{"id":44739800,"url":"https://github.com/prosdevlab/doc-agent","last_synced_at":"2026-02-15T20:34:22.523Z","repository":{"id":330355210,"uuid":"1111432109","full_name":"prosdevlab/doc-agent","owner":"prosdevlab","description":"Document extraction and semantic search CLI with MCP integration. Extract structured data from invoices, receipts, and bank statements using Vision AI.","archived":false,"fork":false,"pushed_at":"2025-12-09T13:20:24.000Z","size":731,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-26T11:50:03.289Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/prosdevlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-12-06T23:21:17.000Z","updated_at":"2025-12-09T13:20:27.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/prosdevlab/doc-agent","commit_stats":null,"previous_names":["prosdevlab/doc-agent"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/prosdevlab/doc-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prosdevlab%2Fdoc-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prosdevlab%2Fdoc-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prosdevlab%2Fdoc-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prosdevlab%2Fdoc-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/prosdevlab","download_url":"https://codeload.github.com/prosdevlab/doc-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prosdevlab%2Fdoc-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29488627,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-15T19:29:10.908Z","status":"ssl_error","status_checked_at":"2026-02-15T19:29:10.419Z","response_time":118,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":[],"created_at":"2026-02-15T20:34:20.114Z","updated_at":"2026-02-15T20:34:22.513Z","avatar_url":"https://github.com/prosdevlab.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# doc-agent\n\nDocument extraction and semantic search CLI with MCP integration. Extract structured data from invoices, receipts, and bank statements using Vision AI.\n\n## Features\n\n- 🔍 **Document Extraction**: Extract structured data from PDFs and images using Vision AI\n- 🦙 **Ollama-First**: Privacy-first default using local `llama3.2-vision` model\n- 🔧 **Zero Setup**: Auto-installs Ollama via Homebrew if needed, auto-pulls models\n- 📄 **Multi-Format**: Supports PDFs and images (PNG, JPEG, WebP)\n- 🔬 **OCR-Enhanced**: Uses Tesseract.js for accurate text extraction from receipts\n- 💾 **Local Storage**: All data persists to local SQLite database\n- 🔎 **Semantic Search**: Natural language search over indexed documents (coming soon)\n- 🤖 **MCP Integration**: Use via Claude Desktop or any MCP-compatible assistant\n- 🔒 **Privacy-First**: Data stays on your machine (unless you opt for cloud AI)\n\n## Quick Start\n\n### Installation\n\n```bash\nnpm install -g doc-agent\n```\n\n### Usage\n\n**Extract document data (uses Ollama by default):**\n```bash\ndoc extract invoice.pdf\n```\n\n\u003e 💡 Don't have Ollama? No problem! The CLI will offer to install it for you via Homebrew.\n\n**With Gemini (cloud, higher accuracy):**\n```bash\nexport GEMINI_API_KEY=your_key_here\ndoc extract invoice.pdf --provider gemini\n```\n\n**Start MCP server:**\n```bash\ndoc mcp\n```\n\n### Claude Desktop Integration\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"doc-agent\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"doc-agent\", \"mcp\"],\n      \"env\": {\n        \"GEMINI_API_KEY\": \"your_key_here\"\n      }\n    }\n  }\n}\n```\n\nThen in Claude Desktop:\n\u003e \"Extract data from ~/Downloads/invoice.pdf\"\n\n## Development\n\n```bash\n# Clone and install dependencies\ngit clone https://github.com/prosdevlab/doc-agent\ncd doc-agent\npnpm install\n\n# Build the project\npnpm build\n\n# Run CLI locally\npnpm dev extract examples/invoice.pdf\n\n# Run tests\npnpm test\n\n# Start MCP server\npnpm mcp\n```\n\n### Architecture\n\nThe CLI is built with [Ink](https://github.com/vadimdemedes/ink) (React for CLIs) for rich interactive output:\n\n```\npackages/\n├── cli/           # Ink-based CLI with services, hooks, and components\n├── core/          # Shared types and interfaces\n├── extract/       # Document extraction (Gemini, Ollama) + OCR\n├── storage/       # SQLite persistence (Drizzle ORM)\n└── vector-store/  # Vector database for semantic search\n```\n\n## Roadmap\n\nSee [ROADMAP.md](./ROADMAP.md) for the project plan.\n\n## License\n\nMIT","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprosdevlab%2Fdoc-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprosdevlab%2Fdoc-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprosdevlab%2Fdoc-agent/lists"}