# simdutf/simdutf

Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extension, LoongArch64, POWER. Part of Node.js, WebKit/Safari, Ladybird, Chromium, Cloudflare Workers,  Ghostty and Bun.

Repository: https://github.com/simdutf/simdutf
Canonical: https://ross.abutalabs.com/products/simdutf
Homepage: https://simdutf.github.io/simdutf/
Language: C++
License: Apache-2.0
License Family: permissive
Topics: utf8, utf16, unicode, simd, neon, avx2, sse2, transcoding, avx-512, risc-v, base64, ppc64le
Last push: 2026-08-19T20:53:54+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 98, longevity 100
- inputs: {"age_days": 2037, "days_push": 14, "days_rel": 15, "gap_med": 9, "n_releases_24m": 44}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1938, forks 149 (observed 2026-08-28T04:05:57.111446+00:00)

## What it is
simdutf is a high-performance C++ library for Unicode validation, transcoding (UTF-8, UTF-16, UTF-32, Latin1, ASCII) and WHATWG-compliant Base64 encode/decode, accelerated with SIMD instructions. It achieves billions of characters per second and is used in production by Node.js, WebKit, Chromium, Bun, and Cloudflare Workers.

## Use cases
- validate utf-8 strings at high speed
- convert between utf-8 and utf-16
- transcode unicode text with simd acceleration
- decode and encode base64 fast
- check if byte sequences are valid unicode
- fast ascii validation in c++
- convert latin1 to utf-8

## When to choose
- you need maximum-throughput unicode validation or transcoding in C/C++
- you are building a runtime, parser, or server that processes large volumes of text
- you need WHATWG-compliant base64 at multi-GB/s speeds
- you want a dependency-free, allocation-free, noexcept library with a C API option

## When to avoid
- you need higher-level text processing like collation, normalization, or case mapping (use ICU)
- you work in a managed language with adequate built-in encoding support and no performance bottleneck
- you need locale-aware string operations

## Facets
- artifact type: library
- maturity: stable
- function: serialization, parser, developer-tools
- domain: developer-tools, performance
- platform: cpp, cross-platform, windows
- tags: simd, unicode, utf8, utf16, utf32, base64, transcoding, validation, avx2, avx-512, neon, risc-v, high-performance, algorithms, natural-language-processing, linux, macos, gpu

## Member repositories
- simdutf/simdutf (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:57.111446+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:08:13.482182+00:00, confidence not recorded.
  - readme: https://github.com/simdutf/simdutf (fetched 2026-08-28T04:05:57.111446+00:00, sha 48ffe7c59fa1)
  - homepage: https://simdutf.github.io/simdutf/ (fetched 2026-08-29T10:47:32.623088+00:00, sha 723d3cd2d06e)
- Data as of 2026-08-30T08:39:29.467469+00:00.