Libraries such as agent development kit (https://adk.dev/) provides abstraction over multiple LLM vendors, long-term memory (persistance + compaction) and allow us to manage subagents & their lifecycles. Vendor neutral memory & context management is a challenge as default long-term memory uses vertext AI (gemini) in ADK.
Similar to how Stripe is a middleman for payments across (fragmented) banks, they want to be a middleman for (fragmented) AI models as tokens are the new currency.
As AI agents/harness/human are spenders of tokens, enabling them to derisk from being locked to a specific model provider & allowing to (re)route to any model at anytime for better leverage in a single API, similar to how they are doing for payments.
Very very poor format support on Apple devices. I have this problem when re-encoding videos for re-upload to Discord, SimpleX, and other destinations which have iOS users.
Only fix seems to be ditching Apple. I can only recommend GrapheneOS for [Pixel] phones (never Samsung), and a favorite flavor of GNU/Linux for general purpose (me: Qubes OS). Apple wants to sell a beautiful but limited walled garden, for a premium price... not worth it!
You are creating content to share with mobile users. The onus is on you to go where the market is to reach those people.
Pixel phones are 4% of the market and bespoke Linux versions of that are a slim fraction of that slim fraction.
Most people are fine with the tradeoff of living in a walled garden and not playing unsupported formats. As a content creator who obviously wants to reach them, the problem is not the users.
Creating an AI native solution to manage workflows of my live streaming business (https://www.cheerarena.com)
Most workflow softwares are complex to extend & customize. Building an AI native, structured workflow orchestrator from scratch for agentic era.
As a starting point, have designed and implemented an AI native data store to store semantic linked structured input & output data of workflow steps/tasks. These structured input/output act as spec and guard rails for the workflow tasks.
From the blog " Gemini CLI spawns a new process within a pseudo-terminal in the background, leveraging the node-pty library...So how does this virtual terminal running in the background show up on your screen? Think of it like a video stream. Our new serializer takes a snapshot of the pseudo terminal at every moment—capturing every piece of text, every color, and even the cursor's position. These snapshots are then streamed to you, allowing you to see and interact with the terminal application in real-time. It's not just a stream of text; it's a live feed."
An MCP server exposes tools that a model can call during a conversation and returns results according to the tool contracts. Those results can include extra metadata—such as inline HTML—that the Apps SDK uses to render rich UI components (widgets) alongside assistant messages.
reply