awesome-repositories.com
Blog
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

4 repository-uri

Awesome GitHub RepositoriesCode Execution Runtimes

Isolated environments specifically designed for executing code generated by AI models during inference.

Distinct from Containerized Execution Environments: Focuses on the runtime execution of AI-generated code for data processing, rather than general infrastructure isolation.

Explore 4 awesome GitHub repositories matching devops & infrastructure · Code Execution Runtimes. Refine with filters or upvote what's useful.

Awesome Code Execution Runtimes GitHub Repositories

Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
  • openai/gpt-ossAvatar openai

    openai/gpt-oss

    20,191Vezi pe GitHub↗

    gpt-oss is an open-weight large language model and reasoning engine designed for complex reasoning and agentic workflows. It functions as an AI agent framework and model serving API, allowing for local deployment and the hosting of standardized interfaces to expose model completions and internal reasoning processes. The project distinguishes itself as a quantized inference engine, utilizing tensor parallelism and weight quantization to run high-parameter models on limited hardware. It features a reasoning model that employs chain-of-thought processing to solve multi-step logical tasks. The s

    Runs Python scripts within secure stateless containers to perform calculations and process data during inference.

    Python
    Vezi pe GitHub↗20,191
  • alibaba/opensandboxAvatar alibaba

    alibaba/OpenSandbox

    11,682Vezi pe GitHub↗

    OpenSandbox is a secure sandbox runtime and containerized code execution engine designed to run AI-generated code and scripts in isolated environments. It serves as a workload orchestrator that prevents host system contamination by utilizing kernel-level isolation to execute arbitrary commands and scripts. The project distinguishes itself by providing a model context server that bridges large language models to the sandbox for performing file operations and system commands. It also includes a remote GUI sandbox that supports browser automation and desktop interfaces via remote access protocol

    Manages the lifecycle of isolated runtimes specifically designed for executing AI-generated code.

    Python
    Vezi pe GitHub↗11,682
  • algorithmicsuperintelligence/optillmAvatar algorithmicsuperintelligence

    algorithmicsuperintelligence/optillm

    4,157Vezi pe GitHub↗

    OptiLLM este un framework de raționament și optimizare AI care funcționează ca un proxy API pentru a îmbunătăți calitatea răspunsurilor modelelor de limbaj mari (LLM). Acesta interceptează cererile pentru a aplica logică de raționament în timpul inferenței și rafinarea output-ului înainte de a returna rezultatele către client. Proiectul se distinge printr-o combinație de arbori de căutare în timpul inferenței pentru verificare logică și un pipeline de anonimizare care elimină informațiile de identificare personală din prompturi. De asemenea, extinde capabilitățile modelului prin orchestrarea unor instrumente externe, inclusiv execuția de cod în timp real și cercetarea web autonomă. Sistemul oferă o infrastructură extinsă pentru gestionarea modelelor, incluzând echilibrarea sarcinii între mai mulți furnizori și capacitatea de a servi modele și adaptoare locale. De asemenea, gestionează impunerea output-ului structurat prin constrângeri de schemă și gestionează istoricul conversațiilor extinse printr-un strat de memorie virtuală de context. Stratul proxy este conceput pentru a fi compatibil cu endpoint-urile API standard, permițând integrarea fără a modifica codul client existent.

    Provides a code execution runtime to validate logic and perform calculations within the model inference loop.

    Python
    Vezi pe GitHub↗4,157
  • e2b-dev/code-interpreterAvatar e2b-dev

    e2b-dev/code-interpreter

    2,348Vezi pe GitHub↗

    This project is an infrastructure platform designed to provide secure, isolated, and ephemeral cloud-based Linux environments for AI agents and automated code execution. It functions as an orchestrator that provisions on-demand virtual machines, allowing developers to run arbitrary code generated by large language models within hardware-level security boundaries. The platform distinguishes itself through its ability to manage stateful, long-lived sessions that persist across multiple execution calls, enabling complex, multi-step workflows. It supports high-concurrency scaling, allowing for th

    Provides a secure infrastructure platform for running arbitrary code produced by large language models in ephemeral containers.

    Pythonaiai-data-analysisanthropic
    Vezi pe GitHub↗2,348
  1. Home
  2. DevOps & Infrastructure
  3. Containerized Execution Environments
  4. Code Execution Runtimes