A 24/7 Claude Code agent with Browser Harness, on any box you own.
TL;DR
Tools & Products
Research Papers
Tools & Products
Self-hosted AI agent OS — streaming chat, tool use, persistent memory, and multi-agent teams. Runs entirely on your machine.
Write your AI agent rules once, deploy to every IDE. Global protocol for Claude Code, Cursor, Windsurf, Antigravity, Codex & more.
A new project introduces Git-like version control capabilities designed specifically for AI agents, enabling better tracking and management of agent workflows.
Research Papers
Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL). StraTA samples a compact strategy from...
We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic forgetting. We introduce GeoStack (Geometric Stacking), a modular framework that allows independently trained domain experts to be composed into a unified model. By imposing geometric and structural constraints on the adapter manifold, GeoStack ensures the foundational knowledge of the base model is preserved. Furthermor...
Industry News
Google Cloud's Fraud Defence tool is criticized for being essentially a repackaged version of WEI (Web Environment Integrity), raising questions about the originality of the offering.
Apple and Intel have announced a preliminary agreement for chip-making collaboration, signaling potential deeper manufacturing partnership between the two tech giants.