Skip to content
mcp/harbor

LLM Gateway changelog

io.github.theopenco/llmgateway

2 changes recorded. MCP Harbor re-reads this listing from the official registry every six hours and asks the live server what it exposes, and keeps what changed between one look and the next.

  • AGENTS.md +4 −2

    https://raw.githubusercontent.com/theopenco/llmgateway/HEAD/AGENTS.md 

    − - Always use pnpm for package management.− - After opening or pushing to a PR, wait for CodeRabbit, then fix every failed pre-merge check and every finding, or resolve it with a one-line reason, before handing off. Docstring Coverage is CodeRabbit's default, not a repo rule; ignore it.+ - Always use pnpm for package management. When bumping pnpm, update both `.tool-versions` and `packageManager` in the root `package.json`; Dependabot reads only `packageManager` and otherwise regenerates the lockfile with a newer pnpm that CI rejects.+ - After opening or pushing to a PR, wait for CodeRabbit, then fix every failed pre-merge check before handing off.+ - Open review feedback (CodeRabbit or human) blocks the merge. Address every item: implement the fix and push, or dismiss it with a one-line reason, then resolve the thread. Docstring Coverage is CodeRabbit's default, not a repo rule; ignore it.+ - Write pull request links in full (`https://github.com/theopenco/llmgateway/pull/<n>`) in every PR status, summary and handoff, never as a bare `#<n>`; a commit hash does not replace the PR link.
  • llms.txt +22 −21

    https://docs.llmgateway.io/llms.txt 

    − - [Notifications](https://docs.llmgateway.io/features/notifications): Receive budget, model retirement, provider health, compliance, and organization limit alerts− - [Health check](https://docs.llmgateway.io/health): Health check endpoint.− - [Create speech](https://docs.llmgateway.io/v1_audio_speech): >-− - [Create transcription](https://docs.llmgateway.io/v1_audio_transcriptions): >-− - [Chat Completions](https://docs.llmgateway.io/v1_chat_completions): Create a completion for the chat conversation− - [Decisions](https://docs.llmgateway.io/v1_decisions): >-− - [Embeddings](https://docs.llmgateway.io/v1_embeddings): >-− - [Create image](https://docs.llmgateway.io/v1_images_generations): >-− - [Retrieve key status](https://docs.llmgateway.io/v1_key_retrieve): >-− - [Anthropic Messages](https://docs.llmgateway.io/v1_messages): Create a message using Anthropic's API format− - [Models](https://docs.llmgateway.io/v1_models): >-− - [Moderations](https://docs.llmgateway.io/v1_moderations): Classify text or multimodal inputs with OpenAI moderation.− - [OCR](https://docs.llmgateway.io/v1_ocr): >-− - [Create a realtime client secret](https://docs.llmgateway.io/v1_realtime_client_secrets)− - [Rerank](https://docs.llmgateway.io/v1_rerank): >-− - [Search](https://docs.llmgateway.io/v1_search): >-− - [System One](https://docs.llmgateway.io/v1_systemone): >-− - [Video content](https://docs.llmgateway.io/v1_videos_content): >-− - [Create video](https://docs.llmgateway.io/v1_videos_create): >-− - [Video log content](https://docs.llmgateway.io/v1_videos_log_content): >-− - [Retrieve video](https://docs.llmgateway.io/v1_videos_retrieve): Retrieves the current state of a video generation job.+ - [Notifications](https://docs.llmgateway.io/features/notifications): Receive budget, model retirement, price change, provider health, compliance, and organization limit alerts+ - [Projects](https://docs.llmgateway.io/learn/projects): See usage and activity for every project, and edit or archive several at once+ - [Health check](https://docs.llmgateway.io/health): Health check endpoint. API reference for GET /: request parameters, response schema and code samples.+ - [Create speech](https://docs.llmgateway.io/v1_audio_speech): Generates audio from input text (text-to-speech). Returns the audio file as binary data.+ - [Create transcription](https://docs.llmgateway.io/v1_audio_transcriptions): Transcribes audio into text (speech-to-text) with word-level timestamps. The request body is multipart/form-data carrying the audio file (or a URL to it).+ - [Chat Completions](https://docs.llmgateway.io/v1_chat_completions): Create a completion for the chat conversation. API reference for POST /v1/chat/completions: request parameters, response schema and code samples.+ - [Decisions](https://docs.llmgateway.io/v1_decisions): Evaluate text or images against typed questions and get calibrated predicate, choice and score answers back. OpenAI-compatible API.+ - [Embeddings](https://docs.llmgateway.io/v1_embeddings): Generate vector embeddings for one or more inputs using an OpenAI-compatible embeddings model.+ - [Create image](https://docs.llmgateway.io/v1_images_generations): Creates an image given a prompt. Internally routes to a chat completions model with image generation capabilities.+ - [Retrieve key status](https://docs.llmgateway.io/v1_key_retrieve): Returns usage information for the API key used to authenticate the request, including the organization's dev plan allowance and weekly premium-model usage.+ - [Anthropic Messages](https://docs.llmgateway.io/v1_messages): Create a message using Anthropic's API format. API reference for POST /v1/messages: request parameters, response schema and code samples.+ - [Models](https://docs.llmgateway.io/v1_models): List the public model catalogue without authentication.+ - [Moderations](https://docs.llmgateway.io/v1_moderations): Classify text or multimodal inputs with OpenAI moderation. API reference for POST /v1/moderations: request parameters, response schema and code samples.+ - [OCR](https://docs.llmgateway.io/v1_ocr): Extract text and structure from a document or image as markdown using an OCR model.+ - [Create a realtime client secret](https://docs.llmgateway.io/v1_realtime_client_secrets): Create a realtime client secret. API reference for POST /v1/realtime/client_secrets: request parameters, response schema and code samples.+ - [Rerank](https://docs.llmgateway.io/v1_rerank): Rerank documents against a query using a cross-encoder reranker. Cohere-compatible API.+ - [Search](https://docs.llmgateway.io/v1_search): Search the web and return ranked results with extracted page content. Perplexity Search API-compatible.+ - [System One](https://docs.llmgateway.io/v1_systemone): Evaluate a state against named typed questions and get calibrated yes/no, choice and score answers back. TypeSafe-compatible API, serving TypeSafe models only.+ - [Video content](https://docs.llmgateway.io/v1_videos_content): Streams the generated video content once the job has completed successfully.+ - [Create video](https://docs.llmgateway.io/v1_videos_create): Creates a new asynchronous video generation job using an OpenAI-compatible request format.+ - [Video log content](https://docs.llmgateway.io/v1_videos_log_content): Streams generated video content through a gateway-managed proxy URL keyed by log ID.+ - [Retrieve video](https://docs.llmgateway.io/v1_videos_retrieve): Retrieves the current state of a video generation job. API reference for GET /v1/videos/{video_id}: request parameters, response schema and code samples.
LLM Gateway MCP server