AI Briefing#ai-agents
The latest AI and developer news about #ai-agents, with the original source and a short summary.
The latest AI and developer news about #ai-agents, with the original source and a short summary.
Meta is preparing a waitlist-based Hatch AI Agent.
GitHub revealed optimizations that reduce token usage in agentic workflows.
Mnemos, an open-source MCP server that solves the cross-session memory loss problem of AI coding agents, has launched.
Donely, a management and knowledge layer platform for AI agents that perform work based on enterprise data, has launched.
Friday Studio, an AI agent runtime that converts natural language into repeatable YAML workflows and executes them, has been released.
Anthropic has released the Model Context Protocol (MCP), an open standard for connecting AI assistants with data sources.
In Anthropic's Gmail connector, the existing message-reading tool has been removed and replaced with a tool that only provides metadata.
Don't just rely on CI passing for agent PRs—you need to directly review for duplication and security.
Coinbase is cutting 14% of its workforce to run a leaner, AI-centered organization.
Salesforce will hire 1,000 new employees to strengthen its AI agent system, Agentforce.
BrowserCode has been released, allowing AI coding agents like Claude Code and Gemini CLI to run in the browser using WebAssembly.
Parloa runs voice customer service agents using OpenAI models.
Anthropic unveiled 10 agents for finance along with Opus 4.7.
Audioscrape has updated its MCP server, which supports audio transcription and search across 18 million podcasts.
MyRealTrip's subsidiary AICX has automated 75,000 CS cases per month.
A collection of agent skills for Claude Code released by Matt Pocock, providing a modular toolset for real-world engineering.
BNA Code, a CLI AI agent that builds full-stack mobile apps from a single prompt, has launched.
It is an open-source MCP-based Claude Code plugin that automates Google Ads, Meta Ads, and SEO management.
A security vulnerability has been reported in which files are leaked through Microsoft Copilot's Cowork feature.
Harvey has released LAB, an open-source benchmark for legal agents.
Google is testing screen sharing and custom agents in Antigravity.
ProgramBench is a benchmark that requires reimplementing a program from only its binary and documentation.
AI agent memory works by combining the context window with retrieval-based long-term memory.
Researchers at CUHK have unveiled OpenGame, a system that creates games by generating code and graphics from just text input.