Anthropic
@anthropics • Open source projects from anthropics. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
63%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
29 repos
Visible snapshot
23 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (7), Unknown (6), HTML (3)
Average size
667
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-05-13(122d ago)GitHub API fallback29 repositories
63%
of the visible star count comes from this organization's top three repositories.
667
stars per repository in this same snapshot.
Python
is the most common language here, with 23 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 29 repositories.
Balanced portfolio across 29 reposTop 3 share 63%
Organization pages work best when you separate portfolio breadth from flagship concentration. In Anthropic's case, the visible top three repositories account for about 63% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (7), Unknown (6), HTML (3). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | anthropics/defending-code-reference-harness Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize | Python | 7.4K |
| 2 | anthropics/commerce-agents Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. | Python | 2.7K |
| 3 | anthropics/cwc-workshops | TypeScript | 2.1K |
| 4 | anthropics/jacobian-lens Companion code for the global workspace interpretability paper | Python | 1.9K |
| 5 | anthropics/fermats-last-theorem | Lean | 1.1K |
| 6 | anthropics/launch-your-agent 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 | HTML | 988 |
| 7 | anthropics/cwc-long-running-agents | Shell | 678 |
| 8 | anthropics/html-effectiveness HTML effectiveness examples | HTML | 651 |
| 9 | anthropics/k12-teacher-skills Skills and eval rubrics for K-12 teachers, co-developed with Learning Commons | Python | 498 |
| 10 | anthropics/code-migration-kit-with-claude-code Prompts, templates, and scripts for running large-scale language migrations with Claude Code | Python | 332 |
| 11 | anthropics/ClaudeForFoundationModels Claude support for Apple Foundation Models | Swift | 290 |
| 12 | anthropics/formal-math | Lean | 238 |
| 13 | anthropics/oncall-kit 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. | Python | 148 |
| 14 | anthropics/cryptography-research-demo | C | 65 |
| 15 | anthropics/cargo-nix-plugin A Nix plugin that resolves Cargo workspaces natively and allows for crate level builds | Rust | 56 |
| 16 | anthropics/claude-tag-plugins | Shell | 48 |
| 17 | anthropics/mythos-5-incident-transcript | HTML | 45 |
| 18 | anthropics/headvis Head Vis Public Release | Svelte | 41 |
| 19 | anthropics/swift-markdown A Swift package for parsing, building, editing, and analyzing Markdown documents. | 18 | |
| 20 | anthropics/riegeli-rs | 7 | |
| 21 | anthropics/mockturtle | C++ | 4 |
| 22 | anthropics/xls Fork of google/xls — main tracks upstream; Anthropic changes live on anthropic-* branches | 2 | |
| 23 | anthropics/rayon Rayon: A data parallelism library for Rust | 2 | |
| 24 | anthropics/leptos-chartistry Chartistry is an extensible charting library for Leptos | 1 | |
| 25 | anthropics/raft-rs Raft distributed consensus algorithm implemented in Rust. | 0 | |
| 26 | anthropics/axt-verify | Go | 0 |
| 27 | anthropics/claude-tag-wif-gateway-sample Sample customer-side gateway for Claude Tag identity federation. Sample code; not maintained. | Python | 0 |
| 28 | anthropics/amulet2 | C++ | 0 |
| 29 | anthropics/OpenROAD-flow-scripts Read-only mirror of The-OpenROAD-Project/OpenROAD-flow-scripts (release tags only). No changes accepted here — contribute upstream. | Verilog | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.