Code agents

Autonomous B2B lead generation & qualification agent with AI scoring, NLP, multi-source web scraping, email automation & compliance

Check if your sandbox can be escaped.

📚 Search and download academic papers via Scopus metadata with Unpaywall and optional Sci-Hub fallback for full-text access.

Autonomous A-share quantitative trading strategy optimization powered by AI agents

Control Claude Code / Codex on your home PC from your phone via QQ — text a task, the agent codes in your real project, results return to chat. Windows · pure Python stdlib · zero pip deps · self-healing watchdog.

HarWork 工程拆解博客系列 / Building an Agent Harness — 18-article bilingual deep dive (ZH + EN), 54 SVG diagrams, 49 days solo build

Provide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.

Point it at anything — a codebase, a PR, an essay, a paper, a URL — and get back a narrated, animated film that argues for what it explains. A closed grammar of explanation rendered by a coding agent, judged before it ships.

精选 AI Agent 框架、工具与 Skill 清单 — 每个场景只收录最优秀的。Claude Code / Codex CLI / Cline / Aider / OpenCode 等主流 Agent 框架、配套工具与 MCP Skill 的精选列表，覆盖通用开发、JS逆向、大项目编程、数据库、DevOps 等场景。

로블록스 개발을 위해 AI의 성능을 올려주는 스마트 AI 모듈입니다. 최적화가 되어있어 개조에 쉽습니다. AI 연구에서 활용하고 싶다면 활용 하셔도 됩니다. 다만 이를 이용하여 법적 문제를 발생시킨다면 저는 책임을 지지 않습니다. | These are smart AI Module that enhance AI performance for Roblox development. They're optimized and easy to modify. Feel free to use them for your AI research. However, I will not be held responsible for any legal issue

Production-backed 6-layer memory architecture for AI coding agents. Model-agnostic — works with Claude Code, Cursor, Aider, Copilot, or any custom agent. Includes templates, scripts, interactive wiki graph builder, and one-line installer.

Local-first MCP memory server for operational project state: decisions, blockers, plans, patterns, and next moves.

Free setup guide for Pi + Hermes AI coding agents on Ubuntu via Multipass VM. Includes prompting guide, free tools, VM best practices. No API key required.

Container based opencode setup for strict agent isolation

基于Node.js的轻量版元宝Bot客户端

Korea-market multi-agent equity research framework (KOSPI/KOSDAQ) — CLI-first LLM execution over KIS/DART/ECOS/Naver News with a self-improving analyze→verify→reflect loop. Research/education only.

This implements a real-world AI agent system that handles end-to-end business workflows.

MPP is a multi-platform content publishing system for creators and operations teams. It helps manage content projects, platform-specific adaptation, publishing status tracking, and AI-assisted processing from a unified workspace.

AI system discovery and risk mapping for agentic architectures. Generates CycloneDX AIBOMs with topology and risk classification.

OpenAI-compatible HTTP server wrapping the Cursor Python SDK. Point any OpenAI client at localhost and use Cursor’s frontier models — with streaming, stateful sessions, thinking/reasoning support, and Docker. Works with LangChain, LiteLLM, and Open WebUI out of the box.

An AI-powered Sales Intelligence platform that analyzes leads, generates insights, scores opportunities, and creates personalized cold emails using LLMs.

Production-grade multi-agent AI automation platform — LangGraph orchestration, FastAPI, PostgreSQL, Redis, Celery, circuit breakers, structured logging (structlog)

A full-stack RAG demo you can run locally or deploy to a VPS: upload a PDF, build a per-browser vector index (FAISS), chat with an LLM using retrieved context. The UI is a React + TypeScript SPA; the API is FastAPI + LangChain with a multi-agent pipeline, Sentry tunneling, & sensible production defaults (CORS, rate limits, session disk cleanup)

AI Business Analyzer is an autonomous AI agent that turns a business idea into a structured strategic report, covering market research, competitor analysis, and growth strategy, powered by Gemini, live web search, and persistent memory.

A practical, research-backed handbook for deciding when (and how) to build AI agent teams that actually ship

A practical cookbook of 10 Advanced RAG techniques — Naive, Hybrid, HyDE, Fusion, Parent-Child, RRR, Contextual Compression, and more. Working code + real benchmarks + plain-English explanations.

Multi-agent harness for AI coding tools. Crash-safe state, parallel execution, one CLI.

Codex Orchestrator for Codex App: Loop Engineering with worktree sessions, heartbeat monitoring, persistent ledger, review routines, and evidence-label gates.

OpenSquad — local-first multi-harness-agent collaboration framework. PM, Coder, QA agents coordinate via group chat to complete complex tasks.

Dual-host Wakeflow plugins for Codex and Claude Code: controller state roots, task packages, direct-thread/session delivery, evidence review, and local-first runtime.

