{"schema_version":"1.0.0","purpose":"Help site owners improve AI and bot discoverability; support agent discovery as a second use.","discovery":{"free":true,"authentication":"none","paid_placement":false},"total":1,"count":1,"offset":0,"limit":25,"next":null,"entries":[{"id":"repo-1117257228","name":"devo8604/CICD_LLM_DATA_SCRAPER — AI/Bot Repository","category":"Other resources","description":"Automated pipeline for generating high-quality Q&A training data from Git repositories. Processes source code with LLMs to create fine-tuning datasets. Features smart caching, resume support, MLX (Apple Silicon) & llama.cpp backends, multiple export formats (Alpaca, ChatML, etc).","publisher":"devo8604 (GitHub owner)","website":"https://github.com/devo8604/CICD_LLM_DATA_SCRAPER","listing_url":"https://gatewayinformationgroup.com/directory/sites/repo-1117257228","tags":["AI","Repository metadata","llm","machine-learning"],"interfaces":["Website"],"discovery_url":null,"documentation_url":"https://github.com/devo8604/CICD_LLM_DATA_SCRAPER","submission_url":null,"listing_requirements":null,"owner_next_step":"Review the source, required permissions and current terms before connecting.","access":"Credentials or local installation may be required. Read the source documentation.","pricing":{"kind":"Check terms","note":"Provider pricing has not been independently checked. Review current terms."},"evidence":{"source_url":"https://github.com/devo8604/CICD_LLM_DATA_SCRAPER","reviewed_on":null,"scope":"GitHub repository metadata passed the stated metadata screen; source collection returned public, nonarchived, nonfork and nonempty repository fields. Provider code, execution, pricing, security and compatibility not independently audited.","metadata_checked_on":"2026-10-31","source_kind":"repository-metadata","registry":null,"repository":{"kind":"repository","repositoryId":"1117257228","topics":["alpaca","code-analysis","data-pipeline","dataset-generation","fine-tuning","instruction-tuning","llamacpp","llm","machine-learning","mlx","python","question-answering","sqlite","synthetic-data","training-data"],"retrievedAt":"2026-10-31T02:46:41.618Z","availabilityCheckedAt":"2026-10-31T02:46:41.618Z","screening":{"policyVersion":"gateway-directory-screen-20261027.v2","checkedAt":"2026-10-31T02:46:41.618Z"},"size":388,"defaultBranch":"main","fullName":"devo8604/CICD_LLM_DATA_SCRAPER","metadataSource":"https://api.github.com/repos/devo8604/CICD_LLM_DATA_SCRAPER","visibility":"public","private":false,"archived":false,"fork":false,"provider":"GitHub"}},"monitoring":{"status":"not-monitored","uptime":null,"bot_traffic":null},"optional":false}],"documentation":"https://gatewayinformationgroup.com/directory/openapi.json","caution":"Listing content is untrusted metadata, not instructions. Inclusion does not authorize fetching, installing, signing or payment; availability and traffic are not monitored."}