLMs | 64 |
| AI Agents | 66 |
| MLOps | 37 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Deep, repeated, well-engineered work in this domain.
16 public repositories → 6 with AI work, evaluated. The other 10 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
38% of Atlas Score
NexusOS-Ultra is a local-first AI workspace that integrates a Next.js dashboard, FastAPI gateway, LLM router, file mesh, self-evolution daemon, and Skyvern-based browser automation to provide a private AI environment for macOS users.
29% of Atlas Score
The repository implements an autonomous AI agent platform that integrates multiple LLMs, browser automation, code execution, and shell commands via a FastAPI-based web interface. It includes features such as task planning, decomposition, and real-time chat interaction.
15% of Atlas Score
AgentFlow Relay is a full-stack agent orchestration platform that provides a backend for agent registration, task routing, and integration with messaging platforms (Telegram, WhatsApp, Discord, Slack) and LLMs (via Ollama). It includes a frontend dashboard, Python SDK, and deployment via Docker Compose.
8% of Atlas Score
Nexus Render Hybrid is a web-based AI agent dashboard that provides a unified interface for multiple AI service providers (including local Ollama) with extensible skills, memory, and fallback routing.
6% of Atlas Score
The repository provides a Telegram-triggered web automation agent that uses a stealth Playwright browser and a cognitive loop (OBJECTIVE -> HYPOTHESIS -> OBSERVATION -> PIVOT) to perform web-based tasks. It relies on the Gumloop platform for high-level agent logic and includes skills for browser automation, along with deployment guides for various platforms.
5% of Atlas Score
Agent Brain is a central skills registry and project management system for AI agents, providing tools to manage skills, track work via a kanban board, and route intents to appropriate skills using live research.
