Anthropic
Explained projects
Anthropic’s `commerce-agents`: the blueprint for AI commerce that stays under control
A deep look at how Anthropic split shopping and merchant agents, enforced safety in code, and made long-running commerce sessions practical with caching, compaction, and staged writes.
anthropics/cwc-long-running-agents: Why Long-Running Agents Need a Harness, Not More Prompts
A compact Bash-and-Git reference architecture that forces evidence, preserves memory, and separates builders from judges.
claude-desktop-buddy: Claude Desktop Buddy: The Desk Pet That Doubles as a Hardware Control Surface for Claude
A tiny ESP32 companion turns Claude Desktop state into motion, mood, and physical approvals, then ships custom assets to the device over BLE with a drag-and-drop workflow.
anthropics/skills: The Tiny Spec That Turns Claude Into a Specialist
How a folder, a SKILL.md, and disciplined scripts let Anthropic ship on-demand expertise without flooding the context window.
anthropics/claude-plugins-community Is Not a Plugin Repo. It Is a Gate.
A read-only marketplace mirror, pinned source references, and a private review pipeline turn Claude's plugin ecosystem into a curated catalog instead of an open code dump.
anthropics/healthcare: The Repo That Turns Claude Into a Resumable Workflow Engine
Inside the waypoint system, MCP servers, and deterministic checks that make healthcare AI feel less like chat and more like infrastructure.
connect-rust: One Rust Service, Three RPC Dialects
Anthropic’s Tower-native runtime makes Connect, gRPC, gRPC-Web, and GET feel like the same request path, then backs it up with a spec-first conformance story.
anthropics/financial-services-plugins: Turning Claude Into a Financial Workstation
A plugin, skill, and MCP stack that pushes Claude past chat and into governed financial modeling, deck checking, and audit-ready document generation.
original_performance_takehome: When the interview is a scheduler
Anthropic's original performance take-home strips away compiler magic, exposes the bottlenecks, and asks whether you can fit real work into a rigid machine.
anthropic-cli: The CLI That Announces Itself Before It Exists
Anthropic-cli is interesting because the public repo already does product work. It claims the terminal as a Claude surface before the implementation is visible.
buffa: Protobuf for Rust, Rebuilt Around Borrowed Reads
A pure-Rust runtime that treats protobuf editions as policy, then generates both owned messages and zero-copy views from the same schema.
agent-sdk-workshop: Anthropic’s Agent SDK Workshop Turns Agent Design Into a Set of Switches
A hands-on repo that teaches Claude Agent SDK by revealing tools, subagents, and memory one layer at a time, so readers learn orchestration before syntax.
anthropics/knowledge-work-plugins: The Repo That Builds Specialists From Files
A role pack here is just markdown, JSON, and MCP wiring. The twist is a meta-plugin that can customize and scaffold the rest, turning Claude into a more company-shaped coworker.
claude-constitution: Anthropic turned Claude’s values into a file you can read
A versioned constitution for an AI model is not a product release note. It is governance as code, with trade-offs written out in plain language.
anthropics/tailscale-hint-extension: The Browser Error Page That Diagnoses Tailscale
A tiny Chrome extension turns NXDOMAIN into infrastructure-aware triage, separating bad DNS, dead tunnels, and broken services.
anthropics/homebrew-tap: The Tiny Repo Making Claude Code Feel Native in the Terminal
A one-formula Homebrew tap hides a bigger strategy: binary distribution, shell completions, and the tradeoffs of shipping an AI tool like infrastructure.
claude-code: Claude Code: The Repo That Turns Markdown Into an Agentic CLI
Inside Anthropic’s terminal-native coding tool, where frontmatter becomes permissions, plugins become capabilities, and the shell becomes the agent’s operating environment.
The Compiler in the Chatbox: How anthropics/prompt-eng-interactive-tutorial Formalizes the Black Art of Prompting
Moving beyond "vibes" to build deterministic, production-grade systems with Claude’s hidden structural levers.
Claude Quickstarts: Building a Digital Body for the Model
How Anthropic's reference implementations move AI from the chatbox to the desktop through "Computer Use" and autonomous loops.
Yet to be explained
code-migration-kit-with-claude-code
Explain
Prompts, templates, and scripts for running large-scale language migrations with Claude Code
k12-teacher-skills
Explain
Skills and eval rubrics for K-12 teachers, co-developed with Learning Commons
oncall-kit
Explain
Starter kit for a Claude-assisted on-call: mines your incident history into triage playbooks, sets up through human-approved gates, and runs read-only in your Slack channel — humans deploy every fix.
claude-for-financial-advisors
Explain
Claude for Financial Advisors: a Claude Cowork plugin with ready-to-run workflows for financial advisors, drawing on third-party connectors.
OpenROAD-flow-scripts
Explain
Read-only mirror of The-OpenROAD-Project/OpenROAD-flow-scripts (release tags only). No changes accepted here — contribute upstream.
claude-tag-wif-gateway-sample
Explain
Sample customer-side gateway for Claude Tag identity federation. Sample code; not maintained.