Open source (Apache-2.0) · v2.0.0 · 100% local
ResumeForgeCovers the main steps of a job search: find jobs, tailor a resume, apply and follow up, prepare for interviews
Supports Windows 10 / 11 · macOS 13+
The problem
These six things are where a job search usually gets stuck. ResumeForge builds something specific for each one — not just another “let AI write it” button.
A hundred applications, three replies. Usually the resume is not badly written — it just does not answer any particular job.
ResumeForge: generates against the JD line by line; match analysis gives five verdict types and an apply / needs confirmation / do not apply recommendation — before you send it.
Calling participation “leading”, or a team result your own. Two follow-up questions and the sentence collapses.
ResumeForge: every claim carries a level of ownership and a personal boundary; unconfirmed statements are explicitly avoided, and a resume still holding [TODO] markers is blocked at export.
You memorized answers, but the interviewer asks how the number was measured. If the definition is unclear, the polished wording does not help.
ResumeForge: interview deep dive stress-tests each confirmed claim — the rubric is locked before the question, evidence status replaces a score, and the session ends with a “what to fix” list.
Which companies, which stage, what to do next — all held in your head and a spreadsheet that keeps getting messier.
ResumeForge: the apply desk queues jobs and applies for you, with per-job progress, pause and a circuit breaker; successful applications flow into the tracker, and pasting an email screenshot updates the stage.
Certificates in one folder, interview notes in a notes app, links in bookmarks. When you need one, none of them can be found.
ResumeForge: the material library holds loose material, the knowledge base holds written notes, and the trash handles deletion and restore for all 22 kinds of content.
Your phone number, full history, a referrer's contact — put those on a website and you start worrying about how they will be used.
ResumeForge: data stays local by default (SQLite), job-site credentials are never stored, and exports can be redacted in one click or packed for offline sharing.
What makes it different
These are not here to make the feature list longer. They exist so the tool's conclusions can be checked by you — and survive an interviewer's follow-up. Each one comes from a real failure mode.
01 · Fact ledger
Every sentence that might go into a resume is first broken into raw fact, resume wording, level of ownership and personal boundary. Only confirmed entries may enter a formal resume — the assistant can read the ledger and add entries, but cannot confirm them for you.
See how the fact ledger works
02 · Match analysis
It returns five verdict types and an apply recommendation, each backed by the JD quote and your evidence. There is also a 0–100 reference score, with hard boundaries: computed locally, never used for the apply decision, and always shown with a disclaimer.
See what a match verdict looks like
03 · Interview deep dive
Each question locks its rubric at generation time — what to verify, which evidence to listen for, when to follow up — and never loosens it because an answer sounded fluent. Evidence status replaces a score; afterwards you get action items and a re-practice queue.
See how interview deep dives are scored
04 · Apply desk
It drives your own browser through “greet → attach resume → submit → verify”. A gate rejects jobs whose source cannot be verified, failure categories state the real reason, and a circuit breaker stops after repeated failures — it never quietly runs in the background without you.
See how the apply desk works
05 · Job analytics
Four themes summarize the search. Records without a date are named separately instead of counted as zero; a chart with no input renders an explicit empty state; metrics that cannot be computed are not shown — no row of zeros.
See the four analytics themes
06 · From resume to review
The editor includes STAR quantification, a phrasing generator, multi-style polishing, Chinese–English translation and version comparison, plus six quality and compliance checks. Export supports PDF / Word / HTML / Markdown / plain text / JSON / PNG with watermarking, one-click redaction or an offline share package; the page limit applies to the six paginated formats other than JSON, and “unlimited” really means no truncation.
See export & sharing
Workflow
You do not need to learn a methodology first. Follow the order once and you end up with a resume you can explain — and defend.
Fill in education and experience once (paste a resume, or upload a PDF/DOCX for extraction); then record the claims you want to use, with ownership level and personal boundary.
Auto-collect, paste text, drop screenshots or upload documents. Collected jobs land in a staging area first; you choose what enters the job board.
Run match analysis: five verdict types against the JD text, with a recommendation. Jobs that fail a hard requirement are dropped early.
Pick an enhancement level and a page budget, then let the AI stream a resume (the fact baseline is the confirmed ledger entries), or write it yourself; writing enhancers, quality checks and version comparison all live on the editor page.
Confirm the layout in the A4 preview; the layout report tells you whether the page is sparse or tight. Set the limit to 1 / 2 / 3 pages or unlimited; when content overflows, “fit to one page” tightens it step by step. A resume with [TODO] markers is blocked.
The apply desk queues and applies; the tracker owns every step after sending; reminders keep the next action visible; mock interviews and deep-dive sessions expose what you cannot yet explain.
A look at the app
Everything below is a real screenshot of the running app; the data is a fictional sample. 32 screens cover the full path from finding a job to reviewing an interview.
