Resume & Thread: Local-First AI Resume Tailoring with Mastra & Google Gemma 2

说明与用途

Resume & Thread 是一个本地优先的简历定制工具，使用 Google Gemma 和 Mastra，快速且安全地定制简历，将 ATS 匹配率从 54% 提升至 96%。

问题

Commercial resume optimization tools charge $20–$40/month and require uploading personal data to cloud servers, exposing privacy risks and producing generic keyword‑based resumes.

结果

Tailoring speed increased from 3–5 minutes to one click; ATS match score rose from 54% to 96% (+42%); all processing remains local with zero cloud leakage.

工作流

• 1. User opens job board in Chrome
• 2. Extension scrapes job requirements
• 3. Popup sends job spec to local server (127.0.0.1:4141)
• 4. Server validates schema with Zod
• 5. Mastra DAG normalizes job spec
• 6. DAG analyzes skill delta
• 7. DAG adapts resume using Google Gemma 2 if Ollama available, otherwise AST fallback
• 8. DAG calculates ATS score
• 9. DAG synthesizes artifacts (PDF, Markdown)
• 10. User downloads tailored resume

证据

Commercial resume optimization tools charge job seekers $20 to $40 every month for superficial keyword matching.

来源

The system runs entirely on the user's local hardware (127.0.0.1:4141).

来源

Increasing ATS match compatibility from 54% to 96% (+42% boost).

来源

Runs on local CPU/GPU threads, zero remote network latency (sub‑5ms).

来源