Public GitHub footprint of Anthropic

Public repository for Agent Skills

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Anthropic's Interactive Prompt Engineering Tutorial

No description provided for this repository.

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Anthropic's educational courses

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

A suite of plugins for legal workflows

No description provided for this repository.

No description provided for this repository.

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

Anthropic's original performance take-home, now open for you to try!

No description provided for this repository.

Claude Opus 4.6 wrote a dependency-free C compiler in Rust, with backends targeting x86 (64- and 32-bit), ARM, and RISC-V, capable of compiling a booting Linux kernel.

Claude Code SDK Demos

Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop

Access to Anthropic's safety-first language model APIs in TypeScript

No description provided for this repository.

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

No description provided for this repository.

Companion code for the global workspace interpretability paper

Access to Anthropic's safety-first language model APIs via Go

This repo is a mirror of the contents of base-action in https://github.com/anthropics/claude-code-action.

Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views

HTML effectiveness examples

No description provided for this repository.

The CLI for the Claude API

Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to host the marketplace.json long-term, but not the actual MCP servers.

No description provided for this repository.

No description provided for this repository.

Report issues related to MCP integration with Claude here.

No description provided for this repository.

No description provided for this repository.

No description provided for this repository.

No description provided for this repository.

Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission.

Access to Anthropic's safety-first language model APIs in C#

Anthropic Dev Container Features, including Claude Code CLI

Claude support for Apple Foundation Models

No description provided for this repository.

A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations

Prompts, templates, and scripts for running large-scale language migrations with Claude Code

Lightweight demo using the Anthropic Python SDK to experiment with Claude's Search and Retrieval capabilities over a variety of knowledge bases (Elasticsearch, vector databases, web search, and Wikipedia).

Access to Anthropic's safety-first language model APIs in PHP

Skills and eval rubrics for K-12 teachers, co-developed with Learning Commons

Notebooks accompanying Anthropic's "Toy Models of Superposition" paper

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

This repo contains detailed implementation information about Anthropic's paired prompts approach for evaluating political neutrality.

GitHub's official MCP Server

The foundational document describing Claude's values and behavior

No description provided for this repository.

https://transformer-circuits.pub/2025/attribution-graphs/methods.html

No description provided for this repository.

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

No description provided for this repository.

Display and customize Markdown text in SwiftUI

No description provided for this repository.

A Nix plugin that resolves Cargo workspaces natively and allows for crate level builds

"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files

Head Vis Public Release

No description provided for this repository.

Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation

No description provided for this repository.

No description provided for this repository.

No description provided for this repository.

No description provided for this repository.

Development repository for the Triton language and compiler

Homebrew formulae for Anthropic tools.

A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...

Supplementary materials for Claude Model Cards

Maestro: Netflix’s Workflow Orchestrator

No description provided for this repository.

Chrome extension showing helpful troubleshooting when Tailscale .local domains fail to resolve

A minimal HTTP client. ⚙️

Hypercorn is an ASGI and WSGI Server based on Hyper libraries and inspired by Gunicorn.

No description provided for this repository.

Apache Beam is a unified programming model for Batch and Streaming data processing.

No description provided for this repository.

A Swift package for parsing, building, editing, and analyzing Markdown documents.

Declarative Continuous Deployment for Kubernetes

Terragrunt is a flexible orchestration tool that allows Infrastructure as Code written in OpenTofu/Terraform to scale.

Serialization library for Exceptions and Tracebacks.

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

No description provided for this repository.

Like Python's faulthandler module, but also prints the C call stack

No description provided for this repository.

No description provided for this repository.

Parallel nix evaluator with a streamable json output [maintainers @Mic92, @adisbladis]

No description provided for this repository.

Chartistry is an extensible charting library for Leptos

No description provided for this repository.

Rayon: A data parallelism library for Rust