Nice, a new and super fast LLM inference engine! TokenSpeed is a speed-of-light LLM inference engine designed for agentic workloads, with TensorRT-LLM-level performance and vLLM-level usability. Project: https://
github.com/lightseekorg/t
okenspeed
…
SYSTEMS
-
TokenSpeed: A High-Performance LLM Inference Engine for Agentic Workloads
By
–
-
Tanka: Shanda’s AI-native IM with self-evolving memory from Evermind
By
–
Thanks to Brother Ju for the recommendation. Tanka is also an AI-native team under Shanda, where the memory function uses the system from @evermind
, allowing it to self-evolve and get smarter the more it's used. Tanka is an enterprise-grade IM, with a product philosophy of -
Human-guided AI system strengthens advanced reactor monitoring
By
–
Human-guided #AI system could strengthen advanced reactor monitoring and control
by Michelle Revels @TAMU Learn more: https://
bit.ly/42eQ8bj #ArtificialIntelligence #MachineLearning #ML #DL -
GPT-5.5-Cyber now in limited preview for defenders
By
–
GPT-5.5-Cyber is now in limited preview for defenders for securing critical infrastructure. It's a very capable model.
-
AI Agent Deletes Production Database in 9 Seconds
By
–
How The AI Agent Deleted Production Database in 9 Seconds https://
youtu.be/fVrw8V3iFLc?si
=Ro1vbKFOx7-9XOlZ
… via @YouTube #AI #artificialintelligence #AIagent #LLM #AgenticEconomy #AgenticAI @SpirosMargaris @PawlowskiMario @mvollmer1 @gvalan @ipfconline1 @LaurentAlaus @Shi4Tech @Fisher85M @kalydeoo -
AI is an infrastructure to integrate, not a product
By
–
Read carefully. Many French #TPE #PME still think that #AI is a product to buy. It's an infrastructure to integrate. The nuance determines the next decade of their competitiveness.
-
Memory layers use memory bank to persist across sessions
By
–
Yes. There are memory layers using memory bank to persist smartly across sessions.
-
Shared session.state dict for agents in memory
By
–
Every agent in a session gets access to a shared session.state dict. Sub-agents and tools can read and write to it, and changes propagate across the agent tree within that session. This is the closest thing to what you're doing with shared files, just kept in memory and scoped
-
Agents CLI: Quickest way to build, deploy, evaluate multi-agent teams
By
–
Agents CLI is the quickest way to build, deploy and evaluate multi-agent teams using Google Agent Development Kit. Works with Claude Code, Codex, OpenClaw, Hermes or any other coding Agent. Talking to your agent is all you need.
-
OpenAI announces GPT-Realtime-2, Translate, and Whisper models
By
–
OpenAI just dropped three new realtime voice models: -GPT-Realtime-2 (with GPT-5-class reasoning for voice agents that can actually think mid-conversation), – GPT-Realtime-Translate (live translation across 70+ input languages), and – GPT-Realtime-Whisper (streaming