Llama.cpp has a new visual identity + official website. Run local models today! Now more than ever, open source must prevail. By @alekgrygier and @ggerganov at ggml/hf
SOFTWARE
-
Essential feature missing from most vibe-coding platforms
By
–
such an essential feat. I genuinely don’t understand why most vibe-coding platforms don’t offer it
-
Software jobs change: AI Strategic Technologists and AI Full Context
By
–
Read carefully. Software professions are undergoing profound change and redefinition. I plan to identify and group AI Strategic Technologists (strategic technologists who design projects and have the vision) and AI Full Context.
-
Self-generating 3D game fusing learning with kids’ interests
By
–
While we wait for Claude Fable 5 to come back, here's another wild demo I built for Alpha School.
— Matt Shumer (@mattshumer_) 17 juin 2026
A 3D game that generates itself on the fly, fusing what a kid has to learn with what they're actually into.
Just the first prototype, done in two days with Fable.
(sound on!) pic.twitter.com/GVbS6x1AzmWhile we wait for Claude Fable 5 to come back, here's another wild demo I built for Alpha School. A 3D game that generates itself on the fly, fusing what a kid has to learn with what they're actually into. Just the first prototype, done in two days with Fable. (sound on!)
-
Fable uses ThreeJS and GPT-Realtime-2 for interactive kid experience
By
–
Under the hood, Fable generates the world with ThreeJS, and GPT-Realtime-2 lets the kid answer out loud, ask questions, etc. As you can see, there are still small issues and paper-cuts throughout (it's a POC!), but the possibility of what this could become is absolutely insane!
-
Memanto: infinite on-prem memory for Claude, Codex and Cursor
By
–
Ahora puedes darle memoria infinita a Claude, Codex y Cursor sin que tus datos salgan de tu máquina.
— Nico (@nicos_ai) 17 juin 2026
Memanto acaba de lanzar su actualización más grande hasta la fecha:
→ ahora corre 100% en tu propia infraestructura (on-prem)
→ eliges tu proveedor de embeddings y LLM:… https://t.co/DrZ8WYQJwA pic.twitter.com/Jnr10zenZ5Now, you can give infinite memory to Claude, Codex and Cursor without your data leaving your machine. Memanto has just launched its biggest update to date: → now it runs 100% on your own infrastructure (on-prem) → you
-
GitHub COO interviewed on agent-created pull requests surge
By
–
GitHub has a front-row seat to how code is changing now that everyone—and their army of agents—can ship code. In March alone, agents created 17 million pull requests on the platform.
— Dan Shipper 📧 (@danshipper) 17 juin 2026
That’s why I was thrilled @hammer_mt was on hand to interview @github COO @kdaigle at Microsoft… pic.twitter.com/bwMYCgLOW1GitHub has a front-row seat to how code is changing now that everyone—and their army of agents—can ship code. In March alone, agents created 17 million pull requests on the platform. That’s why I was thrilled @hammer_mt was on hand to interview @github COO @kdaigle at Microsoft
-
Introduction of On-Call Copilot, new agent model
By
–
Introducing On-Call Copilot – a new agent template in LangSmith Fleet
— LangChain (@LangChain) 17 juin 2026
→ Triages every alert and investigates root cause across your code and traces
→ Manages tickets and routes every incident to the right channels
→ Continuously learns from your runbooks, escalation rules,… pic.twitter.com/5SM2FmJE7LIntroduction of On-Call Copilot – a new agent model in LangSmith Fleet
→ Sorts each alert and investigates root cause across your code and traces
→ Manages tickets and redirects each incident to the right channels
→ Continuously learns from your -
Tavus: a collaborative avatar worthy of Star Trek
By
–
I've been working with Tavus for a while now, but this is simply amazing.
— Chubby♨️ (@kimmonismus) 17 juin 2026
I'm serious, it's like science fiction. An avatar that I can collaborate with on the PC feels exactly like the future from Star Trek, just as I've always imagined it. It's fantastic.
Computer use + voice… https://t.co/C4rcQRj67FI have been working with Tavus for a while now, but it's simply incredible. I'm serious, it's like science fiction. An avatar with which I can collaborate on the computer looks exactly like the future of Star Trek, as I have
-
RemoteGraph for deployment interaction with agents via A2A and MCP
By
–
✅ RemoteGraph for deployment ↔ deployment interaction
— LangChain (@LangChain) 17 juin 2026
✅A2A Protocol support out of the box
✅ Interact with your agent via MCP Protocol@VictorMoreira16 on Agent Interoperability in Managed Deep Agentshttps://t.co/wiQVO5luru pic.twitter.com/z8Gwco88ArRemoteGraph for interaction deployment deployment A2A protocol support out of the box Interact with your agent via the MCP protocol @VictorMoreira16 on agent interoperability in managed deep agents https://
langchain.com/blog/introduci
ng-managed-deep-agents
…