DEV TRENDS / CATEGORY
21 new projects first discovered during Sep 6, 2026 – Sep 12, 2026, deduplicated across 4 sources.
A novel-writing skill set for AI agent terminals (Claude Code, OpenCode, Codex, ZCode). It walks writers through worldbuilding, characters, outlines, drafting and review, with genre knowledge bases and one-click install scripts.
Multi-agent research workbench: literature review, code execution, data analysis and writing in one place. A main agent coordinates specialists; a Graph of Trace shows tasks, tools and evidence. TypeScript, self-hostable.
Jiandan is a Windows tool for Jianying Pro. Copy/screenshot an image, press Ctrl+V in the draft media panel to import it as a clip asset. It tries to place it at the playhead above tracks (version/UI). Suits and knowledge cards.
A skill pack for web-fiction authors that turns Claude Code, Codex and other coding agents into writers: scan rankings, deconstruct hits into plot modules, draft with hooks, then de-AI the prose and make covers. 13 skills, 7 agents.
IELTS writing practice platform offering Task 1 and Task 2 question banks, mock writing sessions, AI scoring, and sentence-by-sentence feedback.
Login-free, open-source AI image prompt library: 541 cases in 13 categories like e-commerce, posters, photography and illustration. Browse results, copy prompts, search, filter, bookmark locally, and use a prompt skill in AI assistants.
CLI tool that reads and writes local Jianying/CapCut draft files to batch add subtitles, style captions, edit timing, speed, volume, templates and animations, and split long videos into shorts. JSON in/out lets any LLM agent drive it.
AI image generation and editing service: upload an image and describe the changes to get new visuals that keep key elements like people, product details and composition.
MotiClaw is a local AI content creation workspace.
wenbiao: 5 copyable prompts—tender parsing, score-point breakdown, outline, chapter drafts, bid-rejection checks. Missing facts marked 'to be filled'; no fabricated credentials; human review required. Open prompts/workflows, not SaaS.
Open-source multi-agent dev env for Codex, Claude Code, and OpenCode. Terminal/chat views, Git Worktree isolation, kanban, Tailscale phone access. CLI for agent task/worktree/session control. Codex imagegen. Windows/macOS/Linux; AGPL-3.
WYSIWYG Markdown editor built with Tauri 2 and system WebView, not Electron. Live rendering for tables, tasks, code, LaTeX and Mermaid; file tree, outline, image assets, autosave, themes, HTML/PDF export. Local-first, no account/cloud sync.
YYLO is a CLI that governs AI coding agents: each task freezes the protected branch SHA, runs in its own git worktree, and must clear validation, merge and release-readiness gates. Review is risk-tiered; runs stay auditable via receipts.
A web workbench for GPT Image 2.5: generate from a prompt or upload a reference image and describe edits, returning several images at once. Flare and Sunburst models, 1K/2K/4K output and square/portrait/landscape ratios. English UI.
One-stop AI video and image generation platform that aggregates mainstream video and image models.
针对图片中单一文字修改耗时的问题，推出工具 EditTextImage：上传图片后填写原文字和替换文字，即可保留原字体、颜色、背景和透视，只改目标文字。适合改价格、日期等。
OriginalOpen-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first · multi-Harness roadmap · DeepSeek Harness integration in progress
Meltbead是一款免费在线拼豆图纸工具：上传图片可自动生成可编辑网格图，提供颜色色号、珠子用量，支持Perler/Hama/Artkal，无需注册，图片本地处理。
OriginalVisualStyles 是在线视觉风格图鉴，以同一苹果为主体呈现100多种艺术、设计、摄影、数字风格。支持随机浏览、双风格对比、看图猜风格，中英文双语，免注册免费，适合艺术设计爱好者与学习者。
OriginalYayaTools 免费在线工具箱，提供 80+ 工具，涵盖 PDF、图片、文本、开发调试、数据转换、安全、计算等；多数处理在浏览器本地完成，无需注册，不上传文件，打开即用。
OriginalScreentell是一款无需安装的浏览器一站式录屏工具，集录屏、运镜、剪辑、导出于一体。支持录制屏幕、摄像头、系统声和麦克风，提供3D运镜、标注、剪辑等功能。
OriginalTry another keyword or category.
