[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
OramaCore is the complete runtime you need for your projects, answer engines, copilots, and search. It includes a fully-fledged full-text search engine, vector database, LLM interface, and many more utilities.
Agentic First OpenAPI & AsyncAPI Documentation. Works 100% offline, straight from disk, shareable or publisable to any static host. AI and agent output built in, Built in API Catalog generation.
Make your Magento 2 catalog readable to AI. Generates spec-compliant llms.txt, llms-full.txt, llms.jsonl and on-the-fly Markdown page mirrors so ChatGPT, Claude, Gemini & Perplexity can ingest your store efficiently. Multi-store, Page Builder-aware, large-catalog safe. CLI, cron, admin. Free & MIT.
A Convex component that auto-generates, caches, and serves llms.txt, agents.md, and llms-full.txt from your Convex backend. Register it with app.use(agentReady), drop the widget into your React or Svelte frontend, and your app is discoverable by AI agents. No external hosting required.
A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.