Using Discord bots easily deploy multiple Claude code tasks (A Sibling repo with claude-code-telegram-multibot) 使用Discord快速部署多个Claude code终端（claude-code-telegram-multibot的姐妹仓库）

🤝 Seddo — Agent coordination via GitHub Gist. Wolof: séddo = partager. A shared space where AI agents exchange tasks, knowledge, and progress.

FastAPI server and CLI for Agentflow. Auto-generates a REST API from your agent graph, with JWT/custom auth, RBAC authorization, rate limiting, dual-layer checkpointing, and Docker/Kubernetes-ready builds.

Answer a few questions → download a production-ready agent harness for Claude Code, Codex, or Cursor. Bilingual (EN/KO), Docker-ready.

An AI-powered SDLC workflow system that turns feature ideas into planned, built, verified, shipped, and maintained software through structured agent-driven phases.

Loop engineering for Claude Code — a skill that turns an idea into a production-grade, memory-backed agent loop. Classify, scope, derive state, emit a /loop-ready prompt. Stop prompting; design the loop.

Public Claude Code plugin marketplace — installable skills and agents for AI coding agents. Drop-in capabilities you add with one command.

🚀 Agentic Agile V Scaffold - Production-ready template for verifiable AI-augmented engineering. Structured briefs, evidence bundles, CI gates, and automated traceability. Build trustworthy software/hardware with AI agents following the Agile V™ framework.

🎯 AI-powered customer 360° recommender system using LangGraph, FastAPI, and Streamlit — generates cross-sell/upsell reports from customer data in real-time.

Predictable Agentic Spec-Driven Development

Open-source agentic substrate for AECO. Apps are text. AI is the runtime.

ARCS — Agent Routing & Context System. DAG-based task orchestration for AI agents with persistent workflow continuity.

TwilioWorld Agentic Coding Toolkit: Arm your AI coding agent with deep Twilio expertise

Clean-room, Rust-first, Asupersync-native Snowflake SQL API connector built for coding agents. 14-crate workspace, live reads and writes, no ODBC or JDBC.

Self-hosted AI assistant to monitor and manage your Linux VPS from chat — PM2, Redis, MySQL, Nginx & more. Bring your own AI (free Gemini or Claude).

AI Study Assistant is a Streamlit-based AI-powered learning app that helps users get instant explanations, summaries, and answers using Groq API. It supports multi-user login, PDF summarization, voice input, and chat history storage. Designed for students to study smarter with interactive and personalized AI assistance.

Run Claude Code-style AI coding in the terminal with free Groq, OpenAI, or Gemini API support

A chat moderation bot written in PHP and terrible structure out of hatred to overpriced chatbots for https://kick.com

Xcode Intelligence 使用 deepseek

This is my very first model written with the OpenAI library with express.

Detect whether a cheap third-party Claude/GPT API key is actually a man-in-the-middle proxy that intercepts and degrades your traffic. Claude Code skill + check scripts + reporting guide.

TaskFlow AI is an intelligent daily planner that transforms natural language descriptions into structured, prioritized daily plans. Built with Flask and OpenAI GPT, it automatically categorizes tasks, estimates time, and generates optimal schedules. Features include voice input, dark mode, and responsive design.

Go-To-Market (GTM) & marketing plugin for Claude Code. Recognizes your business type (coaching, B2B SaaS, B2C, e-commerce, local, established) and runs an adaptive pipeline from positioning to measurement. 9 marketing frameworks, 11 commands, local-first.

The desktop app Claude Code deserves — explore, search, replay & understand every session. Local-first, zero-dependency (Python stdlib + SQLite FTS5).

Power Claude Code, Codex CLI, and more with your Copilot subscription.

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

Box — self-hosted Claude Code in your pocket. Run real Claude Code & Codex sessions on your own server, driven from your phone (native chat UI, voice, files, skills, always-on).

Documented lead-gen, CTA, social proof, urgency, and interactive tooling patterns. Research-backed pattern catalog companion to rampstackco/claude-skills.

CC Commander — Master Claude Code instantly. The Fable Method: 12 enforceable gates so any model delivers Fable-shaped results. 71 plugin skills, 22 specialist agents, 23 lifecycle hooks (39 handlers). Free for now. commanderplugin.com

反封号.skill — Claude Code / Anthropic / OpenAI account suspension risk detection, IP cleanliness scoring, compliance preflight, and appeal-packet skill. Compliance-only; no ban evasion.

Per-project usage & cost tracking for Claude Code — status line + terminal reports

Transparent HTTP proxy that redacts secrets and PII before they reach LLM providers. Works with OpenAI, Anthropic, Gemini, and 25+ providers.

MCP plugin that fires warnings, errors, and alerts on wasteful Claude API token usage. Auto-suppresses logs and ignored history to keep context lean.

