Persistent Memory with zkStash SDK Made by the LangChain Community zkStash is a TypeScript SDK for persistent memory in AI agents. Integrates with LangChain via MCP tools or middleware, using Zod schemas for structured storage of preferences and conversations. Docs:
TOOLS
-
Bloom: Open-Source Tool for AI Behavioral Misalignment Evaluation
By
–
We’re releasing Bloom, an open-source tool for generating behavioral misalignment evals for frontier AI models. Bloom lets researchers specify a behavior and then quantify its frequency and severity across automatically generated scenarios. Learn more:
-
Building Enterprise Agents with Deep Agents and Runloop
By
–
Building Enterprise Agents with Deep Agents Learn to build and deploy enterprise AI agents using Deep Agents and Runloop. Uses Runloop to run code safely in sandboxes Watch the full tutorial: https://
youtube.com/watch?v=rj5OhG
ujPoE
…
Made by the LangChain Community -
Using ChatGPT to generate personalized Sora holiday videos
By
–
You can get a personalised Christmas Sora video on ChatGPT if you send emoji to the chat. Looking forward to ChatGPT wrapped
-
AI Tools Reach Massive Scale: ChatGPT Leads with 4.7B Monthly Visits
By
–
AI tool usage at scale is here. ChatGPT: 4.7B monthly visits (Jan 2025)
Canva: 887M
Google Translate: 595M
DeepSeek: 268M (massive surge) http://
Character.AI: 226M
Perplexity: 133M
Gemini: 118M
Claude: 105M AI isn’t a trend anymore — it’s infrastructure. What’s your #1 -
8 RAG Architectures Every AI Engineer Must Know
By
–
8 RAG architectures all AI Engineers should know:
-
Building RAG Applications on AWS: Ingestion and Querying Stages
By
–
Building a RAG app on AWS is simpler than you might think.
— Akshay 🚀 (@akshay_pachaar) 20 décembre 2025
Let me explain how you can achieve this using services you already know:
At its core, RAG follows a two-stage pattern: ingestion and querying.
Here's how you can implement each stage on AWS:
1️⃣ Ingestion: Turning raw… pic.twitter.com/UOTBpoUcpeBuilding a RAG app on AWS is simpler than you might think. Let me explain how you can achieve this using services you already know: At its core, RAG follows a two-stage pattern: ingestion and querying. Here's how you can implement each stage on AWS: Ingestion: Turning raw
-
AI 2025 Breakthroughs: RL, Reasoning Models, and Future Paradigms
By
–
Things move very very fast in AI. 2025 was a year of RL with verifiable rewards(RLVR), LLM ghosts/jagged intelligence, Cursor-like LLM apps, claude code/codex, vibe-coding, NanoBanana showing early glimpse of LLM promptable graphical interfaces(PGI, i just coined this lol), LLM reasoning models crushing olympiad competitions (maths, physics, code). Most altering releases tend to come early in a year, jan-feb, and then scaling-up and small fixes begin. Eagerly looking forward to new paradigm shifts. What will next NanoBanana look like, just bigger or new capabilities no one thought before? There are several stages of training now, RL(VR) being the most recent. What will be the RL successor? And continual learning, will it be fixed in 2026, or this is a problem we will live with for long? There are also world models, agents that actually work reliably in the wild for hours. Andrej Karpathy (@karpathy) x.com/i/article/200211463822… — https://nitter.net/karpathy/status/2002118205729562949#m
-
Feature update: Filtering posts for characters on Sora
By
–
ICYMI: Now it is possible to filter out top posts for Characters on Sora. Have you met "testingcameo" already?
-
Claude Web Features Converge with Claude Code Integration
By
–
Haven't used Claude Web in a while… and I just saw that it has compacting now. It looks like Claude Code features are now converging onto Claude Web