{"data":{"slug":"p-e-w-heretic","name":"heretic","tagline":"Fully automatic censorship removal for language models","github_url":"https://github.com/p-e-w/heretic","owner":"p-e-w","repo":"heretic","owner_avatar_url":"https://avatars.githubusercontent.com/u/2702526?v=4","primary_language":"Python","stars":27709,"forks":2997,"topics":["abliteration","llm","transformer"],"archived":false,"github_pushed_at":"2026-08-14T11:09:07+00:00","maintenance_label":"Very active","stars_delta_30d":1309,"url":"https://www.graphcanon.com/tools/p-e-w-heretic","markdown_url":"https://www.graphcanon.com/tools/p-e-w-heretic.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/p-e-w-heretic","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=p-e-w-heretic","description":"Fully automatic censorship removal for language models","homepage_url":"https://heretic-project.org","license":"AGPL-3.0","open_issues":74,"watchers":125,"ai_summary":"A tool designed for removing censorship from language models automatically.","readme_excerpt":"## License\n\nCopyright &copy; 2025-2026  Philipp Emanuel Weidmann (<pew@worldwidemann.com>) + contributors\n\nThis program is free software: you can redistribute it and/or modify\nit under the terms of the GNU Affero General Public License as published by\nthe Free Software Foundation, either version 3 of the License, or\n(at your option) any later version.\n\nThis program is distributed in the hope that it will be useful,\nbut WITHOUT ANY WARRANTY; without even the implied warranty of\nMERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the\nGNU Affero General Public License for more details.\n\nYou should have received a copy of the GNU Affero General Public License\nalong with this program.  If not, see <https://www.gnu.org/licenses/>.\n\n**By contributing to this project, you agree to release your\ncontributions under the same license.**","github_created_at":"2025-09-21T05:46:16+00:00","created_at":"2026-07-07T17:32:38.911601+00:00","updated_at":"2026-08-16T18:02:03.8899+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"abliteration","name":"abliteration"},{"slug":"llm","name":"llm"},{"slug":"transformer","name":"transformer"}],"trust":{"provenance":{"is_fork":false,"github_id":1061041576,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T18:02:03.130Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":2,"last_release_at":"2026-06-14T12:55:57Z","stars_delta_30d":1309,"open_issues_delta_30d":2},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:59:20.586Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-16T18:02:03.579Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-16T18:02:03.579Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-16T18:02:03.579Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-08-16T18:02:03.579Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use Heretic if your work involves uncovering full capabilities of censored or restricted language models. Heretic excels in tasks requiring the removal of such restrictions.","Consider using Heretic when you have access to models with built-in content filtering that limits their output and you need unrestricted generation for research or developmental purposes."],"when_not_to_use":["Avoid Heretic if operating within jurisdictions where removing censorship from language models is illegal or against organizational policies. This could result in regulatory violations.","If your project does not benefit from uncensored content produced by language models (e.g., compliance-driven applications that require filtering mechanisms), using Heretic might be unnecessary."],"source":"enrich:decision_facts","observed_at":"2026-07-11T13:37:10.233Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Heretic is a Python-based tool that removes censorship from language models automatically."}]}}