{"data":{"slug":"verifywise-ai-verifywise","name":"verifywise","tagline":"Complete AI governance and LLM Evals platform","github_url":"https://github.com/verifywise-ai/verifywise","owner":"verifywise-ai","repo":"verifywise","owner_avatar_url":"https://avatars.githubusercontent.com/u/262239808?v=4","primary_language":"TypeScript","stars":322,"forks":110,"topics":["ai","ai-auditing","ai-compliance","ai-governance","ai-governance-model","ai-risk","audit","auditing","compliance","eu-ai-act","governance","grc","iso27001","iso42001","llm-eval","llm-evaluation","nist-ai-rmf","risk-management"],"archived":false,"github_pushed_at":"2026-07-28T09:05:06+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/verifywise-ai-verifywise","markdown_url":"https://www.graphcanon.com/tools/verifywise-ai-verifywise.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/verifywise-ai-verifywise","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=verifywise-ai-verifywise","description":"Complete AI governance and LLM Evals platform with support for EU AI Act, ISO 42001, NIST AI RMF and 20+ more AI frameworks and regulations. Join our Discord channel: https://discord.com/invite/d3k3E4uEpR","homepage_url":"https://verifywise.ai","license":"Other","open_issues":104,"watchers":3,"ai_summary":"Provides support for EU AI Act, ISO 42001, NIST AI RMF, and over 20 other AI frameworks and regulations.","readme_excerpt":"## Installation\n\nThe VerifyWise application has two components: a frontend built with React.js and a backend built with Node.js. At present, you can use `npm` (for development) or Docker/Kubernetes (production) to run VerifyWise. A PostgreSQL database is required.\n\n---\n\n### Installation using npm (for development)\n\nPrerequisites:\n\n- npm and Docker\n- Python 3.12+ (for EvalServer)\n- A running PostgreSQL, preferably as a Docker image (eg. using `docker pull postgres:latest`)\n- Available ports: 5173 (frontend), 3000 (backend), 5432 (database), 6379 (Redis), 8000 (EvalServer)\n\n#### Step 1: Clone, install dependencies, and set up databases\n\nFirst, clone the repository to your local machine and go to verifywise directory. Then, navigate to the Clients directory and install the dependencies:\n\n```\ngit clone https://github.com/bluewave-labs/verifywise.git\ncd verifywise\ncd Clients\nnpm install\ncd ../Servers\nnpm install\n```\n\nGo to the root directory and copy the contents of .env.dev to the .env file. For security, you must set a strong and unpredictable JWT_SECRET in your .env file. This secret is used to sign and verify your JWT tokens, so it must be kept private and cryptographically secure. You can generate a 256-bit base64-encoded secret using `openssl rand -base64 32`.\n\n```\ncd ..\ncp .env.dev Servers/.env\n```\n\nIn `.env` file, change FRONTEND_URL and set your super admin credentials:\n\n```\nFRONTEND_URL=http://localhost:5173\nSUPERADMIN_EMAIL=admin@verifywise.com\nSUPERADMIN_PASSWORD=ChangeMe!Str0ng\n```\n\n**Important:** Change `SUPERADMIN_PASSWORD` to a strong password (minimum 8 characters). These credentials are used to create the initial super admin account on first setup.\n\nNote: CORS is automatically configured to allow requests from the same host (localhost, 127.0.0.1) where the backend is running.\n\nRun the PostgreSQL container with the following command:\n\n```\ndocker run -d --name mypostgres -p 5432:5432 -e POSTGRES_PASSWORD={env variable password} postgres\n```\n\nRun redis with following command:\n\n```\ndocker run -d --name myredis -p 6379:6379 redis\n```\n\nAccess the PostgreSQL container and create the verifywise database:\n\n```\ndocker exec -it mypostgres psql -U postgres\nCREATE DATABASE verifywise;\n```\n\n#### Step 2: Set up EvalServer (for LLM evaluations)\n\nEvalServer is a Python-based service that handles LLM evaluations. If you want to use the evaluation features, follow these steps:\n\n```\ncd EvalServer\npython3.12 -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\n```\n\nSet up the environment file. You can copy the minimal `.env.example` file in the EvalServer directory:\n\n```\ncp .env.example .env\n```\n\n#### Step 3: Start the application\n\nNavigate to the EvalServer/src directory, activate the virtual environment (if not already activated), and start the server:\n\n```\ncd EvalServer/src\nsource ../venv/bin/activate\npython app.py\n```\n\nNavigate to the Servers directory and start the server in watch mode:\n\n```\ncd Servers\nnpm run watch\n```\n\nNavigate to the Clients directory and start the client in development mode:\n\n```\ncd Clients\nnpm run dev\n```\n\n**Note:** Make sure to replace {env variable password} with the actual password from your environment variables.