DEV TRENDS / CATEGORY
70 new projects first discovered during Sep 6, 2026 – Sep 12, 2026, deduplicated across 8 sources.
Native Mac tool: type @@ in any text field to send screenshots, selected text, clipboard items or Finder files to your own Claude Code/Codex agent, preview the answer, then Tab it back in. Also screenshots, recording, clipboard history.
Mobile Easy Use lets AI agents access Android/iOS app runtimes via MCP for debugging and validation. It adds UI automation, business/config reads, method hooks, call stacks, timing/memory, value/field swapping. Based on Frida; MIT.
A Markdown AI skill that first lists 3–5 prerequisite concepts of an unfamiliar topic, has you mark used/learned/never, then teaches from your level step by step with diagnostics; citations are DOI-verified or flagged unverified.
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.
DeliverKit links packaging knowledge, reviewable plans, and real artifacts for AI agents via MCP. Linux deb/rpm/AppImage builds and clean-container install/run verified; Windows/macOS/HarmonyOS dispatch to CI runners. MIT TypeScript.
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.
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
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.
Cortex is an open source API knowledge layer that turns OpenAPI, AsyncAPI, GraphQL, gRPC, and OpenRPC specs into interactive documentation, typed SDKs in 11 languages, and MCP servers for AI agents.
QApilot MCP automates tests on real Android devices and emulators by talking to Claude, Cursor or Codex. Describe a test flow in plain English, no Appium code required. Your agent lays out the steps. QApilot runs the steps.
Stackness is where developers and vibe coders show the tools, workflows, and approaches they build with. Build a stack profile you share as one link, post your moves, follow people whose taste you trust, and watch tools rise and fall.
A Mac menu bar agent status tool and local usage ledger. Track Claude Code, Codex, and other tool activity, receive supported Hook completion or pending alerts, filter token records by tool, model, and project, and export CSV.
Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.
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.
Project URL Category JS Project Title Official MCP server for the Taskade workspace Project MIT-licensed MCP server that connects Claude, Cursor, VS Code, or any MCP client to a Taskade workspace.
ContextOS is a macOS app and MCP server for Codex: it stores a Git-tracked project graph, serves path::symbol locations instead of full files, compresses terminal logs, and gates completion on test results, cutting long-task context ~60%.
codereview-ai: self-hosted AI code review platform. It posts line-level PR/MR comments via LLM, Semgrep, and agentic reasoning. Webhooks trigger reviews, backfill missed PRs, notify DingTalk/Feishu/WeCom. Docker deployment, Vue 3 admin.
Converts PDF, DOCX and HTML to Markdown in-browser; text-layer PDFs never upload. Edit/copy results, download files or batch ZIP. Cloud OCR for scans; Markdown-to-PDF, REST API, MCP for automation. Local use is free.
The tools Claude is missing: track time, sign contracts, send invoices, get paid. Free MCP connector for Claude, Claude Code, and any agent.
Jackalope brings Codex, Claude Code, Grok, and OpenCode into one shared workspace. Run tasks in parallel Git worktrees, keep project context together, and review changes before applying them.
Cadenya is not a framework you bolt into your application stack. It's a hosted agentic loop. You connect tools using specs you already know, like OpenAPI and MCP, and Cadenya runs the agent for you.
Kernel-level anti-detection browser that alters fingerprints in C++ instead of injecting scripts. Exposes a standard Playwright BrowserContext over CDP, so existing Playwright scripts run unchanged. Free tier: unlimited local profiles.
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot.
JeecgBoot is an enterprise AI low-code platform that generates full-stack code and whole systems from prompts. AI Skills create workflows, forms, reports, and dashboards; built-in AI offers chat, knowledge base, orchestration, MCP plugins.
One-command job hunt for China: aggregates Liepin, BOSS Zhipin, Zhaopin and 51job listings, filters hard requirements, scores matches, drafts greetings and Typst resume PDFs, tracks applications locally; you apply manually.
Project URL Category JS Project Title Selfhosted BYOK AI workspace: multiprovider chat, plainEnglish agent builder, scheduled runs Project A selfhosted AI workspace that runs on your own provider API keys (Groq, OpenRouter, NVI…
The open agent skills tool - npx skills
MERVYX is a marketplace for verifiable outcomes from AI agents, APIs and automation services. Providers list services with pricing and acceptance criteria; buyers post tasks with budgets for quotes. Currently 0% commission.
