{"id":50297156,"url":"https://github.com/auraoneai/open","last_synced_at":"2026-05-28T09:34:33.857Z","repository":{"id":357184448,"uuid":"1235807245","full_name":"auraoneai/open","owner":"auraoneai","description":"Open tools for the human-judgment layer of AI evaluation: EvalKit (Python package + CLI), Robotics ReviewKit, and the Buying Toolkit.","archived":false,"fork":false,"pushed_at":"2026-05-11T19:04:17.000Z","size":193,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-11T19:05:47.240Z","etag":null,"topics":["ai-safety","auraone","evals","evaluation","human-feedback","lerobot","llm","openx","rlds","robotics","rubrics","teleoperation"],"latest_commit_sha":null,"homepage":"https://auraone.ai/open","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/auraoneai.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-11T17:13:31.000Z","updated_at":"2026-05-11T19:04:51.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/auraoneai/open","commit_stats":null,"previous_names":["auraoneai/open"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/auraoneai/open","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/auraoneai%2Fopen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/auraoneai%2Fopen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/auraoneai%2Fopen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/auraoneai%2Fopen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/auraoneai","download_url":"https://codeload.github.com/auraoneai/open/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/auraoneai%2Fopen/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33603475,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-28T02:00:06.440Z","response_time":99,"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":["ai-safety","auraone","evals","evaluation","human-feedback","lerobot","llm","openx","rlds","robotics","rubrics","teleoperation"],"created_at":"2026-05-28T09:34:31.443Z","updated_at":"2026-05-28T09:34:33.830Z","avatar_url":"https://github.com/auraoneai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AuraOne Open\n\nOpen tools for the human-judgment layer of AI evaluation. Rubric authoring, scoring, judge calibration, reviewer agreement, drift detection, leakage audits, dataset documentation, and robotics review data — local, inspectable, and runnable without an AuraOne account.\n\nThe thesis behind this release: the best evals will stay private, but the standards for building trustworthy evals should not. Read it in full at [resources/writing/measuring-human-judgment-layer.md](resources/writing/measuring-human-judgment-layer.md).\n\n## What's in this repository\n\n| Component | What it is |\n| --- | --- |\n| [`packages/evalkit/`](packages/evalkit/) | `auraone-evalkit` Python package + `evalkit` CLI for rubric validation, scoring, judge calibration, reviewer agreement, drift, leakage audits, sampling, and versioning. |\n| [`robotics-reviewkit/`](robotics-reviewkit/) | Schemas, exporters, taxonomy, and a static viewer for teleop review and failure data. Includes LeRobot and RLDS/OpenX export bridges. |\n| [`resources/buying-toolkit/`](resources/buying-toolkit/) | Templates and checklists for teams buying human-data work: SOWs, RFPs, SLAs, vendor comparison, pilot design, reviewer certification, and program playbook. |\n| [`resources/writing/`](resources/writing/) | The thesis posts behind this release. |\n| [`docs/PRD/`](docs/PRD/) | The audit trail from source to v0.1.0. |\n\n## Quick start\n\n```bash\npip install auraone-evalkit\n\nevalkit validate-rubric path/to/rubric.jsonl\nevalkit lint-rubric path/to/rubric.jsonl\nevalkit score --rubric rubric.jsonl --responses outputs.jsonl --out scores.json\n```\n\nFull CLI reference: [`packages/evalkit/README.md`](packages/evalkit/README.md).\n\n## What this release is not\n\n- Not an expert-authored benchmark. The tutorial datasets included here are synthetic and exist to make the tooling runnable.\n- Not real robotics data. The example episodes in `robotics-reviewkit/examples/` are mock metadata.\n- Not a hosted AuraOne service. EvalKit runs locally with no API key, no tenant, no database.\n\nThese limits are intentional. The release ships the standards, not the dataset.\n\n## Related links\n\n- AuraOne Open landing page: https://auraone.ai/open\n- Resource hub: https://auraone.ai/resources\n- Hosted AuraOne: https://auraone.ai\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fauraoneai%2Fopen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fauraoneai%2Fopen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fauraoneai%2Fopen/lists"}