Javascript agents

Local-first Chrome extension: inject selected web content into ChatGPT with reusable prompt templates.

Time-boxed autonomous iteration that turns Claude into its own editor. A Claude Code skill that drafts, scores, questions, and revises any task until time runs out -- then distills what it learned into a reusable skill file.

Beginner-friendly OpenClaw multi-agent content creation starter with one-command install, self-check, sandbox testing, and Chinese-friendly provider presets.

🤖 Streamline ticket management with AI that categorizes, prioritizes, and assigns support tickets to the right moderators for efficient resolutions.

A job-application app whose backend is a headless LLM agent (Claude Code CLI). Markdown + git as the database.

Full-stack air quality analytics platform built with FastAPI, React, and MySQL. Aggregates multi-source PM2.5/PM10 data, performs multi-city comparison and time-series forecasting (SARIMAX), and integrates an LLM-based planning agent with tiered access, secure APIs, and PDF reporting.

🎨 Enhance cinematic image quality with ComfyUI-None-upup. This AI engine offers nodes for clarity, brightness, and video processing to elevate your visuals.

This project is a GitHub Repository Analyzer that helps developers quickly understand unfamiliar repositories. Often when developers encounter a new repository, it can take significant time to understand the structure, technologies used, and architecture. So I built a web application that analyzes a GitHub repository and generates insights

Official integrations for SnapRender Screenshot API — MCP server, SDKs, OpenClaw, ChatGPT Actions, Postman

Локальный совет AI-агентов: API-провайдеры и Ollama обсуждают задачи в параллельных раундах с Knowledge Base и Autopilot.

A Feishu-first multi-agent system for content intake, evaluation, and action routing.

Self-hosted autonomous AI agent platform with 90+ MCP tools, persistent memory, and self-extension capabilities. Runs on your remote machine and grows its own capabilities.

Connect AI agents representing humans through the A2A protocol for seamless, secure interaction across apps and tools.

Claude Code marketplace and home of claude-engineer: an opinionated, design-system-first, plan-gated autonomous engineer for full greenfield React/Next and FastAPI projects.

AI-agentic-first Claude Code framework: bootstrap projects with safety + standards in under 3 minutes; let Steward maintain them autonomously every night.

Arbitrage AA and bot for arbitraging between Ostable and 2 Oswap pools

Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.

Forging a minimalist universal language for AI, unconditionally eradicating hallucinations and automating Agent Swarm intelligence.

Orchestration runtime for AI agent workflows that preserves task-state fidelity, prevents reasoning drift, and reduces wasted computation in long-horizon pipelines.

🤖 Build and manage AI-driven SRE agents to automate operations tasks with natural language and integrated monitoring tools.

Glass-box, multi-domain agentic orchestrator for Claude Code: detect context, assemble the right crew, run domain pipelines, show the reasoning.

NiyoX AI - Powered by DanuZz.

Markdown generator for AGENTS.md

A dry-run firewall for coding agents — approve & audit tool/MCP/shell calls before they hit the real world. By Martello Systems.

A local-first personal operating system template for thinking, planning, creating and evolving with an AI interface.

Chrome MV3 side-panel AI assistant — multi-provider (Gemini, OpenAI, Anthropic, OpenRouter, Ollama, LM Studio), BYOK, page context, local RAG, custom skills

Local interview copilot web app and meeting overlay extension

An intelligent AI-powered assistant add-in for Microsoft Word that integrates with Groq and Google Gemini AI to provide document analysis, smart editing, summaries, and formatting capabilities.

Add local persistent memory to AI coding agents with Markdown storage, hybrid search, and MCP support, all offline.

A glass terminal materializes running Claude Code as your personal AI assistant. Persistent memory (LLM wiki), voice, computer use, Obsidian-compatible.

Modue control surface plugin for OpenClaw — live agent activity, channel health, physical approve/deny buttons, and agent-callable LED/display tools.

Full-API MCP servers generated from official OpenAPI specs: Stripe (587 tools), Vercel (333), Clerk (224). One npx command, intent-friendly tool names. Run standalone or behind Toolport.

Stateless reducer that turns a feature description into a 9-file PRD. 17 MCP tools · multi-judge verification with weighted-average + Bayesian consensus · deterministic Hard Output Rules · research-evidence-backed strategy selection · 248 tests · part of the ai-architect ecosystem.

Tunnel Panda is a modular, secure reverse-proxy that streams local Ollama API and Chrome DB via Cloudflare Tunnel of yours to make it publicly accessible. Now we do have an GUI interface for the configuration.

BMAD-inspired sprint workflow skills for Pi (https://pi.dev)

Agent's procedural memory for the web. Turn one successful browser workflow into reusable, zero-cost CLI commands.

IssueMe is a Pi extension that streamlines GitHub issue management, making it easier to create, track, and organize issues directly from your workflow.

Fast, secure, client-side tool to bundle your codebase into a single text file for LLM context.

Flarepoint | A plaza of small, behavioural Claude Code plugins that make the AI's cognitive state explicit and persistent

Enable automatic topic-based memory for Claude Code to maintain context across sessions and data compactions without losing information.

Open API for AI agents to research 29,000+ declassified U.S. government documents (Epstein, JFK, 9/11)

Local side-by-side eval workbench that turns one AI product evaluation idea into eval cases, comparable evidence, and a decision-grade report.

Cloud-native smart token & queue management system - real-time queues, AI assistant, team messaging, ML predictions. React + Express + Firebase.

Multi-agent deep research for Claude Code. Zero API keys. Paste one line, type /research.

A job-application app whose backend is a headless LLM agent (Claude Code CLI). Markdown + git as the database.

Chrome-tillägg som låter en LLM sköta kundtjänstchatten åt dig — du pekar ut fälten, den skriver.

Offline plan drift scoring for LLM agent traces

Claude Code Workflow that executes cys:plan implementation plans with independent tasks running in parallel via a dependency DAG — ships the cys plugin (design, plan, run, check, ship).

Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.

Judgment continuity for AI agents — load your project's scars, taste, and non-negotiables into every session. Judgment-layer companion to edda. (formerly project-doctrine)

Give AI agents hands without handing them the keys: exact one-use approvals and verifiable receipts for registered actions.

Portable Claude Code skills + agent panel that translate any project or files into any language — codebase i18n, WordPress/gettext, docs — with adversarial QA, per-run domain specialization, and terminology research.

Zero-dependency multi-agent build, automation and review system for Claude Code. 18 agents, 23 skills, a live per-project dashboard, and a /setup-forge onboarding wizard. One command: /forge.

RSS for state. Open portable evidence layer for machine state - preserving what an agent or system saw, produced, derived and learned, so another party or future agent can verify the lineage independently.

A Jarvis-style local second brain — voice-controlled Claude Agent SDK orchestrator with a live neural dashboard, a self-learning markdown knowledge base, and worker agents dispatched into your repos.

Agentic RSS Parser - An open-source Node.js library for parsing RSS and Atom feeds with built-in heuristic and LLM-based relevance analysis, deduplication, article enrichment, a CLI, and an MCP server.

Human-like browser control for AI agents — verify-first (proves every action worked), with an MCP server + JS & Python SDKs. Playwright + native + extension. MIT.

Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work

TalentFlow HR — modern dark-themed HR dashboard for IT staffing & consulting firms. Drag-and-drop candidate pipeline, job requisitions, interview tracker, analytics, and a built-in AI assistant (Ollama / OpenAI / Anthropic / Gemini) with offline template fallback. React + Vite + Tailwind. Zero backend, zero cost.

ATHENA is an AI-powered desktop voice assistant with real-time speech recognition, LLM integration, and system automation. It performs tasks like opening apps, setting reminders, fetching weather, and generating documents, all through voice commands with an animated globe UI for interactive feedback.

AXI: A next-generation Cybernetic Intelligence Assistant. High-performance voice control, HUD-inspired interface, and autonomous learning powered by a custom-built NLP engine with 1,400+ intents.

AI-powered side panel for DHIS2 (Chrome MV3). 32 tools — analytics, tracker writes, atomic metadata authoring (programs, datasets, category combos, sharing), rule/indicator audit + repair, backups. Any OpenAI-compatible provider; defaults to local Ollama, no API key. Authenticates via active DHIS2 tab session.

MCP server: verified SaaS price-change history, watch-log for AI assistants, data by ComparEdge

MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge

Tool-agnostic agent workflow starter kit. One workflow core + team profile, generates adapters for Claude, Codex, Cursor, Copilot, CodeBuddy, Kiro, Trae.

Local-first Chrome extension: inject selected web content into ChatGPT with reusable prompt templates.

TypeScript/Node.js MCP server for LinkedIn API integration - Create posts, manage content, and interact with LinkedIn through Claude Desktop and Windsurf IDE

🎯 AI agent skill for optimizing Next.js applications for search engines

DeepSeek Harness 官方架构的 Windows 桌面发行版 (Desktop distribution of the official DeepSeek Harness)

Execute SKILL.md agents via 4 modes — binary CLI, npx, HTTP API server, or embedded Node.js SDK

Lightweight modular AI assistant platform with multi-provider LLM support, MCP integration, RAG-powered fact memory, profiles, chat persistence, and live token tracking.

