{"id":30108297,"url":"https://github.com/menezess42/vaultseer","last_synced_at":"2026-04-17T12:33:58.297Z","repository":{"id":308236630,"uuid":"1030422637","full_name":"Menezess42/vaultSeer","owner":"Menezess42","description":"VaultSeer is a local-first knowledge retrieval tool designed to help developers query and navigate their personal archives through semantic search and RAG pipelines","archived":false,"fork":false,"pushed_at":"2025-09-04T15:56:30.000Z","size":356,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-04T17:39:05.812Z","etag":null,"topics":["data-science","local","python3","rag","security"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Menezess42.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-08-01T16:00:00.000Z","updated_at":"2025-09-04T15:56:34.000Z","dependencies_parsed_at":"2025-09-04T17:24:51.221Z","dependency_job_id":"42d39a39-d727-4eb0-ac14-e5ae256baa14","html_url":"https://github.com/Menezess42/vaultSeer","commit_stats":null,"previous_names":["menezess42/vaultseer"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Menezess42/vaultSeer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Menezess42%2FvaultSeer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Menezess42%2FvaultSeer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Menezess42%2FvaultSeer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Menezess42%2FvaultSeer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Menezess42","download_url":"https://codeload.github.com/Menezess42/vaultSeer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Menezess42%2FvaultSeer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31929817,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T10:35:34.458Z","status":"ssl_error","status_checked_at":"2026-04-17T10:35:09.472Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["data-science","local","python3","rag","security"],"created_at":"2025-08-10T02:08:53.269Z","updated_at":"2026-04-17T12:33:58.292Z","avatar_url":"https://github.com/Menezess42.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ch1\u003eVaultSeer\u003c/h1\u003e\n\u003cimg width=\"300\" height=\"300\" alt=\"vaultSeer\" src=\"https://github.com/user-attachments/assets/05a26aad-0dc6-43dc-8b7e-b9b0f6c9944c\" /\u003e\n\u003chr/\u003e\n\u003c/div\u003e\n# VaultSeer\n\n**VaultSeer** is a local-first semantic search tool designed to navigate through a user's personal knowledge base — such as markdown notes and PDF documents — without relying on any online APIs or cloud services.\n\nThis tool is ideal for individuals who value privacy, control over their data, and the ability to search abstract or concrete information across curated directories.\n\n---\n\n## 🧠 Project Philosophy\n\nVaultSeer works as a librarian in a fortress: it does not provide final answers, but rather points to the most relevant documents from your knowledge vaults, helping reinforce understanding through active retrieval.\n\nInitially, VaultSeer will:\n\n- Index and monitor local directories (e.g., Obsidian vaults, curated PDF folders).\n- Use semantic similarity to return a list of documents most likely to contain relevant information.\n- Operate purely via terminal and entirely offline.\n- Rely on metadata such as file names, directory structures, and markdown headers.\n\n---\n\n## 📁 Project Structure (suggested)\n\n```text\nvaultseer/\n├── flake/                   # Nix flake files\n│   ├── flake.nix\n│   └── flake.lock\n├── .envrc                   # direnv environment loader\n├── README.md                # Project description and instructions\n├── vaultseer/               # Main Python package (to be developed)\n│   ├── __init__.py\n│   ├── aux_dataStructures/  # auxiliar data structures created to help walking the data\n│   ├── aux_Files/           # auxiliar files \n│   └── crawler/             # baseDirs Crawler and maestro goes here\n│   \n├── tests/                   # Unit and integration tests\n│   └── __init__.py\n├── data/                    # Temporary folder for ingested documents (git-ignored)\n├── notebooks/               # Prototypes, scratchpads, embeddings experiments\n├── requirements.txt         # Python dependencies for pip\n└── pyproject.toml           # Optional Python build metadata\n```\n---\n### ⚠️Note:\n- This is a proposed layout based on scalable software architecture principles and typical RAG-based workflows. It is subject to change as the project matures.\n---\n### ✅ Current Status\n- [X] Initial project skeleton established\n- [ ] Evaluate local embedding libraries (e.g., sentence-transformers, gtr, all-MiniLM)\n- [ ] Evaluate vector index options (e.g., faiss, annoy, chroma, hnswlib)\n- [ ] Implement document ingestion and metadata extraction\n- [ ] Implement semantic search prototype\n- [ ] Integrate with terminal CLI\n---\n### 📜 License\n- To be defined.\n---\n### 🛠️ Developed by\n- This project is maintained and built by [Menezess42](github.com/Menezess42).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmenezess42%2Fvaultseer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmenezess42%2Fvaultseer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmenezess42%2Fvaultseer/lists"}