Curated developer resources that demonstrate building RAG systems, multi-agent workflows, and memory-augmented AI using Oracle AI Database and OCI — includes end-to-end reference apps, notebooks, guides, and workshops for hands-on prototyping.
Transforms websites into structured data for AI agents and analytics. Uses configurable graph-based scraping pipelines and LLM integrations, available as a self-hosted Python library or a managed cloud API with SDKs.
Runs AI-generated code in isolated, elastic sandboxes with SDK, API, and CLI access for agent workflows that need stateful execution and environment control.
Asynchronous, reverse-engineered Python API for programmatic access to the Google Gemini web app — supports persistent cookie auth, streaming text, image/video/audio generation, deep-research workflows, model selection, and a CLI for automation and chatbots.
Turns repeatable business workflows into versioned agent skills that can run in Refly, ship to coding agents, or be exposed as APIs and webhooks.
Memory engine that lets AI apps remember users across conversations: it extracts facts, tracks updates, resolves contradictions, and auto-forgets stale info, returning context in ~50ms. Tops the LongMemEval, LoCoMo and ConvoMem memory benchmarks.
SDK for building browser-based AI agents: expose Playwright-style APIs plus natural-language primitives (act/observe/extract) with self-healing actions, token-efficient accessibility trimming, and runtime extension next to the browser. Supports TypeScript, Python, and Go.
Turns any website into clean markdown, structured JSON, or screenshots through a single API — handling JavaScript rendering, rotating proxies, rate limits, and full-site crawling so LLM apps get web data without running scraping infrastructure.
BYOK desktop app working as a universal MCP client: run any MCP server against OpenAI, Anthropic, Gemini, Grok, Ollama and 10+ providers. Also offers prompt-anywhere, AI text commands, local-file RAG, media generation and voice input.
Runs open LLMs entirely on your own machine — discover and download models from Hugging Face, chat in a desktop GUI, or expose an OpenAI-compatible local server. Native Apple MLX and llama.cpp backends; headless deploy via llmster.