Audit any public URL for free, no signup. FreeScan uncovers problems and missed opportunities across SEO, AEO, GEO, security, accessibility, and design. Every finding includes evidence, why it matters, and how to fix it.
Speechmark is a private macOS meeting-notes app. It records, transcribes, and summarizes meetings entirely on your Mac — decisions, action items, speaker-attributed transcripts. No bot joins the call, no account, one-time price.
Adnify is a local-first multi-agent IDE for editing, agent runs, task orchestration, terminal and browser checks. Plan Mode yields reviewable task graphs with dependencies and acceptance criteria; parallel agents use Git worktrees.
rpi is a Rust-native implementation of the Pi agent, following a library-first design that splits providers, agent loop, tools, sessions, and terminal UI into separate crates.
FluentRead is an open-source browser extension for bilingual web page translation, displaying original and translated text side by side. It uses DeepSeek Harness as its engine and has been open source and ongoing since 2024.
A prompt and case library for GPT Image 2 / 2.5 with 530+ examples, 20+ industrial-grade templates, reusable Skills, and a new same-prompt comparison section, each with full prompts and generation records.
Codex Memories: a preview local memory tool for Codex. Stores project rules and decisions in Git with a local index. An API-key-free writes fake memories, recalls them in a new process, and cleans up, so you can try before installing.
DSHX: an open-source TypeScript/React toolchain for DeepSeek Harness plugins. Vite-based, with scaffolding, diagnostics, typed Host–Client APIs, and a community plugin/compatibility site. MIT, Preview; needs compatible DeepSeek Harness.
Learn it. Build it. Ship it for others.
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
Runner is a local AI agent orchestrator for multiple Claude Code / Codex in one native desktop app. It uses runner configs, lead-led crews, missions, PTYs, local append-only logs, askhuman, cross-vendor MCP server, Rust/GPUI, GPL3.0.
Harden AIF is a free, local security tool for AI coding agents. Its post-trained model checks tool calls before they run, using your request and session context.
From the team behind Gatsby, Mastra is a framework for building AI-powered apps and agents with workflows, memory, streaming, evals, tracing, and Studio, an interactive UI for dev and testing. Start building: npm create mastra@latest
开发者自荐浏览器工具“AI开源项目雷达”，提供日/周/月趋势榜、爆发、新项目等入口，展示用途/语言/适用人群，建议回上游核对。收录开源AI项目，排名非审计。
OriginalCodex task status lights for the NuPhy Air65 V3 on macOS
Open-source agent runtime for persistent cognition, structured context, and concurrent work.
Open-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
CLI for browser automation: let any AI agent drive your real Chrome — logged-in tabs, zero deps, no relaunch, no MCP server. A11y snapshots + element refs, CDP screenshots, network capture. 让任何 AI 智能体(Claude/Kimi/Qwen/DeepSeek/GLM)驱动你真实的 Chrome 浏览器——已登录会话、零依赖、无需重启。
OriginalAI Context Linker is a privacy-first context compiler and open schema. It lets AI assistants understand local projects through minimal, auditable context bundles without uploading the codebase. Agent skills are optional interfaces over its standalone CLI.
ReadGZH：将公众号链接转为AI可读精简页面，供AI总结整理。提供网页、REST API和MCP，有免费及付费额度，依赖上游可访问性，适合频繁处理公众号资料的人。
OriginalSpatial canvas IDE for AI coding agents
Bring any AI agent into Slack, Teams & Discord
Open-source CRM with approval-gated AI writes
EnReader是一款Agent Native英语阅读工具，支持RSS订阅和电子书导入，阅读中可查词、翻译、逐段讲解并随时向Agent提问；Agent结合上下文回答，帮助真正读懂英文，而非替用户总结。
OriginalA source-grounded translation workflow skill for Codex and Claude Code.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
DeepDeck — an extensible desktop workspace for DeepSeek Harness.
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.
A configurable 3D jump-chess framework with A/B geometries, multi-player rule switches, and RL/self-play training support.
本地开源简历工具，通过AGENTS.md接入豆包、Codex等AI Agent，以对话方式逐块修改简历。数据存本地YAML，带reference记忆区，构建时自动截断。
OriginalThe context quality layer for AI agents — memory that checks itself: lifecycle governance, calibrated confidence, and staged claim gates. Local-first, MCP 19 tools, DeepSeek Harness plugin.
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.
Non-custodial AI Agent: research, predict & trade crypto
See code through a new lens
Agent skill that removes signs of AI-generated writing from text
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Give your team one AI memory. Keep your own private.
Try another keyword or category.
