3GitHub Trending (AI/LLM filtered)·
boop-agent: iMessage personal agent supporting Claude and Codex runtimes
A TypeScript open-source project on GitHub implements a personal AI agent accessible via iMessage, supporting either the Claude Agent SDK or OpenAI Codex app-server as the underlying runtime. The agent includes memory, sub-agents, automations, and integrations. With 1,054 stars and 40 gained today, it represents a community-built example of multi-runtime agentic tooling targeting consumer messaging interfaces.
Related guides (3)
Related events (8)
Claude Tag: Anthropic launches multiplayer, proactive, persistent agent capabilities in Slack
Anthropic has introduced 'Claude Tag,' a Slack integration enabling multiplayer, proactive, and persistent agent behavior for Claude. The deployment allows Claude to be tagged in Slack conversations, take initiative, and maintain context across sessions. This represents a meaningful step in agentic deployment patterns for enterprise collaboration tools.
Anthropic launches Claude Tag: persistent, multiplayer Claude agent for Slack teams
Anthropic has released Claude Tag in beta for Enterprise and Team customers, a Slack-native agentic product that allows teams to tag @Claude in channels where it operates as a shared, persistent team member with memory, tool access, and asynchronous task execution. Claude Tag builds on Claude Code and Cowork, adding multiplayer context (one Claude per channel visible to all), ambient proactive updates, and the ability to schedule and pursue tasks autonomously over hours or days. Anthropic reports that 65% of its own product team's code is now generated by an internal version of Claude Tag. The product runs on Claude Opus 4.8 and allows administrators to scope tool access, data permissions, and token spend per channel.
OpenAI releases Codex App for macOS: multi-agent coding command center
OpenAI launched the Codex App for macOS, a desktop interface for managing multiple coding agents running in parallel on long-horizon and background tasks. The app surfaces agent progress, clean diffs from isolated worktrees, and reusable skill automations, and integrates with existing Codex local and Codex cloud admin controls including RBAC and a compliance API. Enterprise and Edu users receive temporary 2x rate limit boosts as a launch promotion.
OpenAI releases Codex macOS app for managing parallel coding agents
OpenAI launched a native macOS application called Codex, designed as a command center for running multiple coding agents in parallel on long-horizon and background tasks. The app surfaces agent progress and decisions, clean diffs from isolated worktrees, and supports reusable skills and automations. It is available to ChatGPT subscribers with Codex access, with a limited-time trial for Free and Go tiers and 2x rate limits for Plus and Pro users.
Anthropic launches Claude Mythos 5 and Claude Fable 5; Andrew Ng introduces OpenCoworker desktop agent
Anthropic released Claude Mythos 5 and Claude Fable 5, two variants of the same frontier model that set new state-of-the-art results across software engineering, knowledge work, cybersecurity, and agentic coding benchmarks. Claude Fable 5 is the general-availability version with safety classifiers that restrict responses on security, biology, chemistry, and cutting-edge AI topics, priced at $10/$50 per million input/output tokens; Mythos 5 is restricted to selected partners via Project Glasswing. Separately, Andrew Ng and collaborators released OpenCoworker, a free open-source desktop agent harness built on top of aisuite, designed to give users privacy-preserving agentic workflows with their own API keys or local models. The newsletter also contextualizes the broader shift toward LLM-driven agent harnesses as frontier models have become capable enough to reliably drive next-action decisions.
claude-mem: Persistent Cross-Session Memory Layer for AI Coding Agents
claude-mem is an open-source TypeScript library that provides persistent context across sessions for AI coding agents. It captures agent activity during sessions, compresses it using AI, and injects relevant context into future sessions. The tool claims compatibility with Claude Code, OpenAI Codex, Gemini, GitHub Copilot, and other coding agents. The repository has accumulated 78,579 stars with 319 added today, indicating strong community traction.
Anthropic Releases Claude Opus 4.5 with State-of-the-Art Coding, Agent, and Computer Use Capabilities
Anthropic has released Claude Opus 4.5, positioning it as the best model in the world for coding, agentic workflows, and computer use, with pricing reduced to $5/$25 per million input/output tokens. The model demonstrates significant token efficiency gains—up to 65% fewer tokens than prior models on equivalent tasks—alongside improvements in long-horizon autonomous task execution, multi-step reasoning, and self-improving agent behavior. The release is accompanied by updates to Claude Code, the Claude Developer Platform, and integrations with Excel, Chrome, and desktop environments. Early partner feedback from GitHub Copilot, Cursor, Notion, Warp, and others reports measurable benchmark improvements and new use cases previously out of reach.
AstrBot: multi-platform AI agent framework with IM integration trending on GitHub
AstrBot is an open-source Python framework for building AI agent assistants that integrates multiple instant messaging platforms, LLMs, and plugins. The project has accumulated over 34,000 GitHub stars with 110 new stars today, indicating active community interest. It positions itself as an alternative to OpenClaw-style agent orchestration tools.