# #anthropic > Memos related to Anthropic — the AI safety company behind Claude. Covers Claude models, API patterns, and Anthropic's approach to building safe and capable AI. ## Links - [Tag Page](https://mythos.one/tag/anthropic) - [MCP Server](https://mythos.one/api/mcp) ## Memos - [Claude Managed Agents](https://mythos.one/me/brianswichkow/1ba4d7): Claude Managed Agents is a suite of composable APIs from Anthropic for building, running, and observing cloud-hosted AI agents at scale, launched in beta on April 8, 2026. The platform decouples the... - [Anthropic](https://mythos.one/me/brianswichkow/b22104): Anthropic is an American Artificial Intelligence safety company founded in 2021, headquartered in San Francisco. Co-founded by Dario Amodei (CEO) and Daniela Amodei (President), alongside other... - [Claude Mythos](https://mythos.one/me/brianswichkow/4c9871): Claude Mythos by Anthropic is a reported next-generation Artificial Intelligence (AI) model within the Anthropic ecosystem, described in leaked and secondary sources as an advanced tier of the Claude... - [What Anthropic’s Claude Mythos and My Divorce Have in Common](https://mythos.one/me/brianswichkow/00c227): I loved Anthropic and all their products enabled me to create... right until they named their new model Claude Mythos despite our trademark of MythOS and use in commerce since 2018, but now... it's... - [Project Glasswing](https://mythos.one/me/brianswichkow/2b09aa): Project Glasswing is Anthropic's initiative to use Claude Mythos Preview — its most capable frontier model — to find and remediate vulnerabilities in the world's most critical software before... - [Claude Cowork](https://mythos.one/me/brianswichkow/90d19b): Claude Cowork is an AI-powered agent by Anthropic designed to execute administrative and research tasks directly on a user's local machine. Available to Pro, Team, and Enterprise subscribers via the... - [Claude MythOS Context Window](https://mythos.one/me/brianswichkow/e8da42): Claude Mythos Preview ships with a 1M-token context window and 128K max output tokens — matching Claude Opus 4.6 at the top of Anthropic's current lineup. These are the only confirmed specifications... - [Human-AI Augmentation](https://mythos.one/me/brianswichkow/bca911): Human-AI augmentation is the practice of designing systems where a human and an Artificial Intelligence operate as a unified intelligence — not as tool and user, but as collaborators with distinct... - [Claude Code Swarm Mode](https://mythos.one/me/brianswichkow/888513): Claude Code Swarm Mode (officially called Agent Teams) is a multi-agent orchestration system built into Claude Code by Anthropic. Initially feature-flagged and hidden from users, the system was... - [How to Set Up Claude Code](https://mythos.one/me/brianswichkow/d8288d): How to set up Claude Code is a practitioner's guide to getting Claude Code running and configured for real work — not just installed, but set up with the memory, permissions, and workflow patterns... - [Constitutional AI](https://mythos.one/me/brianswichkow/47aacc): Constitutional AI (CAI) is a methodology developed by Anthropic for training AI systems to be helpful, harmless, and honest — by embedding human-controllable values directly into the model through a... - [Agentic Coding](https://mythos.one/me/brianswichkow/7f07f8): Agentic coding is a software development paradigm where an AI agent autonomously reads, plans, writes, tests, and iterates on code — executing multi-step workflows rather than suggesting individual... - [Model Context Protocol (MCP)](https://mythos.one/me/brianswichkow/337a84): Model Context Protocol (MCP) is an open protocol developed by Anthropic that standardizes how Artificial Intelligence models connect to external tools, data sources, and systems. Donated to the Linux... - [Building with Claude Code as a Non-Engineer](https://mythos.one/me/brianswichkow/4e5beb): Building with Claude Code as a non-engineer is the practice of using Claude Code's agentic capabilities to design, build, and ship production software without a traditional engineering background.... - [Claude Code](https://mythos.one/me/brianswichkow/632ca2): Claude Code is an agentic coding tool developed by Anthropic that operates directly in the terminal, IDE, desktop app, and browser. Unlike code completion tools like GitHub Copilot or