awesome-repositories.com
Blog
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoAcerca deCómo clasificamosPrensaServidor MCP
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

4 repositorios

Awesome GitHub RepositoriesToken-Level Incremental Processing

Real-time processing of incoming tokens to identify roles and content in a live stream.

Distinct from Incremental Content Streaming: Focuses on the real-time identification of model roles/content from a token stream, not just UI content updates.

Explore 4 awesome GitHub repositories matching web development · Token-Level Incremental Processing. Refine with filters or upvote what's useful.

Awesome Token-Level Incremental Processing GitHub Repositories

Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
  • openai/harmonyAvatar de openai

    openai/harmony

    4,409Ver en GitHub↗

    Harmony es un SDK de IA diseñado para tokenizar conversaciones, formatear diseños de razonamiento, analizar salidas crudas y definir esquemas de llamadas a herramientas. Proporciona un sistema para convertir diálogos estructurados y llamadas a herramientas en las secuencias de tokens necesarias para la inferencia y el entrenamiento de modelos de lenguaje de gran tamaño. El proyecto incluye un formateador de salida que estructura cadenas de razonamiento y salidas multicanal en diseños consistentes para evitar la pérdida de tokens. También cuenta con un analizador de respuestas que transforma los tokens de finalización crudos y los flujos en vivo de vuelta en objetos de mensaje y roles estructurados. El SDK gestiona la integración de herramientas a través de un framework para definir funciones invocables y espacios de nombres. Además, proporciona capacidades para el análisis de tokens en tiempo real, la configuración del comportamiento del modelo y la serialización de conversaciones con estado.

    Processes incoming tokens one by one to identify roles and content in real-time from a live stream.

    Rust
    Ver en GitHub↗4,409
  • hardmath123/nearleyAvatar de Hardmath123

    Hardmath123/nearley

    3,740Ver en GitHub↗

    Nearley is a JavaScript parser toolkit used to define context-free grammars and generate corresponding parsers. It features an EBNF grammar compiler that transforms language definitions written in extended Backus-Naur Form into executable JavaScript code, utilizing an Earley parser implementation to process any context-free grammar. The toolkit distinguishes itself by its ability to handle left-recursion and ambiguity without failing, allowing it to identify and return multiple valid derivations for a single input string. It also includes a grammar fuzzing generator to produce random strings

    Parses input streams in real time to provide immediate feedback or predictive results in a UI.

    JavaScript
    Ver en GitHub↗3,740
  • kach/nearleyAvatar de kach

    kach/nearley

    3,740Ver en GitHub↗

    Nearley is a JavaScript parser toolkit and context-free grammar compiler. It functions as an Earley parser generator that transforms BNF-like grammar definitions into executable code capable of analyzing text and generating abstract syntax trees. The project is distinguished by its ability to handle any context-free grammar, including those with left recursion and ambiguity, by maintaining multiple valid derivations for a single input. It further supports incremental parsing, allowing input strings to be processed in chunks to provide partial results and real-time feedback. Beyond core parsi

    Processes text streams in small chunks to provide immediate structural feedback for user interfaces.

    JavaScript
    Ver en GitHub↗3,740
  • redhat-developer/yaml-language-serverAvatar de redhat-developer

    redhat-developer/yaml-language-server

    1,486Ver en GitHub↗

    The YAML Language Server is a backend service that provides intelligent editing support for YAML files by implementing the Language Server Protocol. It functions as a validation and analysis engine, enabling code editors to offer real-time diagnostics, structural feedback, and automated assistance for configuration-heavy development workflows. The project distinguishes itself through its schema-driven approach to data integrity, utilizing a JSON Schema validation engine to verify document structure against formal definitions. It supports complex configuration management by allowing developers

    Processes only modified sections of a file to provide immediate feedback without re-parsing the entire document on every keystroke.

    TypeScriptlanguage-serveryamlyaml-support
    Ver en GitHub↗1,486
  1. Home
  2. Web Development
  3. Streaming Rendering
  4. Incremental Content Streaming
  5. Token-Level Incremental Processing

Explorar subetiquetas

  • Incremental Parse FeedbackReal-time processing of input streams to provide immediate structural feedback in user interfaces. **Distinct from Token-Level Incremental Processing:** Distinct from Token-Level Incremental Processing: focuses on returning partial parse trees for UI responsiveness rather than role identification in LLM streams.