AI Tools & Frameworks Directory

Claude Cowork shifts AI from chat-based assistance to task delegation. Instead of giving users instructions, it performs actions directly on the user’s computer, files, applications, and browser workflows. Combined with Playwright MCP, Claude Desktop can open pages, click buttons, fill forms, extrac...

Like other AI wearables, Amazon's Bee offers an odd combination of convenience and privacy anxiety.

Microsoft Research introduces Webwright, a terminal-native browser agent framework that replaces click-trace web automation with reusable Playwright scripts. Using a single agent loop across three modules and roughly 1,000 lines of code, Webwright powered by GPT-5.4 reaches 60.1% on the long-horizon...

Linear attention squeezes the unbounded KV cache into a fixed-size recurrent state, but editing that memory without scrambling existing associations is hard. Prior delta-rule models like Gated DeltaNet and KDA use one scalar gate to control both erasing old content and writing new content. NVIDIA's ...

Tencent has open-sourced TencentDB Agent Memory, a fully local memory system for AI agents released under the MIT license. The project pairs symbolic short-term memory, which offloads verbose tool logs into a compact Mermaid task canvas, with a 4-tier long-term memory pyramid (L0 Conversation → L1 A...

In this tutorial, we build an advanced workflow using the SuperClaude Framework as a structured layer on top of the Anthropic API. The post Build a SuperClaude Framework Workflow with Commands, Agents, Modes, and Session Memory appeared first on MarkTechPost.

Engineer token-efficient, self-adapting workflows for production The post From Prototype to Profit: Solving the Agentic Token-Burn Problem appeared first on Towards Data Science.

Nous Research releases Contrastive Neuron Attribution (CNA), a method that identifies and ablates sparse MLP neuron circuits to steer LLM behavior — no sparse autoencoder training, no weight modification, and no degradation of general capability benchmarks. The post Nous Research Releases Contrastiv...

Perplexity has open-sourced Bumblebee, an internal security tool it uses to protect the developer systems behind its search product, Comet, and Computer. Bumblebee is a read-only inventory collector for macOS and Linux developer endpoints. It scans npm, PyPI, Go modules, MCP configs, editor extensio...

arXiv:2605.21602v1 Announce Type: new Abstract: Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether LLM monitoring pipelines...

arXiv:2605.21623v1 Announce Type: new Abstract: Researchers in Holocaust studies have often distinguished between two styles of oral survivor testimony: the USC Shoah Foundation's interviews tend to follow a structured, interviewer-guided format, whereas the Yale Fortunoff Video Archive generally f...

arXiv:2605.21630v1 Announce Type: new Abstract: Although LLMs have made substantial progress in reasoning, systematically producing frontier-level reasoning data remains difficult. Existing synthesis methods often have limited visibility into the structural factors that govern problem difficulty, w...

arXiv:2605.21645v1 Announce Type: new Abstract: Adverse Outcome Pathways (AOP) are logic models that causally link biological mechanisms that can be measured in a lab to adverse outcomes, relevant to chemical regulatory endpoints. AOPs contextualize new approach methodologies (NAMs), in vitro and i...

How AI architecture prevents plausible but wrong analytics The post Hybrid AI: Combining Deterministic Analytics with LLM Reasoning appeared first on Towards Data Science.

Alibaba’s Qwen team has unveiled Qwen3.7-Max, a flagship model built for the agent era. Unlike conventional chatbot-focused LLMs, it is designed as a foundation for autonomous AI agents that can code, debug, use tools, manage workflows, and execute long-running enterprise tasks. Alibaba claims the m...

We kicked off our new weekly series This Week in AI on Monday, and we covered a lot of ground in 30 minutes, including an AI model that found security holes faster than decades of human auditing, a data center in Utah the size of two Manhattans, and a practical argument for why the harness […]

For AI engineers who want to understand every step, not just call the library The post Enterprise Document Intelligence: A Series on Building RAG Brick by Brick, from Minimal to Corpus scale appeared first on Towards Data Science.

The SpaceX S-1 is finally here, and the story it tells goes way further than rockets. The filing runs to 36 pages of risk factors alone, and the numbers inside match the ambition: a $28 trillion total addressable market, a pay package tied to establishing a Mars colony, and a valuation target that w...

Quantum Machine Learning promises access to exponentially large representational spaces, but before any computation can happen, classical data must first be embedded into quantum systems. This article explores one of the most overlooked bottlenecks in QML: getting data into a quantum computer effici...

Keyword search breaks the moment a user types something a document doesn't literally say.

In this tutorial, we will give Gemma 4 two new tools and watch the model decide, on its own, when to look around and when to compute.

During Tuesday’s Google I/O keynote, Demis Hassabis, the CEO of Google DeepMind, proclaimed that we are currently “standing in the foothills of the singularity.” It was a striking statement—the singularity is the theoretical future moment when AI rapidly exceeds human intelligence and dramatically t...

Microsoft Research released Fara1.5, a family of browser computer-use agents in 4B, 9B, and 27B sizes. Fara1.5-27B scores 72% on Online-Mind2Web, outperforming OpenAI Operator, Gemini 2.5 Computer Use, and Yutori Navigator n1. The release also includes FaraGen1.5, a synthetic data pipeline that trai...