{"id":46880334,"url":"https://github.com/rohitprasad-code/digital.me","last_synced_at":"2026-03-10T21:03:56.825Z","repository":{"id":336335400,"uuid":"1149195722","full_name":"rohitprasad-code/digital.me","owner":"rohitprasad-code","description":"An AI agent mirroring my life and work by syncing Strava, LinkedIn, and personal data into a conversational twin.","archived":false,"fork":false,"pushed_at":"2026-03-03T19:32:28.000Z","size":1155,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-03T23:20:52.784Z","etag":null,"topics":["digital-twin","nextjs","ollama","strava-api"],"latest_commit_sha":null,"homepage":"","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/rohitprasad-code.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2026-02-03T20:43:02.000Z","updated_at":"2026-03-03T19:32:31.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/rohitprasad-code/digital.me","commit_stats":null,"previous_names":["rohitprasad-code/digital.me"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rohitprasad-code/digital.me","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitprasad-code%2Fdigital.me","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitprasad-code%2Fdigital.me/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitprasad-code%2Fdigital.me/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitprasad-code%2Fdigital.me/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rohitprasad-code","download_url":"https://codeload.github.com/rohitprasad-code/digital.me/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitprasad-code%2Fdigital.me/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30355223,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T15:55:29.454Z","status":"ssl_error","status_checked_at":"2026-03-10T15:54:58.440Z","response_time":106,"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":["digital-twin","nextjs","ollama","strava-api"],"created_at":"2026-03-10T21:03:56.253Z","updated_at":"2026-03-10T21:03:56.804Z","avatar_url":"https://github.com/rohitprasad-code.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Digital Me\n\nDigital Me is an AI-powered personal digital twin. It's designed to ingest your personal data (resume, GitHub activity, etc.) and use a local LLM (via Ollama) to answer questions as if it were you.\n\n## Features\n\n| Category                      | Details                                                                                                          |\n| ----------------------------- | ---------------------------------------------------------------------------------------------------------------- |\n| **RAG Pipeline**              | Retrieval-Augmented Generation grounded in your personal data for accurate, contextual answers                   |\n| **Smart Memory Router**       | Keyword \u0026 LLM-based query classification across Static, Dynamic, and Conversational memory types                 |\n| **Structure-Aware Ingestion** | Two-stage document pipeline — parses PDFs \u0026 text into structured sections, then chunks with configurable overlap |\n| **Multi-Source Data**         | Resume (PDF), `me.json` identity config, GitHub (profile + repos + commits), Strava (activities)                 |\n| **CLI Interface**             | `chat` and `ingest` commands powered by [Commander](https://github.com/tj/commander.js)                          |\n| **Next.js API**               | RESTful chat endpoint with full RAG orchestration                                                                |\n| **100% Local**                | Powered by Ollama (Llama 3) — your data never leaves your machine                                                |\n\n## 🏗️ Architecture\n\n```\n┌──────────────┐     ┌──────────────┐     ┌──────────────────┐\n│   CLI Chat   │────▶│  Next.js API │────▶│   Ollama (LLM)   │\n└──────────────┘     └─────┬────────┘     └──────────────────┘\n                           │                       ▲\n                           ▼                       │\n                    ┌──────────────┐         ┌─────┴───────┐\n                    │ Memory Router│────────▶│ Vector Store│\n                    └──────┬───────┘         └─────┬───────┘\n                           │                       ▲\n              ┌────────────┼────────────┐          │\n              ▼            ▼            ▼          │\n        ┌──────────┐ ┌──────────┐ ┌──────────┐     │\n        │  Static  │ │ Dynamic  │ │ Conversa-│     │\n        │  Memory  │ │  Memory  │ │  tional  │     │\n        └──────────┘ └──────────┘ └──────────┘     │\n              │            │                       │\n              ▼            ▼                       │\n        ┌──────────┐ ┌──────────┐                  │\n        │Resume/PDF│ │ GitHub   │                  │\n        │ me.json  │ │ Strava   │──────────────────┘\n        └──────────┘ └──────────┘\n```\n\n## 📁 Project Structure\n\n```\ndigital-me/\n├── app/\n│   └── api/              # Next.js API route — chat endpoint + RAG logic\n├── cli/\n│   ├── index.ts          # CLI entrypoint (Commander)\n│   └── chat.ts           # Interactive chat session\n├── integrations/\n│   ├── github/           # GitHub profile, repos \u0026 commit ingestion\n│   └── strava/           # Strava activity ingestion\n├── memory/\n│   ├── ingest.ts         # Orchestrates full ingestion pipeline\n│   ├── router.ts         # MemoryRouter — routes queries by type\n│   ├── vector_store/     # Embedding storage \u0026 cosine similarity search\n│   └── data_processing/  # Document parsing, structure analysis \u0026 chunking\n│       └── parsers/      # Parsers for PDF, Markdown, JSON and all\n├── model/\n│   ├── llm/              # Ollama client configuration\n│   └── prompts/          # System prompts \u0026 prompt templates\n├── public/               # Raw static data sources\n│   ├── codes/            # Structured config (e.g., me.json)\n│   └── documents/        # PDFs, Markdown, Text (e.g., resume.pdf)\n└── scripts/\n    └── dev-cli.js        # Dev helper for CLI execution\n```\n\n## 📋 Prerequisites\n\n- **Node.js** v18+\n- **Ollama** installed and running — pull a model:\n  ```bash\n  ollama pull llama3\n  ```\n- **GitHub Token** — [Personal Access Token](https://github.com/settings/tokens) with `repo` and `read:user` scopes\n- **Strava Token** — API token with `read`, `activity:read`, `activity:write`, `activity:read_all` scopes\n\n## 🚀 Getting Started\n\n### 1. Clone \u0026 Install\n\n```bash\ngit clone https://github.com/yourusername/digital-me.git\ncd digital-me\nnpm install\n```\n\n### 2. Configure Environment\n\nCreate a `.env.local` file in the project root:\n\n```env\n# GitHub integration\nGITHUB_TOKEN=your_github_token\nGITHUB_USERNAME=your_github_username\n\n# Strava integration\nSTRAVA_ACCESS_TOKEN=your_strava_token\n\n# Optional: Override API URL\n# e.g.:\n# DIGITAL_ME_API_URL=http://localhost:7001/api\n```\n\n### 3. Prepare Your Data\n\n| File                       | Purpose                                               |\n| -------------------------- | ----------------------------------------------------- |\n| `memory/static/resume.pdf` | Your resume (parsed via LLM into structured sections) |\n\n### 4. Run\n\n```bash\n# Terminal 1 — Start the API server\nnpm run dev\n\n# Terminal 2 — Ingest your data into the vector store\nnpm run cli ingest\n\n# Terminal 3 — Run the scheduler\nnpm run scheduler\n\n# Terminal 4 — Start chatting with your digital twin\nnpm run cli chat\n```\n\n## 🧰 Available Scripts\n\n| Script               | Description                                   |\n| -------------------- | --------------------------------------------- |\n| `npm run dev`        | Start the Next.js dev server                  |\n| `npm run build`      | Production build                              |\n| `npm run start`      | Start production server                       |\n| `npm run cli ingest` | Ingest all data sources into the vector store |\n| `npm run cli sync`   | Sync latest changes into vector store         |\n| `npm run cli chat`   | Launch the interactive chat CLI               |\n| `npm run test`       | Run tests with Vitest                         |\n| `npm run lint`       | Lint with ESLint                              |\n| `npm run scheduler`  | Run the scheduler                             |\n\n## 🔮 Roadmap\n\n- [ ] **More Integrations** — LinkedIn, Instagram, Google Fit\n- [ ] **Dynamic Modes** — Intent-based persona switching (Recruiter vs. Friend mode)\n- [ ] **Rich Responses** — Serve visual UI components (GitHub stats, heatmaps, activity charts)\n- [ ] **Hardware Integration** — ESP32 sensors for live status, room presence \u0026 ambient interaction\n- [ ] **Voice Interface** — Conversational voice input/output\n- [ ] **On-Device Inference** — Run smaller models directly on edge hardware\n- [ ] **Agent Scheduling** — Automated periodic data refresh \u0026 proactive notifications\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frohitprasad-code%2Fdigital.me","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frohitprasad-code%2Fdigital.me","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frohitprasad-code%2Fdigital.me/lists"}