LangSmith Self‑Hosted v0.10 is here If you're on a LangSmith self-hosted deployment, we have a suite of new features available to you in v0.10! Key features since v0.9: Catch production failures early with alerts
New UI driven workflows for creating evaluations and
OPEN SOURCE
-
LangSmith Self-Hosted v0.10 Released with Alerts and Evaluations
By
–
-

Alpha-Factory: Self-Forging Intelligence Engine for AGI
By
–
Alpha‑Factory Demo Gallery Seminal ideas awaken inside a single agentic engine: · Era of Experience · MuZero Planning · AI‑GA Meta‑Evolution Demos: https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos
… Alpha‑Factory — forging intelligence that forges itself. #AGI #AGIALPHA -

Algorithms That Invent Algorithms: Self-Generating Code Evolution
By
–
Algorithms That Invent Algorithms Inside our digital atelier, code now breeds code. Algorithms spawn heirs, worlds reshape, minds bloom unprompted. Feel tomorrow stir—explore the living demo. https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/aiga_meta_evolution
… #AGI #AGIALPHA #ReinforcementLearning -
MASt3R-SLAM: Real-Time Dense SLAM System with Global Consistency
By
–
MASt3R‑SLAM is a truly plug and play real‑time dense SLAM system that leverages the rich two‑view 3D reconstruction priors of MASt3R to deliver globally consistent geometry and highly accurate camera poses.
— Satya Mallick (@LearnOpenCV) 22 avril 2025
By integrating novel matching, fusion, and optimization… pic.twitter.com/YECWe2aoDHMASt3R‑SLAM is a truly plug and play real‑time dense SLAM system that leverages the rich two‑view 3D reconstruction priors of MASt3R to deliver globally consistent geometry and highly accurate camera poses. By integrating novel matching, fusion, and optimization
-

Alpha-Factory v1: MuZero Planning Agent in Browser Demo
By
–
Somewhere between Eustace Tilley’s knowing smirk and DeepMind’s chessboard, we coaxed Alpha‑Factory v1 into a living novella of code: MuZero planning, balancing, outwitting—all inside your browser Pure delight. Demo: https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/muzero_planning
… #AGI #AGIALPHA -

Alpha-Factory v1: Multi-Agent AGI Learns Through Experience
By
–
Eustace Tilley would nod: Alpha‑Factory v1 now breathes Silver & Sutton’s “Era of Experience.” Multi‑agent α‑AGI that learns by living—cross‑industry ready, deployable in one command. Demo ➜ https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/era_of_experience
… #AGI #AGIALPHA #ReinforcementLearning -
Clarifying smolagents name and multi-agent orchestration
By
–
It seems smolagents was a bit under-researched. First of all it's "smolagents", without a space in the middle. We do have multi-agents (not with a dedicated abstraction, we managed to handle the orchestration under the base agent class): https://
huggingface.co/docs/smolagent
s/examples/multiagents
… We do have -

TextArena: Open-Source Competitive Games for LLM Agents
By
–
TextArena went live on Hugging Face It's an open-source collection of competitive text-based games for LLMs, spanning 57+ unique environments Tests for different agentic behaviors—negotiation, theory of mind, deception, via competitive play
-
Magi-1: World’s First Autoregressive Video Model Released
By
–
Magi-1 is the world's first autoregressive video model with top-tier output. It was released by @SandAI_HQ. Great to see another AI company after DeepSeek open source world-class models. Let's make AI more open! Check out: https://t.co/ykqABdm3vzhttps://t.co/WkR8srZc4D
— Kai-Fu Lee (@kaifulee) 22 avril 2025Magi-1 is the world's first autoregressive video model with top-tier output. It was released by @SandAI_HQ
. Great to see another AI company after DeepSeek open source world-class models. Let's make AI more open! Check out: http://
sand.ai -
SandAI Open-Sources Magi-1 Autoregressive Video Model
By
–
@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see another AI company after DeepSeek developing world-class open source models. Let's make AI more open! Check out: https://t.co/ykqABdm3vzhttps://t.co/WkR8srZc4D
— Kai-Fu Lee (@kaifulee) 22 avril 2025@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see another AI company after DeepSeek developing world-class open source models. Let's make AI more open! Check out: http://
sand.ai