@cheaper-inference
Organization
52 skills1 repository 79.4K
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.
The English summary is being prepared. Showing the original description.
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.
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.
Start, stop, and restart the OmniRoute server from the command line. Configure its port, background operation, automatic recovery, and system tray integration, or open the dashboard to manage the running server.
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.
Synchronize OmniRoute configuration, provider connections, and settings with cloud storage. Manage authentication for the cloud worker, a remote service, along with its credentials and remote backup destinations.
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.
The English summary is being prepared. Showing the original description.
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.
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.
Create, list, rotate, and revoke OmniRoute API keys from the CLI. Manage OAuth flows for provider authentication and inspect key scopes and expiration.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
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.
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.
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.
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.
Manage OmniRoute context settings from the command line, including token budgets and RTK filters for processing context. Switch saved server connections, import or export configurations, and inspect or expire conversation sessions.
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.
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.
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.
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.
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.
Check and control OmniRoute’s MCP server, which connects agents to tools. Inspect tool permission scopes, enable or restart the server, and invoke tools with JSON arguments from the command line.
Check OmniRoute server health, component status, and live metrics from the command line. Filter alerts or watch a refreshing dashboard to see provider status and circuit breakers, which interrupt requests when failures occur.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)