ml-intern
Description
An open-source, autonomous AI agent by Hugging Face designed to function as a specialized Machine Learning Engineer. It handles the end-to-end ML lifecycle, including researching papers, writing code, running experiments, and shipping models to the Hugging Face Hub. [Intro](docs/ml-intern/README.md)
Related Tools
MastraAI
Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals
codesight
CLI token optimizer and AI context generator with built-in MCP server. Scans codebases to extract routes, schema, components, and dependencies, reducing AI context tokens by 9x–13x. Profiles for Claude Code, Cursor, Copilot, Codex, and Windsurf. Zero runtime dependencies.
Codex
OpenAI's lightweight coding agent. Supports the terminal CLI, VS Code/Cursor/Windsurf IDE extensions, Codex Web, and a Codex App/desktop app experience; it can understand and modify code directly. [Intro](docs/codex/README.md)
autoresearch
An autonomous AI agent for machine learning research by Karpathy. It can formulate hypotheses, modify training code, run experiments, and evaluate results autonomously to find performance improvements.
AnyGen
AnyGen is the AI assistant that truly "gets work done" for you. From writing and analysis to planning and reporting, it transforms your ideas into ready-to-use professional deliverables in minutes. [The AI Assistant Built for Work](https://www.anygen.io/task/LkA2pg7EXaVJkrgETSol5DelgEd)
agentscope
Agent-Oriented Programming for Building LLM Applications, Open-sourced by Alibaba