Flisk starts microservices on your machine. Not a deploy tool, not a Compose file. Production stays on Helm.
AI-Atlas score
| Machine Learning | 57 |
|---|---|
| Computer Vision | 17 |
| Data Science | 36 |
| NLP & LLMs | 61 |
| AI Agents | 69 |
| MLOps | 34 |
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.
67 public repositories → 24 with AI work, evaluated. The other 43 (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.
21% of Atlas Score
This repository maintains an up-to-date curated list of open-source tools for training and shipping small specialist models, using a Node.js script to fetch live metadata and regenerate the README.
18% of Atlas Score
This repository trains and evaluates a small language model (Qwen2.5-Coder 1.5B) to generate Flisk configuration files, comparing its performance to larger models and analyzing failure cases.
13% of Atlas Score
Flisk is a command-line tool that orchestrates local multi-service development, generating Dockerfiles, Compose files, and Traefik routes from service.json manifests, and integrates with AI agents via the Model Context Protocol.
8% of Atlas Score
This repository provides a portal for interacting with an AI model that repairs Flisk service.json files, featuring GitHub authentication, API key management, rate limiting, and deployment options for local (Ollama) and cloud (Cloudflare Workers) environments.
8% of Atlas Score
Run My Agents is a plugin for Claude Code that prevents concurrent file edits by multiple AI coding sessions using a file-based claims system. It provides a web interface and native Mac app to monitor and manage agent sessions.
7% of Atlas Score
Helpdock provides a self-hosted help center and MCP server for any public GitHub repository, enabling developers to expose their documentation to AI agents via search and question-answering endpoints.
