642 个（diegosouzapw 的仓库） · 按人气排序
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。
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。
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。
Connect AI agents to OmniRoute for text and image generation, speech synthesis, transcription, and web search. Use OpenAI-compatible APIs and create embeddings, numerical representations of text, through documented requests.
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。
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.
中文简介正在准备中。当前显示英语简介。
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。
Set up and check OmniRoute authentication for API access and dashboard sessions. Use Bearer credentials for remote requests, manage login cookies, inspect authentication status, and configure OIDC, a standard for signing in through an identity provider.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
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。
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。
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。
Handle system backups and restore data from backup files while managing a SQLite database. The skill also covers data export, import, and incremental snapshots, which capture changes since an earlier saved state.
中文简介正在准备中。当前显示英语简介。
Register and manage webhook endpoints, which receive event notifications from OmniRoute. Choose events such as completed requests or exceeded quotas, test delivery, inspect delivery history, and manage retries when notifications need another attempt.
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。
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.
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。
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。
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。
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.
中文简介正在准备中。当前显示英语简介。
Prepare selected pull requests for maintainer review by comparing failures with their current base, fixing authorized defects, and preserving contributor credit. Report complete or partial validation with evidence and outstanding checks before any separately authorized merge.
中文简介正在准备中。当前显示英语简介。
Manage AI service connections in OmniRoute through its API. Add, update, remove, and test connections, maintain API keys and sign-in credentials, and inspect usage metrics and connection health.
中文简介正在准备中。当前显示英语简介。
Find available AI models across configured providers and browse a catalog that includes provider-specific variants. Inspect individual models and create or update aliases, alternative names used to refer to models.
中文简介正在准备中。当前显示英语简介。
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。