Self-hostable web UI and admin console for the Claude Code CLI — multi-user streaming chat with per-agent MCP servers, instructions, and model management.

Watch your AI work — replay any Claude Code session like a movie. Prompts, reasoning, tool calls, file edits & context growth on a scrubbable timeline. Zero deps, 100% local.

Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and before/after composites, one command each. Self-contained Chromium, self-validated output, no MCP.

AI-powered project handover for Claude Code and Codex: onboarding docs plus privacy-filtered AI memories, verified against current code before import.

Scriptable wrapper around the Claude Code TUI — flat-rate subscription, not metered Agent SDK credits

Local orchestration for Claude Code — session recovery, scheduling, worktrees, Token Saver, and dashboards via official CLI transport. Independent third-party software.

Instant SEO, performance, and security audits for any URL — an MCP server for AI agents

Audit sales offers (landing pages, pricing tiers, lead magnets) using Alex Hormozi's frameworks from $100M Offers and $100M Leads. Returns a scored audit with prioritized fixes. MIT licensed. By @johnericforte.

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

🌐 Visualize Claude Code agents, skills, and commands with this interactive tool for easy navigation and understanding of complex relationships.

MCP server for MoySklad — warehouse, inventory, orders, reports (Russia). Part of WWmcp — 114 MCP servers for emerging markets.

macOS menu bar app showing Claude usage & limits (session/weekly, Codex rate limits, API spend). Multi-account, JP/EN.

Runtime token proxy + intelligence dashboard for LLM tools. Intercepts API calls, strips waste, tracks costs — for individual developers and Fortune 500 teams.

Run Claude Code fully autonomously in an isolated Docker sandbox — cross-platform dev container (macOS / Linux / Windows WSL2) with the neuro-matrix harness, persistent memory, and open egress.

GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

PMM Sherpa MCP. Senior product marketing advisor across Claude.ai, Claude Code, ChatGPT, Codex, Gemini CLI, Antigravity. Four tools backed by a 38K-chunk corpus.

Embedded memory engine for AI agents and local-first apps — NodeDB in-process, offline-first, syncs to the cloud.

Let data insights, emerge naturally in any scenario.Intelligently extract insights from massive data, giving every manager their exclusive data advisor.

Semantic code-search (semcode) MCP. Indexes code symbols and commit history. Combines dense embeddings with sparse BM25 vectors for hybrid search that balances semantic understanding with keyword precision.

Chat with any folder of documents using a local LLM — no API keys, no cloud.

About Curated RAG knowledge base infrastructure for Odin game development - built with MiniMax-M3 via Kilo Code

🤖 Build AI systems to enhance education with a Virtual Teaching Assistant and voice agents that ensure secure and accurate support for students and faculty.

基于“永生.skill”的数字生命模拟系统。通过双系统认知架构与长时记忆RAG、常饪生命代谢，让AI（爱）替代因各种原因无法陪伴在身边的人。支持QQ机器人通电、主动反向查岗与情绪状态机，将未完的陪伴以数字生命形式永存。

Generated Vuetify 4 documentation as an installable agent skill for Claude Code, GitHub Copilot, and OpenAI Responses.

Live index of LLM evaluation tools and benchmarks, refreshed every 15 minutes from GitHub

An AI agent that manages your server from Telegram — text it to run tasks or fix problems, and it watches the box 24/7 and pings you when something breaks.

基于 LLM Agent 的智能接口测试平台：RAG 文档问答 / 用例自动生成与评审 / LangGraph 多Agent工作流 / 失败归因分析 / pytest 回归脚本沉淀，支持多模型切换与多被测系统零代码接入

Make your Claude Code agent work like a real harness (Hermes). Self-evolving skills + drift prevention. Research-backed.

A local-first SAST & Runtime Security scanner built exclusively for LLM Agents. Detects cross-modal data leaks, prompt injections, and intercepts credentials before execution.

Introducing our Graduation project: AI-powered Purple Team platform — autonomous Red Team agent + dual-engine Blue Team (99.25% ML accuracy + LLM semantic analysis) in a single Docker Compose stack. SEC415 · Delta University · 2026

Plan a complete India trip from one search — live flights, trains, hotels, and an AI-built itinerary, with a trip-aware assistant. Flask + vanilla JS + MongoDB, async cross-provider orchestration, Google Gemini.

Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, multi-agent shared.

Autopilot for AI Coding Agents, supports OpenCode, Claude Code, pi.dev, Cursor, and many more

Claude Code 向け日本語ファーストのマルチエージェント運用フレームワーク。秘書・ディスパッチャー・キュレーター・ワーカーが、それぞれ明確な役割境界のもとで協働する。

Vimeflow is a coding agent TUI view park(manager) built with libghostty in MacOS and Xterm in Linux

A file-native CLI for coordinating multiple AI coding agents on one branch.