Search Results for "openai codex"

OpenAI Agent Skills is an open-source repository that serves as a broad catalog of agent skills designed to extend the capabilities of OpenAI Codex and other AI coding agents. It organizes reusable, task-specific workflows, instructions, scripts, and resources into modular skill folders so that an AI agent can reliably perform complex tasks without repeated custom prompting, making agent behavior more predictable and composable.

Claude Codex Settings is a configuration-focused repository that provides curated settings, prompts, and workflow optimizations for improving AI-assisted coding environments. It is designed to help developers fine-tune how Claude and similar models behave within coding workflows, ensuring more consistent and high-quality outputs. The project emphasizes practical usability, offering ready-to-use configurations that can be directly integrated into development environments. It also includes...

...The benchmark has become a standard for evaluating code generation models, including those in the Codex and GPT families. Researchers can use the dataset to run reproducible comparisons across models and track improvements in functional code synthesis. By focusing on correctness through execution, human-eval provides a rigorous and practical way to evaluate programming capabilities in AI systems.

Flow-Next is a workflow orchestration tool designed to manage complex processes by structuring tasks into organized and repeatable pipelines. It focuses on improving productivity by allowing users to define workflows that can be executed step by step or in parallel. The system emphasizes modularity, enabling tasks to be broken down into smaller components that can be reused across different workflows. It supports integration with various tools and services, making it adaptable to different...

...Each skill is a self-contained folder with structured metadata and guidance that tells an agent how to execute tasks such as dataset creation, model training, evaluation, or Hub operations. The project is designed to be interoperable across major agent ecosystems, including Claude Code, OpenAI Codex, Gemini CLI, and Cursor, making it a cross-platform building block for agent automation. By formalizing best practices and workflows, Skills helps transform general-purpose coding agents into domain-aware assistants that can execute complex ML pipelines with less manual prompting. The repository also includes ready-to-use skills for common Hugging Face operations and encourages teams to extend them with custom domain logic.

...It orchestrates dozens of agent types across swarms that handle designated roles — such as architecture, coding, QA, deployment, and business workflows — running in parallel to cover both engineering and operational tasks without continuous human intervention. By supporting multiple AI providers (like Claude Code, OpenAI Codex CLI, and Google Gemini CLI), loki-mode dynamically selects and spawns only the needed agents for a given project, optimizing computational resources and task throughput. Its Reason-Act-Reflect-Verify (RARV) cycle with self-verification loops emphasizes quality and resilience, automating end-to-end development lifecycles.

Orbi takes a GitHub Issue from label to release. When an Issue is marked ai-ready, Orbi builds the change in a dedicated worktree and opens a pull request. A reviewer agent, separate from the one that wrote the code, compares the PR with the Issue's acceptance criteria and repairs it. Orbi then merges only that reviewed head and publishes a tagged GitHub release. It is installed from the GitHub repo, with the CLI on PyPI as orbi-cli and Docker images on GHCR and Docker Hub, and can also be...