Cursor, Claude... - [BrianBot](https://mythos.one/me/brianswichkow/85920f): BrianBot is a 57+ agent AI ecosystem built by Brian Swichkow as a living implementation of Collaborative Augmentation — the unified system where BioBrian (the human) and BotBrian (the AI) operate as... - [What Is Mythos? The AI Model and the Platform That Came First](https://mythos.one/me/brianswichkow/3bff55): The Short Answer "Mythos" currently refers to two things in the AI world: Claude Mythos — Anthropic's reported next-generation Artificial Intelligence (AI) model, a frontier Large Language Model... - [Claude Mythos for Developers — What to Expect](https://mythos.one/me/brianswichkow/a34f2d): What the Benchmarks Suggest The leaked and reported benchmarks for Claude Mythos paint a picture that developers should pay close attention to. While Anthropic hasn't officially confirmed specific... - [Building on Claude: A MythOS Creator's Perspective](https://mythos.one/me/brianswichkow/1fd9f8): The Starting Point I didn't identify as an engineer for the first decade of my career. I built systems, ran companies, and thought architecturally — but the actual writing of code was something I... - [MythOS vs Claude Mythos — Same Name, Different Worlds](https://mythos.one/me/brianswichkow/baf126): Two Systems, One Name If you've recently searched for "Mythos" in the context of AI, you've likely encountered two very different things: MythOS, a personal knowledge management platform, and Claude... - [Claude Mythos Benchmarks — What the Numbers Actually Mean](https://mythos.one/me/brianswichkow/e9910c): Post The Benchmark Landscape Every Frontier Model launch comes with benchmarks. Numbers go up, charts get shared, and the discourse cycles between "this changes everything" and "benchmarks don't... - [Why We're Excited About Claude Mythos (Despite Everything)](https://mythos.one/me/brianswichkow/5c645c): Post The Honest Version I want to be direct about something: Anthropic named their next model the same thing as the platform I've been building since 2017. MythOS — the knowledge management system,... - [Claude Mythos and AI Safety — What More Capability Means for Risk](https://mythos.one/me/brianswichkow/85de1e): Post The Capability-Safety Tension Every frontier model release surfaces the same tension: more capability means more utility and more risk. Claude Mythos, Anthropic's reported next-generation model,... - [Frontier Models and the Future of Personal Knowledge Systems](https://mythos.one/me/brianswichkow/31ebf4): Post The Convergence Something is converging that few people are talking about explicitly: frontier AI models are getting good enough to genuinely understand personal context — and the systems that... - [Model Context Protocol and Claude Mythos](https://mythos.one/me/brianswichkow/9e45fe): The Model Context Protocol (MCP) is an open protocol developed by Anthropic and donated to the Linux Foundation that standardizes how Artificial Intelligence (AI) models connect to external tools,... - [Agentic AI and Claude Mythos — The Next Step for Autonomous Systems](https://mythos.one/me/brianswichkow/9906eb): Agentic AI refers to Artificial Intelligence (AI) systems that can autonomously plan, execute, and iterate on complex tasks — using tools, making decisions, and adapting to feedback without... - [Claude Mythos Release Date and What We Know So Far](https://mythos.one/me/brianswichkow/bc0112): Claude Mythos is Anthropic's anticipated next-generation Artificial Intelligence (AI) model. As of April 2026, no official release date has been confirmed. This memo tracks what is known, what has... - [Claude Mythos](https://mythos.one/me/brianswichkow/fd4e8c): Claude Mythos is a reported next-generation Artificial Intelligence (AI) model developed by Anthropic, positioned as the most capable tier within the Claude model family. Described in leaked... - [Bartz v. Anthropic PBC](https://mythos.one/me/brianswichkow/780f51): What the case is The lawsuit is commonly known as Bartz v. Anthropic PBC, filed in 2024 by authors Andrea Bartz, Charles Graeber, and Kirk Wallace Johnson as a putative class action on behalf of... - [--dangerously-skip-permissions](https://mythos.one/me/brianswichkow/43e1ea): The --dangerously-skip-permissions flag is an officially documented Command Line Interface (CLI) option for Claude Code (Anthropic) that bypasses all permission prompts, granting unrestricted access...