resume-studio

KO | EN

gitlite — search

#web #open-source #chatgpt #sql #gemini #postgresql #github #machine-learning #svg #editor

(★ 9)

AI-native resume workspace — chat with an agent that edits your resume, design layouts with live preview, and practice mock interviews.

File Explorer

ZIP Download

- - resume.yaml
- - d-resume-hero.svg
  - logo.svg
- - architecture.md
  - setup.md
- - ai-tailor.md
  - dashboard.md
  - mock-interview.md
  - resume-builder.md
  - settings.md
- index.md
- README.md
- example-resume.json
- README.md
- - api.ts
  - App.tsx
  - index.css
  - llm-settings.ts
  - main.tsx
  - preferences.ts
  - types.ts
  - vite-env.d.ts
- .env.production
- index.html
- package-lock.json
- package.json
- postcss.config.cjs
- tsconfig.json
- tsconfig.node.json
- tsconfig.node.tsbuildinfo
- tsconfig.tsbuildinfo
- vercel.json
- vite.config.d.ts
- vite.config.js
- vite.config.ts
- - pre-push
- add_jds.py
- extend_jds.py
- seed_jds.py
- - __init__.py
  - routes_resources.py
  - routes_v3.py
- - default.json
- - build_llm.py
- - __init__.py
  - context.py
  - logging.py
- __init__.py
- config.py
- errors.py
- main.py
- - resume.tex.jinja2
  - section.tex.jinja2
- - README.md
- - __init__.py
  - conftest.py
  - test_agent_loop.py
  - test_api.py
  - test_edit_field_integration.py
  - test_latex_api.py
  - test_resources_import_recent.py
  - test_sse_scenarios.py
  - test_v3_routes.py
- - __init__.py
  - conftest.py
  - helpers.py
  - test_edit_field_llm.py
  - test_interview_llm.py
  - test_latex_llm.py
  - test_memory_llm.py
  - test_parse_llm.py
  - test_refine_llm.py
  - test_tailor_llm.py
- - __init__.py
  - conftest.py
  - test_edit_field.py
  - test_intent_resolver.py
  - test_interview.py
  - test_jd_tools.py
  - test_latex_render.py
  - test_llm_settings.py
  - test_self_check.py
  - test_suggestion_ops.py
  - test_transient_personal_storage.py
  - test_turn_runner.py
- __init__.py
- conftest.py
- README.md
.dockerignore
.env.example
.gitignore
CONTRIBUTING.md
docker-compose.yml
Dockerfile
LICENSE
package-lock.json
package.json
pyproject.toml
pytest.ini
README.md
README.zh-CN.md
requirements.txt
start-backend.bat

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Version

File

Link

Example

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1 align="center">
 <svg width="40" height="40" viewBox="0 0 48 48" fill="none" xmlns="http://www.w3.org/2000/svg" style="vertical-align: middle; margin-right: 8px;">
 <rect x="0" y="0" width="48" height="48" rx="11" fill="#0071e3"/>
 <g transform="translate(11,6)" stroke="white" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round" fill="none">
 <path d="M3 3h14l6 6v22a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2z"/>
 <path d="M17 3v6h6"/>
 <path d="M7 17h12"/>
 <path d="M7 22h10"/>
 <path d="M7 27h8"/>
 </g>
 </svg>
 Resume Studio
</h1>
 
 Build, tailor, review, and rehearse your resume with an AI-native workspace.
 
 
 Conversational Editing • Visual Layouts • JD-Aware Optimization • Mock Interviews

<a href="#why-resume-studio">Why</a>
 •
 <a href="#preview">Preview</a>
 •
 <a href="#product-tour">Product Tour</a>
 •
 <a href="#quick-start">Quick Start</a>
 •
 <a href="#architecture">Architecture</a>
 •
 <a href="./README.zh-CN.md">中文</a>

---

## Why Resume Studio?

Resume Studio is a full-stack AI workspace for the messy, iterative reality of job applications. Instead of treating resume writing as a one-shot document generation task, it gives users a place to refine content, tune layout, align with a target job description, and practice the interview that follows.

