{"id":28472135,"url":"https://github.com/filecoin-project/data-prep-tools","last_synced_at":"2025-07-02T00:31:18.785Z","repository":{"id":140830390,"uuid":"612326255","full_name":"filecoin-project/data-prep-tools","owner":"filecoin-project","description":null,"archived":false,"fork":false,"pushed_at":"2024-07-15T17:59:09.000Z","size":3740,"stargazers_count":18,"open_issues_count":7,"forks_count":4,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-06-07T11:11:22.846Z","etag":null,"topics":["filecoin","ipfs"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/filecoin-project.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-03-10T17:34:20.000Z","updated_at":"2025-06-03T07:47:20.000Z","dependencies_parsed_at":"2023-05-27T18:45:09.051Z","dependency_job_id":null,"html_url":"https://github.com/filecoin-project/data-prep-tools","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/filecoin-project/data-prep-tools","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filecoin-project%2Fdata-prep-tools","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filecoin-project%2Fdata-prep-tools/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filecoin-project%2Fdata-prep-tools/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filecoin-project%2Fdata-prep-tools/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/filecoin-project","download_url":"https://codeload.github.com/filecoin-project/data-prep-tools/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filecoin-project%2Fdata-prep-tools/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263055965,"owners_count":23406805,"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":["filecoin","ipfs"],"created_at":"2025-06-07T11:10:16.864Z","updated_at":"2025-07-02T00:31:18.774Z","avatar_url":"https://github.com/filecoin-project.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data preparation for Filecoin\n\nThis repository contains information about everything related to data preparation that is\nrequired before onboarding data to [Filecoin](https://filecoin.io). This includes tooling,\ndocumentation, and performance benchmarks.\n\nThe repository is split into 4 main sections:\n\n1. [Docs](./docs): this section includes documentation explaining how data onboarding to\nfilecoin works, best practices and common pitfalls. It also contains links to available\ntools in the ecosystem.\n2. [Modules](./modules): the different data onboarding steps are encoded as modules\n(written in python and bash) which could be easily imported and used in any data\nonboarding pipeline.\n3. [Orchestrators](./orchestrators): these are example scripts demonstrating how to import\nand use the modules from the [modules section](./modules) to orchestrate data onboarding.\n4. [Performance benchmarks](./performance): these include performance benchmarks for\ndifferent available tools.\n\n\n## Other tools in the ecosystem\n\n- [banyancomputer/dataprep](https://github.com/banyancomputer/dataprep) -- this tool handles encryption, compression, deduping and chunking. The output of this tool could then be carred etc and used for deal making.\n\n\n## Lead Maintainer\n\n[Anjor](https://github.com/anjor)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffilecoin-project%2Fdata-prep-tools","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffilecoin-project%2Fdata-prep-tools","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffilecoin-project%2Fdata-prep-tools/lists"}