{"id":18652475,"url":"https://github.com/devidw/inferit","last_synced_at":"2025-10-07T13:52:43.893Z","repository":{"id":261171016,"uuid":"883472319","full_name":"devidw/inferit","owner":"devidw","description":"Visual inference exploration \u0026 experimentation playground","archived":false,"fork":false,"pushed_at":"2024-11-29T22:44:23.000Z","size":2442,"stargazers_count":96,"open_issues_count":1,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-10-01T00:00:04.750Z","etag":null,"topics":["chrome-ai","chromeai","inference-client","openai-compatible-api"],"latest_commit_sha":null,"homepage":"https://inferit.index.garden","language":"Svelte","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/devidw.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"license.txt","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},"funding":{"github":"devidw"}},"created_at":"2024-11-05T02:49:19.000Z","updated_at":"2025-09-27T21:06:52.000Z","dependencies_parsed_at":"2024-11-05T04:26:50.893Z","dependency_job_id":"9efc72d6-cd9b-4b20-a404-3d5c9fddc402","html_url":"https://github.com/devidw/inferit","commit_stats":null,"previous_names":["devidw/inferit"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/devidw/inferit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devidw%2Finferit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devidw%2Finferit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devidw%2Finferit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devidw%2Finferit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/devidw","download_url":"https://codeload.github.com/devidw/inferit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/devidw%2Finferit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278786690,"owners_count":26045588,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-07T02:00:06.786Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["chrome-ai","chromeai","inference-client","openai-compatible-api"],"created_at":"2024-11-07T07:01:36.687Z","updated_at":"2025-10-07T13:52:43.873Z","avatar_url":"https://github.com/devidw.png","language":"Svelte","readme":"\u003ch1 align=\"center\"\u003e\n    \u003cimg src=\"./public/icon_32.png\" alt=\"inferit\" /\u003e\n    \u003cbr /\u003e\n    inferit\n\u003c/h1\u003e\n\n_inferit_ is a visual take on llm inference. Most inference frontends are\nlimited to a single visual input/output \"thread\". This makes it hard to compare\noutput from different models, prompts and sampler settings. _inferit_ solves\nthis with its UI that allows for an unlimited number of side-by-side\ngenerations. This makes it a perfect fit to compare and experiment with\ndifferent models, prompts and sampler settings.\n\n![](./screens/24-11-29.png)\n\n![](./screens/24-11-11_whoami.png)\n\nSome example use cases:\n\n- model exploration and comparison\n- prompt engineering\n- sampler setting optimizations\n\nSupported Backends:\n\n- Any local or remote backend that is compatible with the OpenAI API\n- [Chrome's built-in llm](https://developer.chrome.com/docs/ai/built-in) (Gemini Nano)\n\n## run it\n\n1. I've deployed an instance for instant access here: https://inferit.index.garden (online)\n2. Same code also ships as browser extension to run local and offline w/o having to start a process:\n   https://chromewebstore.google.com/detail/inferit/celkhcifjknihgjlieolcmchofdloagk\n3. Run it locally from this repo:\n   ```bash\n   pnpm install\n   pnpm build\n   pnpm preview\n   ```\n\nonce running, set your api creds in the settings (stored on your device, [window.localStorage](https://developer.mozilla.org/en-US/docs/Web/API/Window/localStorage)) and u are good to go\n\n## development\n\n```bash\npnpm dev\n```\n\n\u003cp align=center\u003e\n    Contributions of any kind are warmly welcomed!\n    \u003cbr\u003e\n    \u0026lt;3\n\u003cp\u003e\n","funding_links":["https://github.com/sponsors/devidw"],"categories":["others","Svelte"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevidw%2Finferit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevidw%2Finferit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevidw%2Finferit/lists"}