Most resume tools stop at templates. Resume Studio focuses on the whole loop:

<table>
 <tr>
 <td width="25%" align="center">Import Bring in resume data and job context.</td>
 <td width="25%" align="center">Improve Use an agent to rewrite, clarify, and restructure.</td>
 <td width="25%" align="center">Design Tune the layout with visual controls and reusable templates.</td>
 <td width="25%" align="center">Rehearse Run mock interviews grounded in the resume and target JD.</td>
 </tr>
</table>

It is designed as a practical product prototype and as an agent engineering playground: the backend exposes observable tool calls, regression evaluations, self-checking, and deterministic test coverage so changes can be measured instead of guessed.

## Preview

<details open>
<summary>AI Tailor — Chat-Driven Editing</summary>
 
<img src="./docs/assets/screenshots/ai_tailor_1.png" width="92%" />
<img src="./docs/assets/screenshots/ai_tailor_2.png" width="92%" />
</details>

<details>
<summary>Layout Builder — Visual Design</summary>
 
<img src="./docs/assets/screenshots/layout_builder_1.png" width="92%" />
<img src="./docs/assets/screenshots/layout_builder_2.png" width="92%" />
</details>

<details>
<summary>LaTeX Export</summary>
 
<img src="./docs/assets/screenshots/overleaf_export.png" width="92%" />
</details>

<details>
<summary>Mock Interview — Setup & Coding</summary>
 
<img src="./docs/assets/screenshots/interview_setup.png" width="92%" />
<img src="./docs/assets/screenshots/code_problem_1.png" width="92%" />
</details>

<details>
<summary>Interview Report</summary>
 
<img src="./docs/assets/screenshots/finish_interview_1.png" width="92%" />
</details>

## Product Tour

### Chat-Driven Resume Editing
Ask for targeted edits like "make my summary more backend-focused" or "rewrite the first bullet with stronger metrics." The agent reads the current resume, chooses tools, applies field-level edits, and streams its progress to the UI.
* Function-calling agent loop
* Resume-aware context assembly
* Field-level updates with structured paths
* Confirmation flow for sensitive factual changes

### Visual Layout Builder
Design the resume as a real document, not just a blob of text. Adjust sections, template guidance, spacing, typography, two-column layouts, tags, headers, and printable HTML output.
* Single-column and two-column resume layouts
* Section order and visibility controls
* Template-level guidance and local presets
* HTML export path for reliable browser printing

### JD-Aware Resume Targeting
Attach a target job description and let the assistant reason against it. The system can inject JD context into the agent loop and use retrieval-oriented guidance to identify alignment opportunities.
* Target JD context injection
* RAG-ready local artifacts
* Role-specific rewrite guidance
* Clear separation between resume data and layout templates

### Mock Interview Workspace
Practice with interviewers from different domains. The flow supports interviewer recommendations, resume/JD-grounded questions, interview termination detection, and a dedicated review mode after the session ends.
* Multi-industry interviewer presets
* Resume-aware and JD-aware prompts
* Custom user preference prompt
* Post-interview review mode

## Highlights

| Area | What makes it useful |
| --- | --- |
| **Agent UX** | Tool calls are streamed over SSE, so the UI can show what the assistant is doing instead of waiting on a silent black box. |
| **Resume Edits** | Edits are applied to structured resume fields, which keeps content changes inspectable and easier to test. |
| **Layout Design**| Template state is separated from resume content, so changing a layout does not silently mutate the resume itself. |
| **Export** | Printable HTML is the default export path. TeX is generated as source for users who want to compile in Overleaf or a local XeLaTeX environment. |
| **Evaluation** | Agent behavior has regression scenarios, fixture-based tests, and reporting scripts for iterative improvement. |
| **Local-first privacy** | Resumes, imports, job descriptions, and chat history persist in the browser. The server keeps active AI sessions in memory and reads only bundled sample data. |

> **Privacy note:** AI features must send the current resume/JD content to the configured backend and LLM provider for processing. The application does not persist that personal content on the server by default, but it is transiently processed there. Clearing browser site data removes the locally saved workspace.

