Fay is an open-source digital human framework that lets you freely pair LLMs with digital human models, supporting fully offline use.

- Completely open source with commercial use permitted
- Supports any digital human model, LLM, ASR, and TTS
- Works on microcontrollers, apps, websites, and third-party systems
- Includes auto-broadcast, multi-user concurrency, and MCP tool management

I am now 43 yo. My advices to Gen-Z:

- The secret to work life balance is generational wealth. Work as much to build that generational wealth.
- Stay away from tobacco’s and alcohol.
- Hit the gyms, but don't get mad for protein.
- Avoid watching porns.
- Instead of making online friend, socialize in real.
- Avoid going to clubs.
- Stop comparing your education.
- Stay away from unnecessary controversies.

Obsidian Mind provides persistent memory for AI coding agents via a local Obsidian vault. It works with Claude Code, Codex CLI, and Gemini CLI to help agents retain context, notes, and project history across different sessions.

https://github.com/breferrari/obsidian-mind https://x.com/tom_doerr/status/2078942883290190067

90% of your KV cache never gets reused.

(prompt caching was never meant to fix it)

if your system prompt and tool definitions are stable, prompt caching is the single highest-leverage optimization available today. cached input tokens get up to 90% cheaper, and hit rates of 60 to 85% are realistic.

but it comes with one rigid rule. the cached portion must be an exact, byte-for-byte prefix of the new request. change a single character in that region and you get a full cache miss.

that rule breaks in three situations you hit constantly:

→ RAG with multiple documents. you cached document A alone and document B alone. a query now needs both. document B's cached state was computed without any awareness of A, so it's invalid and gets recomputed from scratch.

→ document order changes. the same three documents appear in a different order across requests. every permutation is a cache miss, even though the content is identical.

→ growing conversation history. each new turn changes everything after the stable prefix, so earlier cached states beyond it become useless.

Alibaba Cloud's production data shows how bad this gets: 10% of KV cache blocks serve 77% of all hits. the rest sits in storage and never gets reused, because prefix matching won't allow it.

CacheBlend, a research paper from the LMCache team (EuroSys 2025 Best Paper Award), attacks exactly this. the insight is that in modern transformers, tokens overwhelmingly attend to their own local context. only a small fraction of tokens carry real connections across document boundaries.

so instead of recomputing everything after the first cached document, CacheBlend reuses every document's cache as-is and selectively recomputes just those few boundary tokens. those are the small orange fixes between documents in the diagram, and they are the entire cost. the result is 2 to 4x faster processing on multi-document queries with no quality loss.

the order problem disappears with it. shuffle the same documents however you like, and every permutation stays cached, where prefix caching recomputes all of them every time. the bottom of the diagram shows that side by side.

that's the real shift: from caching prefixes to caching knowledge. every document in your knowledge base becomes a reusable cached asset, regardless of what order it appears in or what sits next to it.

CacheBlend ships inside LMCache, the open-source cache management layer that runs outside the inference engine and integrates with vLLM, SGLang, and TensorRT-LLM, on both NVIDIA and AMD GPUs.

check it out on GitHub: https://github.com/LMCache/LMCache

(don't forget to star 🌟)

i wrote the full breakdown of the architecture, including why cache management should never live inside your inference engine. the article is quoted below.

stay tuned for more on this!

Very high level programming language (VHLPL) https://x.com/GithubProjects/status/2079240600050864473

Digital Marketing Pro is an open-source AI marketing plugin with 158 skills and 24 specialist agents, supporting Claude Code, Codex, Cursor, Copilot CLI, Antigravity, and OpenClaw. It provides a 12-part strategy flow to standardize multi-brand portfolio management for agencies handling 50-200 clients.

https://github.com/indranilbanerjee/digital-marketing-pro