🐒 Hebo Gateway 0.6 Prompt caching support across Google, Anthropic, OpenAI, and Amazon models. Save 90% on your LLM calls by hosting your own gateway. Release notes: github.com/8monkey-ai/heb… Got feedback or ideas for 0.7? Drop them in the repo! 🙌 #ai #llm #opensource

Gemini 3.1 Flash Lite Preview beats 2.5 Pro in overall performance. BUT what happend to tool calling 🤔

GPT-5.4 better than your parents using a computer

🐒 Hebo Gateway 0.7 We just added standardized Service Tiers across: OpenAI, Bedrock, Groq, Vertex The hardest one? Gemini. It exposes tiers via HTTP headers instead of request fields. Hebo normalizes all of this so you can just write: `serviceTier: "priority" / "flex" /

Most observability stacks look like: SDK → queue → workers → transformation → database Ours: SDK → GreptimeDB Why we chose Greptime over ClickHouse for AI observability 👇 hebo.ai/blog/260316-gr…

Feels like the AI SDK team is heads down on v7, but a number of PRs have been sitting unattended for 2+ weeks. Any good way to get eyes on them?

My workflow these days: 1/ Wake up and have Codex in VS Code draft the ticket with all the needed context 2/ Hand it to Claude on GitHub Web to start building 3/ Ping-pong between CodeRabbit and Claude on GitHub Mobile during the commute 4/ Clean things up manually in VS Code at

Codex controlling Paper via MCP feels like magic.

Most LLM infra treats calls as stateless. But real apps need history, memory, traceability 🍌 This is our first step toward fully stateful /responses: 💬 /conversations API (OpenAI-compatible) 🪣 Pluggable storage (memory, Postgres, SQLite, MySQL, Greptime ) 🧠 Support for

By now you can basically predict Claude Code / Cowork roadmap from what Jarred Sumner is working on 👇 1/ Bun.Cron → background agents doing scheduled work 2/ Bun.WebView → agents that see + iterate via screenshots 3/ ... what's next? 👉 Bun is becoming the runtime for

So Google just released a model that is worse than what OpenAI released a year ago. I don’t get the buzz about Gemma 4 🤔