## Quick Start

### Environment Setup

Detailed install guides for Python and Node.js on all platforms: [Development Setup → Environment Setup](./docs/development/setup.md#environment-setup--%E7%8E%AF%E5%A2%83%E5%AE%89%E8%A3%85)

**TL;DR:**

| Platform | Python | Node.js |
|----------|--------|---------|
| macOS | `brew install python@3.13` | `brew install node@22` |
| Windows | [python.org](https://www.python.org/downloads/) (check "Add to PATH") | [nodejs.org](https://nodejs.org/) (LTS) |
| Ubuntu | `sudo apt install python3 python3-pip python3-venv` | `curl -fsSL https://deb.nodesource.com/setup_22.x \| sudo -E bash - && sudo apt install -y nodejs` |

Minimal versions: **Python ≥ 3.11**, **Node.js ≥ 18**. Verify with `python --version` and `node --version`.

### Install

```bash
git clone https://github.com/MengPaul07/resume-studio
cd resume-studio

python -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install -r requirements.txt

# Frontend
cd frontend
npm install
cd ..

# Config
cp .env.example .env        # Windows: copy .env.example .env
# Edit .env and add your LLM_API_KEY
```

### Run Everything

```bash
npm run dev
```

| Service | URL |
| --- | --- |
| Frontend | `http://127.0.0.1:5173` |
| Backend API | `http://127.0.0.1:8000` |
| API Docs | `http://127.0.0.1:8000/docs` |

### Run Services Separately

```bash
npm run dev:backend
npm run dev:frontend
```

## Agent System

Resume Studio uses a function-calling agent loop rather than a single prompt that returns prose. This makes editing behavior observable and testable.

| Component | Role |
| --- | --- |
| Agent loop | LLM picks tools autonomously (`read_resume`, `add_entry`, `update_field`, `compose`, etc.) — up to 6 rounds per turn |
| Tool registry | All tools registered via `@tool` decorator; LLM selects based on JSON schema |
| Self-check | Code-based verdict on output quality — no extra LLM call needed |
| SSE streaming | Every tool call, reasoning step, and final result streamed to frontend in real time |
| Turn logging | Personal-content traces are disabled by default and can be enabled explicitly for local debugging. |

### Key Files

| Path | Role |
| --- | --- |
| `src/services/content_refinement_v3/agent/_agent_loop.py` | Agent loop — LLM tool selection + execution |
| `src/services/content_refinement_v3/agent/turn_runner.py` | Turn orchestration, SSE output, log saving |
| `src/services/content_refinement_v3/agent/_tools.py` | Tool definitions (`add_entry`, `update_field`, `set_entry`, `delete_entry`, etc.) |
| `src/services/content_refinement_v3/prompts/agent.py` | Agent and self-check prompts |
| `src/services/layout_design/` | Resume layout rendering, pagination, and HTML/TeX generation |
| `frontend/src/` | React app, chat UI, layout builder, and mock interview UI |

## Layout Builder

The layout system is built around reusable guidance and section configuration rather than hard-coded one-off templates.

| Capability | Description |
| --- | --- |
| Section control | Reorder and hide resume sections without changing the underlying resume content. |
| Template guidance | Store layout and style preferences as template-level state. |
| HTML rendering | Generate A4-style printable HTML for browser-native export. |
| TeX source | Generate TeX for users who prefer Overleaf or local XeLaTeX compilation. |
| Style tuning | Adjust variables such as page padding, column width, spacing, heading style, tag style, and font sizing. |

