AI Train2024
Trains a sub-100M-parameter LLM from scratch — pretraining, SFT, LoRA, DPO/RLHF, and distillation, sized from ~26M up to ~100M-plus dense and MoE. Headline figure: the ~64M minimind-3 variant's SFT stage runs 1 epoch in ~2h and ~3 RMB on one NVIDIA 3090.
AI Agent2024
Stores agent memory as human- and agent-readable Markdown files with wikilinks instead of an opaque vector DB. Auto Memory/Resource/Dream jobs distill conversations into long-term notes, and hybrid wikilink + BM25 + embedding search retrieves them.
AI Agent2024
Gives LLM agents self-editing memory that persists across sessions, so they keep learning about a user instead of resetting each chat. Model-agnostic: bring your own LLM while it handles the memory and agent state, run via API or open source.
AI Coding2024
Generates and deploys full-stack React apps from natural-language prompts on Cloudflare’s platform, combining AI code generation, previews, Workers, Durable Objects, and containers.
AI Client2024
Runs AI models on user devices with native SDKs, optimized model management, hardware acceleration, and OpenAI-compatible APIs for apps that need offline, private inference.
AI Infra2024
Lets Python developers write tile-based parallel kernels for NVIDIA GPUs, generating CUDA Tile IR while staying close to Python syntax for custom GPU operations.
AI Infra2024
A compact domain-specific language for writing high-performance GPU/CPU kernels (GEMM, FlashAttention, sparse kernels) with Python-like syntax. It provides tiling/pipelining primitives, a TVM-based compiler and multiple backends (CUDA/CuTeDSL, NVRTC, WebGPU, Metal, Ascend) for operator-level performance work.
AI Agent2024
Runs autonomous AI-agent workforces where each agent, skill, and company process lives as version-controlled code you own. Agents act in isolated sandboxes and submit deliverables for human review, with 3,000+ connectors plus MCP support.
AI Train2024
Parses, generates, and filters training data from noisy sources like PDFs and weak QA, then feeds it into LLM pre-training, SFT, RL, or RAG cleaning. Ships 100+ operators and ready-made pipelines for text, reasoning, Text2SQL, and agentic data.
Embodied AI2024
Agentive operating system for physical robots that lets developers compose agent-native modules in Python to connect perception, spatial memory, and control across humanoids, quadrupeds, drones, and simulators.
A GitHub repository of learning notes and code dedicated to ML + SYS (machine learning systems). It collects tutorials, code walkthroughs and engineering notes on RLHF, distributed training (FSDP, Megatron), inference and scheduling (SGLang, vllm), quantization, CUDA/GPU optimization, system design, and practical engineering.
MCP Server2024
Official remote MCP servers that let AI agents read and change Cloudflare config in natural language — managing Workers and bindings, querying observability and DNS analytics, searching docs. Each capability is a separate scoped server.