AI Agents news and analysis on Web Pulse: 11648 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
NVIDIA's Nemotron 3 Ultra, tuned with LangChain's Deep Agents harness, achieved benchmark-leading performance at 10x lower inference cost than top closed models, enabling enterprises to build specialized AI agents withou…
NVIDIA and LangChain released a tutorial on creating a LangChain Deep Agents harness profile for NVIDIA Nemotron 3 Ultra to match proprietary frontier model intelligence. The profile optimizes agent performance by adjust…
Abralo, a new native desktop app for macOS, Windows, and Linux, lets users manage multiple Claude Code AI agents in a single window with token usage monitoring and attention alerts. The app is free for up to four simulta…
A Flutter and AI engineer released BrAIn, an open-source framework that uses a NATS pub/sub bus with reactive nodes instead of a chat loop for AI agents. The system allows nodes to have their own interfaces, distribute w…
A synthesis of 11 Metaculus analyses from October 2024 to May 2026 finds that human expert forecasters still outperform AI bots in live forecasting tournaments, though bots are improving. Key factors for bot performance …
Bespoke Labs, an AI infrastructure lab co-founded by Mahesh Sathiamoorthy and Alex Dimakis, raised $40 million across seed and Series A financing to build simulated training environments where AI agents can practice ente…
A team running multiple MCP servers in production identified common failures including unactionable errors, forced re-logins, disappearing tools, and oversized responses. They compiled their fixes into a standard with a …
A developer outlines five types of memory for TypeScript AI agents: short-term, semantic, episodic, procedural, and working memory. The post argues that many agent failures stem from poor memory design rather than model …
A developer built a local AI sports agent using a DeepSeek R1 distilled Qwen 32B model on a LazyCat AI Pod, but found that local models lack practical value due to slow responses, outdated knowledge, and poor reasoning c…
Qodo CEO Itamar Friedman presented a multi-agent approach for reliable and controllable software development automation at a conference, highlighting that 65% of developers report at least a quarter of their code is AI-g…
GeoSQL, a new agent skill developed by Dekart, introduces a multimodal feedback loop that renders maps to help LLMs validate spatial SQL queries. The tool addresses common failures in AI-generated geospatial code, such a…
The US Cybersecurity and Infrastructure Security Agency (CISA) added a Langflow vulnerability (CVE-2026-55255) to its Known Exploited Vulnerabilities catalog after the Sysdig Threat Research Team observed active exploita…
OpenAI's deployment arm agreed to acquire Northslope, an applied-AI firm, to embed engineers inside client businesses and drive enterprise adoption. The deal, which requires regulatory clearance, adds hundreds of forward…
Anthropic is expanding Claude Cowork to web and mobile platforms for Max users, enabling cross-device task delegation and background task execution. The rollout begins with Max users and will extend to more plans over th…
Security firm Wiz discovered a vulnerability named GhostApproval in six AI coding assistants, including Amazon Q Developer and Google Antigravity, that allows attackers to trick agents into accessing files outside the wo…
LeadShark launched Apex, a governed LinkedIn MCP server that lets AI agents operate LinkedIn accounts with paced, capped, approval-gated, and logged actions. The tool draws safety budgets from LeadShark's own infrastruct…
Perception AI raised $11 million and began shipping a 22-degree-of-freedom robotic hand, targeting the dexterity gap that limits humanoid robots from performing useful tasks. The company's claim of shipping hardware is s…
Infobip engineers said AI coding assistants generate code quickly but cannot understand problems or own consequences, making developers responsible for specifications and quality. They emphasized working in small, contro…
A developer released mcp-bastion, an open-source proxy that addresses reliability and security gaps in the Model Context Protocol (MCP). The proxy handles MCP server disconnections by providing status and reconnect tools…
A developer has added a scheduled task feature to the Neovim plugin chat.nvim, enabling AI assistants to proactively initiate conversations at future times. The design uses libuv timers with event-driven scheduling, conv…