52 个（cheaper-inference 的仓库） · 按人气排序
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。
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。
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 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。
Review OmniRoute audit logs and request history from the command line. Filter records by actor, action, or time, manage access rules, and export logs or compare operational data for compliance reviews.
中文简介正在准备中。当前显示英语简介。
Create and run automated tests that score LLM answers against expected outputs or judging criteria. Monitor progress, inspect individual results, compare models on the same tests, and use score thresholds in CI, an automated checking workflow.
中文简介正在准备中。当前显示英语简介。
通过命令行启动、停止和重启 OmniRoute 服务器，指定端口，配置后台运行、自动恢复和系统托盘显示，并打开管理面板。
Connect AI agents to OmniRoute through MCP, a protocol for accessing tools. Use tools for request routing, memory, cache, providers, and audits, with three connection methods and permission scopes that control which operations are available.
中文简介正在准备中。当前显示英语简介。
Create, list, rotate, and revoke OmniRoute API keys. Control per-key scopes, spending limits, and expiration. Keys gate access to all proxy and management endpoints.
中文简介正在准备中。当前显示原文说明。
Create and manage secure tunnels that make OmniRoute accessible over the internet. Use ngrok, Cloudflare Tunnel, or a custom tunnel to share access with remote agents and automated build and test pipelines.
中文简介正在准备中。当前显示英语简介。
Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.
中文简介正在准备中。当前显示英语简介。
Create, list, rotate, and revoke OmniRoute API keys from the CLI. Manage OAuth flows for provider authentication and inspect key scopes and expiration.
中文简介正在准备中。当前显示原文说明。
Manage provider connections, API keys, OAuth flows, and connection tests via the REST API. List, add, update, remove, and test AI provider integrations across OmniRoute's 375-provider catalog.
中文简介正在准备中。当前显示原文说明。
Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.
中文简介正在准备中。当前显示英语简介。
Create, list, switch, and delete model routing combinations from the command line. Request suggestions using task descriptions, cost limits, and response time limits, with an option to explain recommendations or activate a suggested setup.
中文简介正在准备中。当前显示英语简介。
Inspect OmniRoute connection restrictions, usage quotas, and retry delays from the command line. Reset stuck providers and adjust failure thresholds, cooldowns, and recovery timing to manage how connections respond to errors.
中文简介正在准备中。当前显示英语简介。
Group AI providers and models behind one model ID in OmniRoute. Choose among 19 routing strategies, define fallback sequences for failures, simulate which provider will be selected, and inspect latency, success rates, and costs.
中文简介正在准备中。当前显示英语简介。
Set up OmniRoute and manage its command-line configuration. Inspect and validate tool settings, manage environment variables, check for updates, and control automatic startup using commands that support both interactive and unattended setup.
中文简介正在准备中。当前显示英语简介。
Manage how context, the text supplied to an AI, is compressed with RTK filters. Preview compression on real prompts, validate and install filter files, and inspect filter loading diagnostics.
中文简介正在准备中。当前显示英语简介。
Set spending limits, token quotas, and rate limits, which restrict requests over time. Review current consumption and apply controls per API key or globally to manage AI costs across providers.
中文简介正在准备中。当前显示英语简介。
Send prompts to LLMs from a terminal, display answers as they arrive, or hold an ongoing conversation. Use files or standard input for prompts, choose models, and set system instructions through OmniRoute.
中文简介正在准备中。当前显示英语简介。
Prepare a selected batch of pull requests, or proposed code changes, by reviewing overlaps, diagnosing conflicts, and preserving contributor credit. Check the exact version and required authorization before each merge, then report completed work and remaining holds.
中文简介正在准备中。当前显示英语简介。
Configure HTTP, HTTPS, and SOCKS proxies for requests to external providers. Manage shared or provider-specific rules, test connections, and control proxy rotation to define which intermediary servers handle outgoing requests.
中文简介正在准备中。当前显示英语简介。
通过OmniRoute命令行查看MCP服务器状态和工具权限范围，启用、停用或重启服务器，并使用JSON参数或参数文件调用工具以检查运行情况。