## Mock Interview

The mock interview flow is built for targeted practice rather than generic question lists.

| Stage | What happens |
| --- | --- |
| **Setup** | The user selects interview length, interviewer style, industry tags, target JD, resume, and optional custom preferences. |
| **Interview** | The interviewer starts with the first message, asks resume/JD-grounded questions, and adapts across rounds. |
| **Termination** | The system can detect when an interview has ended instead of forcing a fixed flow. |
| **Review** | A dedicated review prompt can analyze the session and give focused feedback. |

## Tech Stack

| Layer | Technologies |
| --- | --- |
| **Backend** | FastAPI, Pydantic, LiteLLM, SSE, SQLite-backed local stores |
| **Frontend** | React 18, Vite, TypeScript, Tailwind CSS, Framer Motion, i18next |
| **Retrieval** | FAISS, fastembed, local JD/context artifacts |
| **Documents** | HTML export, TeX source export, Jinja2, MarkItDown |
| **Quality** | pytest, frontend build checks, agent eval scripts |

## Project Structure

```text
resume-studio/
  ├── src/                         # FastAPI backend (API routes & services)
  │   ├── api/                     # Controller endpoints
  │   ├── services/
  │   │   ├── content_refinement_v3/ # Agent loop, prompts, resume editing
  │   │   └── layout_design/         # HTML/TeX layout rendering
  ├── frontend/                    # React + Vite frontend
  │   └── src/                     # UI components, pages, hooks, forms
  ├── config/                      # Document types & runtime config
  ├── scripts/                     # Evaluation & maintenance scripts
  ├── tests/                       # Backend test suite
  └── docs/                        # Architecture notes & documentation
```

## Tests

```bash
# Unit + integration — no API key needed (~191 tests)
python -m pytest tests/unit tests/integration -q

# LLM scenarios — requires API key (37 tests, 16 concurrent)
python -m pytest tests/llm -n auto -q

# Frontend build check
npm --prefix frontend run build
```

> **37 real-LLM tests** cover edit scenarios, parse pipeline, interview flow, refine patterns, JD search, multi-turn conversation, and preference memory extraction — all run concurrently on deepseek-v4-flash.

See [tests/README.md](./tests/README.md) for the full guide.

## Agent Evaluation

For agent behavior work, start the backend first:

```bash
python -m uvicorn src.main:app --host 127.0.0.1 --port 8000
```

Then run one of the evaluation commands:

```bash
python scripts/agent_eval.py --regression --base-url http://127.0.0.1:8000/api/v1 -j 4
python scripts/agent_eval.py --base-url http://127.0.0.1:8000/api/v1 -j 4
python scripts/dres_bench.py iterate diagnose
```

## Document Types & Templates

- Copy `.env.example` to `.env` before running the app.
- The project is local-first by default; generated runtime artifacts stay out of the source tree.
- TeX export is generated as pure source text for user compilation.
- Layout templates and resume data are strictly separated to prevent accidental content loss during design changes.

## Documentation

All documentation lives in [`docs/`](./docs/). Start from the [Index](./docs/index.md) or jump directly to any topic:

- **Features**: [Dashboard](./docs/features/dashboard.md) • [Resume Builder](./docs/features/resume-studio.md) • [AI Tailor](./docs/features/ai-tailor.md) • [Mock Interview](./docs/features/mock-interview.md) • [Settings](./docs/features/settings.md)
- **Development**: [Setup Guide](./docs/development/setup.md) • [Architecture](./docs/development/architecture.md)
- **Design & Notes**: [Layout Flow](./docs/layout_design_main_flow.md) • [UI Style Guide](./docs/ui-style-guide-v2.md) • [Plans](./docs/plans/)

## Credits

The frontend and resume template direction were originally inspired by [Resume-Matcher](https://github.com/srbhr/Resume-Matcher).

resume-studio

File Explorer

# Use via CDN

Was this content helpful?

Recent Feedback

Download README