Quick entries can be reordered and grouped by “find jobs / write resume / apply / interview prep / my data / system”; upcoming reminders are color-coded by overdue, next 24 hours and next 3 days, with a month view.
Skill tags are extracted on save; each row opens details, generation, writing or related resumes; status changes and deletion work in bulk; jobs with an empty JD can be filled in with one click.
The JD is split into description, requirements, other information and notes; the bottom actions jump straight to generation, match analysis or the apply queue.
Paste the original text, press Ctrl+V for a screenshot, or upload a PDF/DOCX — documents are extracted locally. The result becomes an editable draft, and the source label stays on the record.
Favorited jobs and resume versions in one paged view; open details or remove a favorite directly.
Both AI-generated and hand-written resumes live here, labeled with source, model, enhancement level and target job; favorite, annotate, and filter by favorite or linked job.
Layout diagnosis shows how much of the page is filled and the order to fix things in (reorder → structure → spacing and type size → trim → add pages); when content overflows, Auto one-page tightens step by step, or choose Unlimited for no cap. Export offers watermark and redaction; with a page cap set, PDF / Word / HTML / Markdown / plain text / image (PNG) are all trimmed to the same limit, and the export says which block was left out.
This is the HTML actually rendered by the server — the same file you get from “Export HTML”, not a mock-up. PDF can also be downloaded directly, without browser printing.
The header states the four-step flow and the connected job site; each job carries an eligibility verdict and the resume used; you can pick the browser, and its state honestly distinguishes “launched by this app” from “your own window”.
Collect by keyword and city, or use the job site's own filters (job type / salary / experience / education / industry / company size / funding stage); conditions can be saved and refilled.
Every collection keeps its conditions and results (staged / duplicate / failure reason); expand it to import selected jobs into the board.
One “start applying” run equals one batch, collapsed into a group with batch statistics and status; failures state the real reason and page, and can be retried.
A dedicated browser opens the company's web form, reads the whole page, lets you verify line by line and then fills it; it writes into text fields only, never submits, reports the real success rate, and keeps a fill log.
One record per company and job, moving “applied → screening → assessment → interview → offer”; status only moves forward (except rejection), and every record keeps its evidence note.
Conversion and blockers, timing and rhythm, channels and destinations, resume and health — four themes; trends cover 1 / 3 / 6 months or one year, and records without a date are listed separately.
Set the job, type (eight kinds), difficulty, interviewer style and rounds; answer and get follow-ups, then a final score, dimension scores and improvement advice.
Generate basic, project-deep-dive and ask-the-HR questions from the linked job and profile; generate a detailed answer for a single question; results are saved to history and restore completely.
Record real interviews — company, job, questions, review — tagged by difficulty and round; click a card to read the full question list.
Enter real interview questions → the AI analyzes answer structure, likely follow-ups and common mistakes → reverse-engineer resume suggestions (advice only; you decide what to change).
Familiar with the interface and the database: it can read reminders, referrals, interview notes, question-bank history, reviews, the knowledge base and analytics, and it also sees web-form fill records and past page URLs, batch match-analysis records and queue state on the apply desk. It writes only when explicitly asked and can never delete anything — nor does it start captures or applications for you; those two steps are yours to click. [source N] in its answers links to the original passage.
Basic information, education / work / campus / project experience, skills and awards are kept in sections, expanded by default (collapse one by its title, or expand/collapse all from the header); each experience can carry a Markdown/TXT summary; up to 8 photos, and photos are never sent to the model.
Each claim records raw fact, resume wording, ownership level and boundary; verification status decides whether it may enter a formal resume; “start a deep dive” starts a stress test.
Confirmed claims are stress-tested one by one; switch between “real simulation” (review at the end) and “training mode” (feedback after each question).
Certificates, works, links, notes, internship and campus materials in one place, with attachments; click a card for the full text and attachment list.
Written notes live here: interview summaries, resume tips, Q&A, company info, industry knowledge; categories and tags, Markdown body, searchable and editable by the assistant.
Create a skill from scratch or import one (prompt plus knowledge files); once enabled it constrains the assistant's style, and the assistant can also revise it for you.
Six built-in styles shown as real thumbnails (not mock-ups — same rendering path as the real preview). Copy a built-in template, import your own HTML, or import a target resume: upload an image or PDF and the model reads its accent color, line height and margins into a format template; click a thumbnail for a 1:1 view.
22 kinds of content share one table, each with a type tag and a deletion time; restoring takes one click, while permanent deletion and emptying ask for confirmation and state the consequences.
16 provider presets (including Anthropic native), model discovery for the current account and advanced parameters; save multiple named configurations and switch anytime.
