4.7 out of 5 stars
(76 Ratings)
KrakenD is a high-performance API Gateway optimized for resource efficiency, capable of managing 70,000 requests per second on a single instance. The stateless architecture allows for straightforward, linear scalability, eliminating the need for complex coordination or database maintenance.
It supports various protocols and API specifications, with features like fine-grained access controls, data transformation, and caching. Unique to KrakenD is its ability to aggregate multiple API responses into one, streamlining client-side operations.
Security-wise, KrakenD aligns with OWASP standards and doesn't store data, making compliance simpler. It offers a declarative configuration and integrates with third-party logging and metrics tools. With transparent pricing and an open-source option, KrakenD is a comprehensive API Gateway solution for organizations prioritizing performance and scalability.
Learn more about KrakenD
4.8 out of 5 stars
(282 Ratings)
TelemetryOS is a vertically integrated platform for connected screens, kiosks, and screen applications. Purpose-built Node hardware, a hardened Edge operating system, Studio cloud, an integrated video CDN, and an application runtime work together so every display can show the right content, respond to real-world conditions, and scale from one location to thousands.
Start with what every screen network needs: playlists, dayparting, calendar schedules, priority overrides, and a media library delivered through adaptive 4K streaming. Content caches locally so playback continues through outages. Proof-of-play reporting, screenshot capture, and audit logs verify what ran, where, and for how long. Design multi-zone layouts, video walls, and touch kiosks on a visual canvas, with scheduling built into each page and AI Assist to generate layouts from a prompt. Instant, scheduled, or CAP-triggered emergency overrides can preempt content on any screen or group.
When playlists are not enough, TelemetryOS runs full screen applications. Developers build in React and TypeScript with the TelemetryOS SDK, preview across aspect ratios, and publish from Git with staged rollouts and one-click rollback. Screens connect to POS, ERP, sensors, serial devices, and MQTT so menus, dashboards, and kiosks update from live business data. Fleet health monitoring, remote diagnostics, automatic OS updates, role-based access, SAML SSO, and SOC 2-aligned enterprise controls keep operations predictable at scale.
Use TelemetryOS for campaign walls and retail media, QSR menu boards and self-service kiosks, healthcare check-in and wayfinding, campus communications, production wallboards, hospitality directories, and corporate KPI displays. Node Mini, Node Pro, and Node Max cover single-screen 4K signage, multi-display apps, and on-device AI workloads—all managed from one console. Built on a decade of operating mission-critical screens, TelemetryOS powers tens of thousands of displays in 40+ countries with a 99.9% uptime SLA.
Learn more about TelemetryOS
LMCache
LMCache is an open source Knowledge Delivery Network (KDN) designed as a caching layer for large language model serving that accelerates inference by reusing KV (key-value) caches across repeated or overlapping computations. It enables fast prompt caching, allowing LLMs to “prefill” recurring text only once and then reuse those stored KV caches, even in non-prefix positions, across multiple serving instances. This approach reduces time to first token, saves GPU cycles, and increases throughput in scenarios such as multi-round question answering or retrieval augmented generation. LMCache supports KV cache offloading (moving cache from GPU to CPU or disk), cache sharing across instances, and disaggregated prefill, which separates the prefill and decoding phases for resource efficiency. It is compatible with inference engines like vLLM and TGI and supports compressed storage, blending techniques to merge caches, and multiple backend storage options.
Learn more about LMCache