Category
Explore by categories
Reference architectures and microservices for building GPU-accelerated vision agents that enable natural-language video search, long-video summarization, visual Q&A, and alert verification. Integrates NVIDIA NIM models, embeddings, VLMs/LLMs, and agent workflows for deployable video-analytics stacks.
Connects AI agents to 50+ apps and databases — Notion, Slack, Salesforce, GitHub, Jira — then continuously syncs and indexes their data behind one search API, with auth, ingestion, and retrieval exposed via MCP, REST, and SDKs.
Provides a shared runtime that composes, extends, and observes services in real time by modeling capabilities as discoverable workers, functions, and triggers. It collapses separate integration surfaces (queues, cron, HTTP, observability) into one live catalog so agents and services can call and trace each other immediately.
Runs stateful AI agents as Cloudflare Durable Objects — each keeps its own storage and lifecycle, hibernating when idle and waking on demand. Adds WebSocket state sync, type-safe RPC, resumable LLM streaming, MCP roles, and durable workflows.
Spins up sandboxed VMs and containers (macOS, Linux, Windows, Android) that an AI agent can fully control through one unified SDK, cloud or local, plus a benchmark suite and background drivers that automate native apps without grabbing the cursor.
Runs a self-hosted meeting bot and transcription API that joins Google Meet, Teams and Zoom and streams speaker-attributed transcripts in real time. Compiles meetings into a git-backed Markdown workspace and runs sandboxed agents on your infrastructure; Apache-2.0 and air-gap capable.
High-performance CUDA tensor-core GEMM kernel library for LLM workloads: supports FP8/FP4/BF16, fused Mega MoE and MQA scoring, and runtime JIT-compiled kernels. Targets NVIDIA SM90/SM100 and PyTorch—for teams working on low-level GPU kernel optimization.
Provides high-throughput, low-latency GPU communication kernels for Mixture-of-Experts (MoE) and expert-parallel workloads, with NVLink↔RDMA-aware forwarding, FP8/BF16 support, and low-latency RDMA hooks for inference decoding.
An asynchronous, high-throughput framework for large-scale reinforcement learning and agentic training that scales to 1T+ MoE models and 1000+ GPUs, with native verifiers integration, end-to-end SFT/RL/evals, and Slurm/Kubernetes deployment; requires NVIDIA GPUs.
Optimized MLA (Multi-head Latent Attention) decoding kernels powering DeepSeek-V3/V3.2 inference on Hopper and Blackwell GPUs. Dense decoding reaches ~3000 GB/s and 660 TFLOPS on H800; the sparse path stores the KV cache in FP8.
Keeps codebases, PDFs, Slack, and docs continuously indexed for RAG and knowledge graphs by recomputing only what changed, not the whole dataset. You declare target state in Python; a Rust engine maintains it with per-row lineage back to the source.
Lets AI agents like Claude Desktop and Cursor explore schemas and run SQL across Postgres, MySQL, MariaDB, SQL Server, and SQLite through one MCP server. A read-only mode stops the agent mutating data; no per-database drivers to wire up.