NVIDIA / Megatron-LM

stablyai / orca

github.com

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS. (4,068 stars)

jingyaogong / minimind

github.com

🧠 Train a 64M-parameter LLM from scratch in just 2h! (7,554 stars)

affaan-m / ECC

github.com

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. (37,178 stars)

anthropics / skills

github.com

Public repository for Agent Skills (20,590 stars)

ruvnet / ruflo

github.com

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated (8,404 stars)

livekit / livekit

github.com

End-to-end realtime stack for connecting humans and AI (2,306 stars)