Nigh/show-me-the-story

Score7.9

Popularity258.0

Risknone

TierSilver

Score breakdown

Usefulness8.0

Novelty8.0

Momentum7.0

Maturity8.2

Open-source/build8.4

Evidence8.0

Workflow potential9.0

Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for writers / novelists / RPG campaign designers / serial-fiction authors who want a **self-hosted** AI novel-writing tool that does not require a SaaS subscription, runs on the user's own hardware, accepts any OpenAI-compatible API (so the user picks the model and the provider), and implements a two-phase outline-then-chapter workflow with per-chapter review; for users who hit the **long-f

Who should use it

Writers / novelists / RPG campaign designers / serial-fiction authors who want a **self-hosted** AI novel-writing tool that does not require a SaaS subscription, runs on the user's own hardware, accepts any OpenAI-compatible API (so the user picks the model and the provider), and implements a two-phase outline-then-chapter workflow with per-chapter reviewUsers who hit the **long-form-coherence problem** in vanilla LLM writing — the foreshadowing system tracks planned → injected → fulfilled lifecycles and surfaces overdue-recycle alerts, and the narrative memory layer auto-extracts per-chapter detail not in the outline and cross-chapter-injects it so character habits and prop details survive summary-window truncationUsers who want **explicit control over the output** — the outline phase requires user sign-off before any chapter is written, the chapter review phase leaves non-destructive comments, and auto-confirm mode is opt-inUsers who want **structured character / world / organization management** — character sheets, worldbuilding notes, organization rosters, and a visual relationship graph (interactive node-edge diagram in the browser) are all first-class entities the writing prompt pulls fromUsers who want **bilingual projects** — each project picks Chinese or English, AI prompts, generated body text, built-in skills, and agent system prompt all switch, and the front-end UI independently togglesUsers who care about **local trust boundary** — single Go binary, reads/writes only the project directory the user picks, makes outbound network calls only to the configured API base URLUsers who want **fact-check + full-book polish** — automatic fact-check runs after each chapter (auto-rewrite on inconsistency), end-of-draft polish runs diagnose → Excel-style work-orders → auto-revise with diff view so the user sees exactly what changed chapter-by-chapterEvaluation: download the binary from the latest release for macOS arm64 / Windows x64 / Linux x64, run `./show-me-the-story`, open `localhost:48090` in the browser, configure the API base URL and API key, and start a new project

Who should skip it

Skip Nigh/show-me-the-story unless the captured evidence suggests it solves a problem you are actively working on.

About this signal

Nigh/show-me-the-story is tracked by RepoRadar as a self-hosted ai novel generator: in the MIT self-hosted AI novel generator that ships as section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Silver tier and easy setup difficulty. Across RepoRadar's eight signals, Nigh/show-me-the-story is strongest on workflow potential (9.0) and setup ease (8.8) and weakest on momentum (7.0) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned Nigh/show-me-the-story a composite score of 7.9 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 258.0 and never affects the composite score or tier. The risk label of 'none' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

github.com

Closest alternatives / related signals

show-me-the-storynighai-novel-generatorself-hostedsingle-go-binaryweb-uilocalhost-48090openai-compatible