Create a blank dataset, export the current or all datasets, import a backup as a new dataset; backups exclude the API key by default (opt in before export), and import is all-or-nothing.
Show or hide interface and navigation entries, the floating assistant, theme, motion and reminder behavior — all on this page.
Opens automatically on first launch and explains how the modules connect in order; reopen it anytime from the bottom of the sidebar.
32 screenshots · use arrow keys or drag · click any image to zoom
Feature list
From reading a job screenshot to applying, following up and reviewing the interview. Each step is documented in the user guide.
Record each sentence as a claim: raw fact, wording, ownership level and boundary; only confirmed claims feed generation.
Stream a draft against the JD, choosing enhancement level, template and page limit (1 / 2 / 3 or unlimited); it runs as a background task you can inspect or cancel.
Prefill from your profile, then edit freely with the job requirements pinned on the right; STAR rewriting, polishing, version comparison, and one-sentence edits to just the selected field.
Duplicates, sensitive words, exaggeration risk, interview follow-up risk, compliance and local ATS checks — six categories; risk points link to the fact ledger. ATS scores are now tied to keyword coverage, so the same resume scores lower than before: that is a correction, not a regression.
Automatic skill tags, status changes and bulk actions; JD analysis returns a structured summary with evidence.
Five verdict types plus an apply recommendation, each with the JD quote and your evidence; the reference score never affects eligibility.
Queue and auto-apply, per-job progress, a circuit breaker after repeated failures; only jobs whose source is on a supported job site are accepted.
A dedicated browser reads the whole form, lets you verify each row, then fills it; it never submits and reports the real success rate.
Eight interview types, three difficulty levels and four interviewer styles; the question bank is generated from the job and your profile.
Confirmed claims are stress-tested one by one with the rubric locked up front, ending with action items and a re-practice queue.
PDF / Word / HTML / Markdown / plain text / PNG share one page limit (JSON is complete data and is never truncated); watermarking, one-click redaction and offline share packages are supported.
Parsing, match verdicts, layout rendering, export, duplicate checks and ATS checks all run on local rules; no model required.
Open source under Apache-2.0; the code can be read and changed. All data lives in local SQLite on your machine, never uploaded, and job-site credentials are never stored. Moving to a new computer is one dataset backup.
See the data & privacy boundariesDownload
ResumeForge is fully open source (Apache-2.0) and stores data only on your machine. This page offers the latest stable release; screenshots and docs follow the current code, so details may differ slightly from the release.
Supports Windows 10 / 11 and macOS
A fictional dataset: 31 jobs, 15 resumes, 21 claims, 20 tracker entries, 12 interview notes, 13 application records across 6 batches with failure diagnostics, 20 reminders, 6 referrals, 18 material-library items and 17 knowledge notes, plus question-bank and review history, interview deep-dive sessions, 3 model configurations and 3 custom templates, covering every screen in the app. Exported by 2.0.0 and meant for the 2.0.0 download; importing only adds a dataset and leaves your data untouched.
Download demo dataClick Download the latest version below to get the installer or archive (the Windows / macOS portable builds are about 27–29 MB and include source and docs; installers are exe / dmg), then extract or install it anywhere. If GitHub is reachable, git clone works too.
On Windows, double-click start.cmd; on macOS, double-click start.command. The launcher prepares the runtime, installs dependencies, starts the services and opens the browser. The first run needs network access and usually takes a few minutes.
For AI generation, match analysis, the assistant and interviews, open Settings, pick a preset or enter a custom endpoint, test the connection and save. Without a model you can still maintain your profile, manage jobs, write a resume by hand and export.
Every package ships with a matching .sha256 file; verify the hash after downloading. Reference values for v2.0.0:
25e84f98ad5bd4095a15229930e6c3e43b9ad51ae44e71fd34422ab985fc3f3b
105c3e4ad7391b867854aa0168c2f4170c45de9a30d53ad84a15e3e577ca6531
81b6ebc7296746f061c3ac3c77bae3ebbc199af31a49f6b672352275c0c36204
0b5daedfbceb459823ab8ec12dd48bbd9774716aa7cf8c1dc22097c5b434a8f8
9fc1806ad38f034cec4f01efc78bcc4ab2be7ac2b574c1e9e0c9d6bdca523f58
To verify (three steps): ① download the package and its .sha256 file; ② in that folder run Get-FileHash .\ResumeForge-2.0.0-windows.zip (Windows PowerShell) or shasum -a 256 ResumeForge-2.0.0-macos.zip (macOS / Linux terminal); ③ compare the output character by character with the value above before running it. In-app updates perform the same check before installing.
Community
This project has no support desk, but the group has people in it. Questions, feature requests and bug reports are welcome, and the next release is discussed there first. The group files also include installers — handy when GitHub is slow.
QQ group 922830167
