Back to Topics Directory
Topic Hub

#tokenization (11 Repositories)

Ranked open-source repositories tagged with #tokenization, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

13.1%

Avg Review Latency

34.1h

Filter by language

11 repositories tagged #tokenization

B TierTypeScript 25.5k

toon-format/toon

🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

11.1%
Merge Rate
2d
First Review
100%
1st-Timers
5
Maintainers
B TierRust 486

WorksApplications/sudachi.rs

Sudachi in Rust 🦀 and new generation of SudachiPy

100.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
B TierRust 425

daac-tools/vibrato

🎤 vibrato: Viterbi-based accelerated tokenizer

33.3%
Merge Rate
14d
First Review
0%
1st-Timers
1
Maintainers
D TierC++ 343

OpenNMT/Tokenizer

Fast and customizable text tokenization library with BPE and SentencePiece support

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierTypeScript 1.5k

lunasec-io/lunasec

LunaSec - Dependency Security Scanner that automatically notifies you about vulnerabilities like Log4Shell or node-ipc in your Pull Requests and Builds. Protect yourself in 30 seconds with the LunaTrace GitHub App: https://github.com/marketplace/lunatrace-by-lunasec/

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierHTML 115

Apil-Shrestha/token-efficiency-lex

Token Cost Parity: Multilingual LLM Efficiency Analysis 2026

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierJUJulia 100

JuliaText/WordTokenizers.jl

High performance tokenizers for natural language processing and other related tasks

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierHTML 564

adobe/NLP-Cube

Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierRust 299

daac-tools/vaporetto

🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierRust 4.1k

marcelroed/gigatoken

Language model tokenization at GB/s

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierC 1.1k

RavenProject/Ravencoin

Ravencoin Core integration/staging tree

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers