LoreConvo launched a context-restoration tool that uses auto-load and auto-save hooks to carry project context between AI coding sessions on Claude Code, Cowork, the Codex desktop app, Cursor IDE, and…
Anthropic has listed Growomat, a hosted MCP connector that has run since June, in the Claude connectors directory, replacing the previous setup that required users to copy and paste the URL https://mc…
LoreConvo, a local-first memory backend that operates as a native MCP server, aims to standardize session persistence across AI development tools such as Claude Code, Cowork, the Codex desktop app, Cu…
Team Winston, an AI platform for cannabis retail, claims to cut invoice processing time from 20-30 minutes to under 3 minutes per invoice. The platform integrates with POS, accounting, compliance, and…
Daniel Blum, a product manager at Melio, has built a self-improving AI system using Anthropic's Claude and Cowork that now handles 70% to 80% of his workday, enabling him to complete a week's worth of…
Daniel Blum, a product manager at B2B payments company Melio, has built a Claude- and Cowork-based productivity system that automates his Notion board, processes Slack and email, and runs self-improve…
Anthropic on August 25 unified memory across Claude chat and Cowork, making all memory entries readable, editable, and deletable, with sensitive categories opt-in, and introduced a memory tool for dev…
Anthropic on Aug. 25 extended Claude's memory to Cowork, allowing information learned in Chat to carry into Cowork tasks and vice versa, with memory enabled by default for Free, Pro, and Max users. Us…
Four papers published today challenge the reliability of LLM-as-judge, showing that judge annotations can mark working code as failures, leak across rubric dimensions, and misalign with human creativi…
Anthropic merged persistent memory between Claude Chat and Cowork, eliminating the need for users to repeat project briefs and preferences across sessions. The unified memory raises privacy concerns b…
Anthropic is rolling out a Morning Brief feature inside Claude's Cowork mode, offering select Max plan subscribers a personalized daily digest from email, calendars, Slack, Notion, and dashboards. The…
Anthropic has unified memory across its Claude AI assistant and Cowork collaboration tool, allowing users to carry context from past chats between the two without re-entering it. The update adds real-…
Anthropic PBC announced updates to Claude's memory, allowing users to view, edit, and delete remembered topics, with sensitive subjects like health, race, ethnicity, gender identity, religion, and pol…
Anthropic's flagship models Fable 5, Mythos 5, Opus 5, and Opus 4.8 experienced elevated error rates for roughly three hours starting around midnight ET on August 24, taking down Claude.ai, the API, C…
A Hacker News user asks whether AI tools like Cowork and Codex are replacing spreadsheets as the go-to for simple apps, noting their own spreadsheet use has dropped immensely since adopting these tool…
Anthropic's Claude AI can now send Gmail messages on behalf of users, a first for its Google Workspace connector, with default approval required for all messages and Team/Enterprise plan owners able t…
Anthropic has built an unreleased, Mac-first meeting recorder inside Claude Desktop, codenamed Parka, that can turn meeting transcripts into Cowork, Claude Code, or manual follow-up actions, according…
Anthropic has begun embedding a statistical watermark into text generated by supported Claude models, a move designed to comply with the European Union's AI Act Article 50, which took effect on August…
Anthropic is developing a built-in web browser for Cowork sessions in Claude Desktop, according to TestingCatalog, which would allow users to browse the web while Claude maintains context, bridging a …
A developer has released an open-source, tool-agnostic system for agentic task management that runs continuously in AI conversation threads, using an append-only task log database and a schema loaded …