{"id":13574920,"url":"https://github.com/UKGovernmentBEIS/inspect_ai","last_synced_at":"2025-04-04T18:32:52.368Z","repository":{"id":235117882,"uuid":"718665019","full_name":"UKGovernmentBEIS/inspect_ai","owner":"UKGovernmentBEIS","description":"Inspect: A framework for large language model evaluations","archived":false,"fork":false,"pushed_at":"2025-03-31T17:56:06.000Z","size":96087,"stargazers_count":850,"open_issues_count":55,"forks_count":203,"subscribers_count":9,"default_branch":"main","last_synced_at":"2025-03-31T17:59:02.947Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://inspect.aisi.org.uk/","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/UKGovernmentBEIS.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-14T14:53:11.000Z","updated_at":"2025-03-31T17:23:53.000Z","dependencies_parsed_at":"2024-04-26T16:27:02.335Z","dependency_job_id":"17155dec-39ef-48c7-a2e0-8ed09e3d9786","html_url":"https://github.com/UKGovernmentBEIS/inspect_ai","commit_stats":null,"previous_names":["ukgovernmentbeis/inspect_ai"],"tags_count":60,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKGovernmentBEIS%2Finspect_ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKGovernmentBEIS%2Finspect_ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKGovernmentBEIS%2Finspect_ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKGovernmentBEIS%2Finspect_ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UKGovernmentBEIS","download_url":"https://codeload.github.com/UKGovernmentBEIS/inspect_ai/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247229941,"owners_count":20905159,"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","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":"2024-08-01T15:00:56.576Z","updated_at":"2025-04-04T18:32:47.360Z","avatar_url":"https://github.com/UKGovernmentBEIS.png","language":"Python","funding_links":[],"categories":["LLM-as-Judge Evaluation","How to run these benchmarks","Evaluation and Monitoring","Python","LLM and Agent Observability","Evals \u0026 Verification","Evaluation","5 · Evaluation infrastructure (the eval stack: datasets, scorers, online/offline, tracing, CI)","Tools","Tools and Code","Agent Harnessing and Evaluation","Best starting points","9. Evaluation, Benchmarks \u0026 Datasets","Testing \u0026 Red-Teaming","Benchmarks \u0026 Evaluations","GPT Security","Supporting Infrastructure","3）参考实现与开源工具（GitHub）"],"sub_categories":["Start with a unified harness","Adjacent Collections","5a · Eval frameworks \u0026 harnesses (code-first test-runners)","Evaluators and Test Harnesses","LLM Evaluation Tools","Benchmark Reality Check (real-world tool use)","AI-Assisted Offensive Security","Standard","Evaluation","评测框架与 Agent Benchmarks"],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FUKGovernmentBEIS%2Finspect_ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FUKGovernmentBEIS%2Finspect_ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FUKGovernmentBEIS%2Finspect_ai/lists"}