Mirror – Open-source job search and resume tool with integrated memory
Mirror is an open-source job search and resume tool designed to learn and adapt to a user's writing style. It features a unique memory system that retains user-specific phrasings and style rules, enhancing the resume generation process. Currently in pre-1.0 status, it offers a structured approach to resume building that prioritizes user voice and fit for job postings.
- ▪Mirror is a self-hosted job search assistant that learns from user edits.
- ▪It generates resumes that reflect the user's voice and drafts answers for application questions.
- ▪The tool features a two-tier memory system that stores both specific phrasings and general writing style rules.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/prateekpuri01/mirror |
| Publication time | Tue, 26 May 2026 16:53:09 +0000 |
| Retrieval time | 2026-05-26T17:07:50.079Z |
| Last seen | 2026-05-26T17:07:50.079Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | --UoZyfFGAPC |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Mirror An AI resume agent that learns your voice from your edits. Mirror is a self-hosted, local-first job search assistant. It does three things most "AI resume builders" don't: ranks scraped job postings by fit to your profile, generates resumes that get progressively more in your voice with every edit, and drafts answers for the open-ended questions on application forms (the "Why do you want to work here?" / "Tell us about a time…" prompts). The deepest piece is the voice memory: most AI tools generate fresh from scratch every time. Mirror remembers the actual phrasings you've hand-tuned for each accomplishment, employer, and skill bucket — and feeds them back to the next generation as grounding examples.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.