\n\n**Note:** On a fresh setup, a super admin account is created automatically using the `SUPERADMIN_EMAIL` and `SUPERADMIN_PASSWORD` environment variables. Log in with these credentials, then create an organization and invite users to get started. The login page will display a banner guiding you through this process.\n\n---\n\n### Installation using Docker (production)\n\nFirst, ensure you have the following installed:\n\n- npm\n- Docker\n- Docker Compose\n\nCreate a directory in your desired folder:\n\n```\nmkdir verifywise\ncd verifywise\n```\n\nDownload the required files using wget:\n\n```\ncurl -O https://raw.githubusercontent.com/bluewave-labs/verifywise/develop/install.sh\ncurl -O https://raw.githubusercontent.com/bluewave-labs/verifywise/develop/.env.prod\n```\n\nMake sure to change the JWT_SECRET","github_created_at":"2024-08-18T23:02:10+00:00","created_at":"2026-07-11T12:00:29.097399+00:00","updated_at":"2026-07-28T18:00:45.357356+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"}],"tags":[{"slug":"ai-auditing","name":"ai-auditing"},{"slug":"ai-compliance","name":"ai-compliance"},{"slug":"llm-eval","name":"llm-eval"}],"trust":{"provenance":{"is_fork":false,"github_id":844279282,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-28T18:00:44.235Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":0,"last_release_at":"2026-07-15T19:25:18Z"},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":1,"high_count":0,"last_scan_at":"2026-07-11T12:00:36.394Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-07-28T18:00:44.754Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-07-28T18:00:44.754Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-07-28T18:00:44.754Z","managed_saas":false},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-07-28T18:00:44.754Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-07-28T18:00:44.754Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-07-28T18:00:44.754Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"unknown","summary":"Pricing information is not found in the repository data."},"requirements":{"notes":["Requires setup of PostgreSQL and Redis databases via Docker.","Uses TypeScript for the backend, so a compatible runtime environment such as Node.js is required."],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"pricing_model":"unknown","requires_docker":true},"when_to_use":["When you need to comply with the EU AI Act or other global regulations such as ISO 42001 and NIST AI RMF, VerifyWise offers direct support for these frameworks.","If your use case involves complex risk management in AI applications, VerifyWise's advanced auditing and compliance features can help maintain regulatory adherence."],"when_not_to_use":["Avoid using VerifyWise if you are specifically looking for a framework agnostic evaluation tool that does not provide integration with specific AI governance regulations.","Do not use VerifyWise when the installation complexity is a barrier, as it involves multiple setup steps including configuring a PostgreSQL database and managing cross-platform dependencies."],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:09:37.005Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"unknown","requires_docker":true},"decision_summary":[{"label":"Pricing","value":"unknown - Pricing information is not found in the repository data."},{"label":"Requirements","value":"Requires Docker; Requires setup of PostgreSQL and Redis databases via Docker.; Uses TypeScript for the backend, so a compatible runtime environment such as Node.js is required."},{"label":"Adopt for","value":"VerifyWise is a comprehensive AI governance and evaluation platform that supports multiple regulatory frameworks like the EU AI Act, ISO 42001, NIST AI RMF, among others."},{"label":"License detail","value":"The license terms are specified as 'Other', indicating custom licensing that may need to be reviewed for specific restrictions or permissions."}]}}