A desktop application for managing multiple TikTok accounts, managing private messaging, and providing AI-powered auto-response.

an AI-based Academic Assistant platform designed to help students and faculty with academic insights, risk prediction, and career guidance

A lightweight desktop client for DeepSeek Harness.

Play local-first AI interactive fiction using a dual-loop system with a fast narrator and file-native background agents to manage story structure.

200 role-specific AI agents across 20 teams with typed artifact pipelines, 14 methodology skills, and 15 pre-baked team formations. The virtual engineering org for Claude Code, Cursor, Codex CLI.

Turn a use case into a grounded agentic system design. An opinionated AI solutions architect as an agent skill.

npx thetacog-mcp — a decidable, on-chip, LLM-free placement receipt a stranger recomputes byte-for-byte. Free for builders; patent-licensed for production & financial use (US Patent App. 19/637,714).

DeepSeek Harness desktop app: ChatGPT-style lightweight window over the dsh web UI with custom background images.

F.R.I.D.A.Y. - a terminal-first AI assistant core. Multi-provider LLM fallback chain (NVIDIA NIM / Groq / Gemini / Ollama), speech-to-text, vision, and live stock/weather/time skills. Backend only - build your own floating-ring UI on top.

Pursue roles that fit. A local-first job-search assistant for scanning jobs, tracking applications, and tailoring resume / cover letter packages.

Get the benefits of pre-converting to markdown without interrupting your workflow. Pour a document into a lighter, cleaner form and leave the heavy sediment (the image layer) behind before it reaches the LLM.

Local OCR for DeepSeek Harness — read text from screenshots on your Mac with Apple's Vision framework. No API key, no upload.

DSH-Desktop - DeepSeek Harness Web GUI 的 Windows 桌面版

Connect Claude Code, Cursor, and Codex to Workflow (workflow.games): your AI coding agent plans requirements, files bugs with dedup, runs real online QA, and drives ticket status — every write verified by read-back. Agent Plugins 1.0.0 + Claude Code marketplace.

DeepSeek Harness (DSH) 代码参考检索与复用调查插件：开发前检索本地代码库与 GitHub/npm 开源项目，评估复用/改造/引入依赖/自制并询问用户，支持架构级复用。Code reference & reuse-survey plugin for DSH: search local code + GitHub/npm before building, evaluate reuse vs rewrite, ask the user, architecture-level reuse.

DeepSeek Harness Core (DHC) · AI 人格核心进化插件 / AI personality core evolution plugin for DeepSeek Harness

Modern Patna Metro mobile app built with React Native & Spring Boot, featuring an AI Voice Assistant (Bodhi), smart route finding, and bilingual support.

小语 AI 工作台 - 有记忆/情绪/进化系统的 Web AI 工作伙伴（多模型+文件交付+一键分享）

Realtime multimodal AI agent with voice streaming, RAG memory, and autonomous workflows

An interactive, client-side app that teaches how modern agents and language models work and how they are used.

Minimal first-turn RL anchor for DeepSeek V4 on DeepSeek Harness Standard.

ARCHIVED historical registry. Atlarix removed the in-app skills registry in v14.45.0 — skills are now markdown files in .atlarix/skills/, committed with your own project. Kept for history only; see atlarix.dev/docs.

给 DSH agent 的插件库"起飞前检查单"——任务型请求时自动预检插件库并注入 Top-K 适用插件提示，让插件库利用率可预期、不靠运气。Pre-flight plugin-library check for DSH agents — task-type requests trigger a Top-K hint of suitable plugins injected into the runtime context, making plugin usage predictable instead of opportunistic.

Codex-native Claude review plugin for read-only, evidence-cited Opus review lanes.

MCP server that brings Perplexity to Claude Code — AI-powered web search, deep research, reasoning, and real-time citations. 9 tools: search, deep research, reasoning, raw search, Q&A, code review, brainstorming, explanations, and file analysis.

🏠 All-in-one lifestyle management WeChat Mini Program — 17 modules, local-first, dark mode, AI assistant

Production-ready MCP servers for GitHub, Bitbucket, GitLab & Jira - enabling AI assistants to interact with your dev platforms

支持 VRM/VRMA、语音状态联动与 MCP 控制的跨平台桌面虚拟角色｜中文界面与可配置动作库