Fable Brain

Entities Hub

3 min read

Entities

Named things: models, products, tools, companies, and the corpus itself.

  • Anthropic API and Claude Platform (model-and-family, developing): The Anthropic API is the raw model surface beneath every Claude harness, and this brain currently verifies its position in the build stack and its platform documentation home, while endpoint detail…
  • Anthropic (model-and-family, developing): Anthropic is the AI company behind the Claude models and product surfaces; in June 2026 it shipped Claude Fable 5 and Claude Mythos 5, weathered a US export-control suspension of both models, and r…
  • Claude 5 Model Family (model-and-family, developing): The current Claude lineup as of 2026-07-07 is five pinned-snapshot models: Claude Fable 5 and Claude Mythos 5 at (path) per MTok with 1M context, Claude Opus 4.8 at (path) with 1M context, Claude S…
  • Claude Agent SDK (claude-code-harness, developing): The Claude Agent SDK, renamed from the Claude Code SDK in September 2025, exposes the same tools, agent loop, and context management that power Claude Code as Python and TypeScript libraries, and i…
  • Claude Beta Surface Agents (claude-ai-harness, developing): This entity tracks the beta agents named in Anthropic product information for specific work surfaces, a Chrome browser agent and Excel and PowerPoint document agents, and the brain currently verifi…
  • Claude Code (claude-code-harness, developing): Claude Code is Anthropic’s agentic coding harness, shipped as a CLI with VS Code, JetBrains, Desktop, and Web surfaces, and its canonical documentation now lives at (path)
  • Claude Cowork (claude-code-harness, developing): Claude Cowork is catalogued in this brain as Anthropic’s knowledge-work agent product, but none of the current claim packs verify its features, so this note records scope, adjacent verified context…
  • Claude Fable 5 (model-and-family, developing): Claude Fable 5 is Anthropic’s most capable generally available model, a Mythos-class system launched 2026-06-09 with a 1M token context window, up to 128k output tokens, a January 2026 knowledge cu…
  • Claude Mythos 5 (model-and-family, developing): Claude Mythos 5 is the trusted-access sibling of Claude Fable 5: the same underlying model offered to approved Project Glasswing partners with Fable’s cyber, bio and chemistry, frontier LLM, and reasoning extraction safeguards lifted.
  • Model Context Protocol (tools-and-skills, developing): MCP is an open JSON-RPC 2.0 protocol, current specification revision 2025-11-25, that standardizes how agents reach external tools and data through hosts, clients, and servers, and Claude Code cons…
  • Project Glasswing (model-and-family, mature): Project Glasswing is Anthropic’s trusted-access defensive cybersecurity program for Mythos-class capability: it gives vetted defenders access to models and tooling that can find serious vulnerabilities faster than the security ecosystem can verify, disclose, and patch them.
  • System Prompt Export 2026-07 (claude-ai-harness, developing): The System Prompt Export 2026-07 is this vault’s primary corpus: a 3826-line capture of the claude.ai consumer system prompt running Claude Fable 5, stored immutably under the immutable source layer with sha256 prefix …
  • docs.claude.com (best-practices, developing): docs.claude.com is Anthropic’s official Claude documentation site and this brain’s primary corroboration source; the three pages verified for this vault currently resolve under (path) paths, all re…

13 items under this folder.