{"id":39688246,"url":"https://github.com/cleanlab/tlm","last_synced_at":"2026-02-23T06:07:59.178Z","repository":{"id":332855818,"uuid":"1118511992","full_name":"cleanlab/tlm","owner":"cleanlab","description":"Score the trustworthiness of outputs from any LLM in real-time","archived":false,"fork":false,"pushed_at":"2026-01-15T21:04:20.000Z","size":4934,"stargazers_count":1,"open_issues_count":19,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-15T23:50:42.512Z","etag":null,"topics":["ai-agents","ai-safety","confidence-estimation","data-extraction","data-labeling","error-detection","evals","evaluation","guardrails","hallucination","hallucination-detection","human-in-the-loop-ai","llm","llm-as-a-judge","llm-evaluation","rag","structured-outputs","trustworthy-ai","uncertainty-quantification","verifiers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cleanlab.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":null,"codeowners":null,"security":null,"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":"2025-12-17T21:42:29.000Z","updated_at":"2026-01-15T21:04:27.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/cleanlab/tlm","commit_stats":null,"previous_names":["cleanlab/tlm"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/cleanlab/tlm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cleanlab%2Ftlm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cleanlab%2Ftlm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cleanlab%2Ftlm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cleanlab%2Ftlm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cleanlab","download_url":"https://codeload.github.com/cleanlab/tlm/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cleanlab%2Ftlm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28534205,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-18T00:39:45.795Z","status":"online","status_checked_at":"2026-01-18T02:00:07.578Z","response_time":98,"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-agents","ai-safety","confidence-estimation","data-extraction","data-labeling","error-detection","evals","evaluation","guardrails","hallucination","hallucination-detection","human-in-the-loop-ai","llm","llm-as-a-judge","llm-evaluation","rag","structured-outputs","trustworthy-ai","uncertainty-quantification","verifiers"],"created_at":"2026-01-18T10:03:08.485Z","updated_at":"2026-01-18T10:03:08.560Z","avatar_url":"https://github.com/cleanlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Trustworthy Language Model (TLM)\n\nThe [Trustworthy Language Model](https://cleanlab.ai/blog/trustworthy-language-model/) scores the **trustworthiness** of outputs from *any* LLM in *real-time*.\n\nAutomatically detect hallucinated/incorrect responses in: Q\u0026A (RAG), Chatbots, Agents, Structured Outputs, Data Extraction, Tool Calling, Classification/Tagging, Data Labeling, and other LLM applications.\n\nUse TLM to:\n- Guardrail AI mistakes before they are served to user\n- Escalate cases where AI is untrustworthy to humans\n- Discover incorrect LLM (or human) generated outputs in datasets/logs\n- Boost AI accuracy\n\nPowered by *uncertainty estimation* techniques, TLM **works out of the box**, and does **not** require: \u003cbr\u003e\ndata preparation/labeling work or custom model training/serving infrastructure.\n\nLearn more and see precision/recall benchmarks with frontier models (from OpenAI, Anthropic, Google, etc): \u003cbr\u003e\n[Blog](https://cleanlab.ai/blog/), [Research Paper](https://aclanthology.org/2024.acl-long.283/)\n\n## Usage\n\nSee [notebooks](notebooks) for Jupyter notebooks with example usage.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcleanlab%2Ftlm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcleanlab%2Ftlm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcleanlab%2Ftlm/lists"}