Auto Added by WPeMatico
Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that treats content moderation as a single yes/no question rather than a fixed taxonomy of harm categories. Most guardrail models bake their category list into the weights, so re-targeting one to a new deployment context means retraining — and the same content […]
Tencent Cloud has open-sourced TencentDB Agent Memory v2.0, a team-level memory hub for AI agents. The idea is super simple: if project context was already explained once, a new session should not need it repeated. The system turns conversations, documents and code into four reusable memory assets — Chat Memory, Skill, LLM-Wiki and Code-Graph —
Microsoft has open sourced code-testing-generator, a polyglot agent that writes unit tests and then proves they work. It ships in the dotnet-test plugin inside the MIT-licensed dotnet/skills repository. The agent targets a gap that coding assistants usually leave open. A prompt like ‘generate unit tests’ does not say which framework, file location or assertions to
Liquid AI released LFM2.5-2.6B, an agentic model that runs entirely on-device. It plans, calls tools, and works through multi-step tasks on phones, laptops, PCs, and robots. The model has 2.69B total parameters, a 131,072-token context window, and a 128,000-token vocabulary. Pre-training used approximately 34 trillion tokens. Two checkpoints shipped: LFM2.5-2.6B-Base for fine-tuning, and LFM2.5-2.6B post-trained
Cloudflare has released Kitesurf, a stateless web browser built specifically for AI agents. It runs entirely in V8 isolates on Cloudflare Workers, with no Chromium underneath. Browser engines like Chromium were built for humans, and their memory and compute overhead makes one-browser-per-agent prohibitively expensive. Agents do not need tabs, extensions, or pixel-perfect 60-fps rendering. They
Prime Intellect has open-sourced Prime Agent, a self-improving coding harness designed around two abstractions, the Recursive Language Model (RLM) and Continual Harness. Fixed tool schemas and context compaction force a model to work around its own scaffolding. Prime Agent replaces both with a persistent Python REPL and a rewritable harness. With Opus 5, it reports
Meta AI has released Muse Code (in beta), a terminal coding agent in beta, powered by its new Muse Spark 1.2 model. Meta positions the pair as its next step toward the frontier, with larger models on the way. Muse Code targets complex software engineering across large repositories: it plans changes, writes code, and validates
NVIDIA has released Alpamayo 2 Super, a 34B-parameter vision-language-action (VLA) model for autonomous driving, under an open commercial license. The stated design target is the long-tail events: rare, multi-agent situations that conventional detection-and-prediction stacks handle poorly. The model pairs a 32B VLM backbone, built on NVIDIA Cosmos 3 Super Reasoner and post-trained with reinforcement learning,
CopilotKit has just released the Channels SDK. It is an open source library that puts an existing agent inside a messaging platform. The core assumption is focused and verifiable. You already have an agent. It already has a model, tools and business logic. Channels gives it a place to work with people, without a rewrite
Cursor Research has open-sourced Mixture-of-Kittens (MoK), the mixture-of-experts training megakernel behind its Composer models. MoK fuses every MoE communication and computation step into a single deterministic kernel. Cursor team reports up to 2.37x higher throughput than the strongest public baseline. It already powers Composer training across tens of thousands of GPUs. Is it deployable Yes,
