High-performance runtime for real-time multimodal generation and world models—streaming inference, stateful sessions, and distributed GPU execution.
6 files for Claude Code, Codex, OpenCode and Gemini CLI: add-new-pipeline, optimize-pipeline, profile-pipeline, TeleFuser AGENTS.md and 2 more — 2,177 tokens loaded in every session.
AGENTS.md A 4 tok CLAUDE.md A 2,169 tok GEMINI.md A 4 tok .claude/skills/add-new-pipeline/SKILL.md A 63 tok .claude/skills/optimize-pipeline/SKILL.md A 64 tok .claude/skills/profile-pipeline/SKILL.md A 49 tok These files are Tele-AI/TeleFuser's own configuration — they tell Claude Code, Codex, OpenCode and Gemini CLI how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.