{"id":28227608,"url":"https://github.com/mlang/llm-api","last_synced_at":"2026-02-06T16:07:21.396Z","repository":{"id":292799420,"uuid":"981961139","full_name":"mlang/llm-api","owner":"mlang","description":"Run a multimodal LLM API server","archived":false,"fork":false,"pushed_at":"2025-11-05T03:25:05.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-01-28T00:40:14.584Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Makefile","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mlang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-12T07:02:36.000Z","updated_at":"2025-11-05T03:25:09.000Z","dependencies_parsed_at":null,"dependency_job_id":"922c3b3c-ae71-4916-9f04-674477774109","html_url":"https://github.com/mlang/llm-api","commit_stats":null,"previous_names":["mlang/llm-api"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mlang/llm-api","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-api","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-api/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-api/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-api/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlang","download_url":"https://codeload.github.com/mlang/llm-api/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlang%2Fllm-api/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29167871,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-06T15:38:29.831Z","status":"ssl_error","status_checked_at":"2026-02-06T15:37:48.592Z","response_time":59,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-05-18T13:16:08.900Z","updated_at":"2026-02-06T16:07:21.381Z","avatar_url":"https://github.com/mlang.png","language":"Makefile","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Run a (multimodal) LLM API server as a systemd user service\n\nThis is a small wrapper to build and run a llama.cpp llama-server\nto serve a (multimodal) LLM.\n\n## Installation\n\nClone the repository, build the llama-server and install a systemd user service:\n\n```sh\ngit clone https://github.com/mlang/llm-api\nmake -C llm-api\n```\n\nThe file `llm-api/Makefile` contains a `MODEL` variable at the top of the file.\nIt is preet to a model that should fit in 16GB RAM.\nChange the `MODEL` variable if you want to use a different HuggingFace model.\n\nTo download the model and test the server, execute:\n\n```sh\nmake -C llm-api llm-api\n```\n\nThe LLM API will listen on 127.0.1.9:8080.\n\nIf this runs fine, you can start the systemd user service with:\n\n```sh\nsystemctl --user start llm-api\n```\n\n### API client\n\nIf you are using the llm Python package, you can\ncopy the file `llm-api/extra-openai-models.yaml` to your llm config directory:\n\n```sh\nln -s $(pwd)/llm-api/extra-openai-models.yaml ~/.config/io.datasette.llm/\n```\n\n## Usage\n\nAssuming you are using the llm Python package, you can describe an image with:\n\n```sh\nllm -m local -a image.jpg\n```\n\nIf this works, you can enable the llm-api service permanently with:\n\n```sh\nsystemctl --user enable llm-api\n```\n\nThis will start the llm-api service when you log in with the current user.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlang%2Fllm-api","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlang%2Fllm-api","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlang%2Fllm-api/lists"}