52 个（cheaper-inference 的仓库） · 按人气排序
Run or inspect local Release-Green checks for a specific code revision or combined pull request candidate. Report blocking failures, diagnostic differences, and missing evidence, compare against the base revision, and identify remaining CI checks.
中文简介正在准备中。当前显示英语简介。
Repair confirmed failures in CI, the automated build and test process, starting with the base branch. Then prepare affected pull requests individually, recording checks for the exact code candidate and unresolved issues for owner review.
中文简介正在准备中。当前显示英语简介。
Configure Codex CLI to connect through OmniRoute on Linux, macOS, or Windows. The workflow detects the operating system and shell, creates configuration files and seven profiles, sets environment variables, and verifies the setup.
中文简介正在准备中。当前显示英语简介。
Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the OmniRoute API.
中文简介正在准备中。当前显示原文说明。
管理将OmniRoute事件发送到外部的Webhook，可设置请求完成、失败和配额超限通知，并处理通知地址验证、测试发送、投递历史查询与重试管理。
Keep coding changes small by questioning unnecessary work and reusing existing code, standard libraries, and native platform features. Apply this approach to implementation, bug fixes, reviews, and dependency choices while preserving validation, security, and accessibility.
中文简介正在准备中。当前显示英语简介。
Review AI call logs by provider, model, time range, status, and cost. Aggregate token usage, export logs, configure budgets, and inspect response times and prompt cache statistics to understand usage and performance.
中文简介正在准备中。当前显示英语简介。
Start and stop ngrok, Cloudflare, or custom tunnel connections from the command line. Inspect active URLs, connection status, and logs, configure authentication, and test whether a tunnel can be reached from outside.
中文简介正在准备中。当前显示英语简介。
Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.
中文简介正在准备中。当前显示原文说明。
Submit groups of AI requests as batch jobs with the OmniRoute command line. Manage input files, monitor or cancel jobs, save results and errors, and incorporate batch processing into automated build and deployment workflows.
中文简介正在准备中。当前显示英语简介。
Configure compression for command output, prose, and chat history before sending them to AI providers. Choose suitable engines, adjust language rules, and preview compressed text and reported savings before enabling a mode.
中文简介正在准备中。当前显示英语简介。
Manage Omni Skills, plugins, and persistent memory from the command line. Find and install skills, run them with supplied input, inspect execution history, and maintain saved information alongside plugin installations.
中文简介正在准备中。当前显示英语简介。
Find agent skills for installed coding tools such as Claude Code and Codex. Use OmniRoute to detect available tools, review relevant GitHub matches, and guide installation into each tool’s skill directory.
中文简介正在准备中。当前显示英语简介。
Manage embedded services such as 9Router and CLIProxyAPI through local service APIs. Install, start, stop, restart, or update services, then check their status, retrieve logs, and configure automatic startup.
中文简介正在准备中。当前显示英语简介。
Run scoped quality checks without changing product code. Record the exact revision, commands, logs, and outcomes, then report failures, incomplete checks, and existing unresolved issues to support reviews or release preparation.
中文简介正在准备中。当前显示英语简介。
通过命令行向OmniRoute的A2A服务器发送任务，查看执行历史和日志，监控或取消任务，并交互测试智能体之间的通信。
Inspect AI costs, token usage—the units used to measure model input and output—and call logs from the OmniRoute command line. Filter records, review spending by connection, and export usage reports for further review.
中文简介正在准备中。当前显示英语简介。
Monitor AI provider health, response times, usage quotas, and spending alerts in OmniRoute. Inspect circuit breakers, which temporarily block failing providers, and configure whether reaching a budget limit switches models, blocks requests, or issues warnings.
中文简介正在准备中。当前显示英语简介。
Manage command-line tools connected to OmniRoute through its API. Inspect tool status, read or change settings, manage Codex profiles and backups, and invoke tool plugins for automation tasks.
中文简介正在准备中。当前显示英语简介。
Browse and search OmniRoute's AI model catalog from the command line. Filter by provider or capability, check model aliases, validate compatible models before adding them, and maintain manually registered model details.
中文简介正在准备中。当前显示英语简介。
Carry out reviewed pull request plans, apply approved fixes, and preserve contributor credit. Validate the exact changes being merged, merge only explicitly authorized groups, and keep items on hold when required checks fail or remain unknown.
中文简介正在准备中。当前显示英语简介。
Manage AI provider connections from the terminal. List configured services, test connections individually or together, rotate credentials, and inspect usage metrics. Validate local configuration without contacting providers when checking its structure.
中文简介正在准备中。当前显示英语简介。
Manage cached LLM responses, which are saved answers available for reuse. Inspect statistics and stored entries, clear cached data, and configure expiration policies and similarity thresholds that govern when answers can be reused.
中文简介正在准备中。当前显示英语简介。
Query OmniRoute through A2A, a protocol for communication between agents. Get provider and model recommendations, check remaining quotas, find providers with required features, estimate request costs, and review system health.
中文简介正在准备中。当前显示英语简介。