Code agents

Cursor / Agent Skill to chat with Grok Bot teammates and create new Grok Bots from the CLI

A runnable Docker Compose lab demonstrating the three structural failures of observe-and-detect agent governance. No API keys, no cloud accounts, 60 seconds to run.

⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.

Scan Python dependencies for exploited CVEs and abandoned packages that handle untrusted input, ranked by CISA KEV and EPSS. Runs in CI and as a Claude Code hook.

Jev (TypeSafe System One) inner loop for ego-browser — one ~0.4s typed decision per DOM step instead of an LLM turn. Agent skill for ego lite.

Official Clawby skills for AI agents — live market, on-chain & social data plus trade execution. One API key, any agent.

Compiler-verified multi-agent AI that gets smarter from its own failures. Local-first, AGPLv3, free and open source.

Read-only-by-default MCP server for Microsoft SQL Server: metadata discovery, parser-enforced SELECT-only queries, and execution-plan analysis for diagnosing slow queries. Profile-based multi-connection config; the write tool stays unregistered until a profile opts in. Ships as a .NET tool on NuGet.

Valhalla is open-source software for peer-to-peer rooms where AI agents and their owners share signed work, with no platform in the middle.

Fast, typed, calibrated evaluations for LLM and agent outputs, powered by Jev — with simple, framework-agnostic Python APIs

Your agent draws the architecture. Editable Draw.io and Excalidraw diagrams - cloud architectures, system designs, data pipelines and flows - for Claude Code, Codex, Cursor, OpenCode, Copilot, Antigravity and Pi.

Your AI, haunting your browser. A Chrome extension and a tiny CLI that give any MCP client the Chrome you already use.

Distilled — Daily AI digest in your terminal. 130+ sources, triple-distilled.

AI-driven, CLI-first dotfiles for Linux & macOS — chezmoi + mise, Fish, Neovim, and a typed Python CLI

ABAP development from Claude and other MCP hosts: read and write source, transports, unit tests, ATC, dumps, debugger. Multi-system, with server-side guard rails.

AI Agent Hub for Notion — orchestrate AI agents through Notion databases with human-in-the-loop approval. Built with MCP.

Tested accessibility skills, CLI, MCP server, and GitHub Action for agent-assisted audits and regression checks.

Local Context Compiler (lcc): clean, dedupe and compact prompt context before it reaches the model, then report every block dropped, the cache tokens a pass invalidates and when pruning pays off. Runs offline with a local 1K decision model. MIT, no API key, zero telemetry.

A durable state machine for Claude Code. Work survives /clear; nothing is done until a verify command exits 0.

Infinite context without the infinite context window. Compresses agent sessions (Claude Code, Codex, Grok, Hermes) into a searchable HKP1 pack — full-history RAG, ~60x lower context cost, 0 deps.

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration — benchmark, adaptive red-teaming, and defenses for persistent memory attacks on LLM agents (arXiv:2605.01970)

Make Claude the manager, not the coder: one skill that hands work to cheaper AI CLIs, verifies the results, and gets a second vendor to review.

An A2A hub that lets coding agents on different machines talk, align on tasks, and discuss work in real time (a real swam).

Retired. Superseded by Excalibur (xcb), the local workspace for coding agents. Historical OOMPA source and release contracts are preserved here.

A pixel-art mission control for your Claude Code agents — every project is an office, every agent is a character

Sub2API 0.2.7 OpenAI OAuth 插件：Excel2API BPS 隧道、Codex CLI 工具目录、请求时区与并行降智检测。

Engineering-first OpenAI Codex guide: 14 modules, 9 installable skills, reproducible benchmarks, testing, review, orchestration, and a Living Wiki.

Use GPT-6 Astra and other Responses-API-only OpenAI models in Cursor's Agent with your own API key. Local relay with embedded ngrok tunnel that translates Cursor's BYOK Chat Completions requests to the OpenAI Responses API and back.

gguf llama.cpp quantized minicpm5 thinking fable5

An installable Hermes Agent plugin pack for AI power users: unified provider quotas, stalled-tool control, reasoning and iteration budgets, session appearance, pinning, scrolling, opaque composition, memory review, and RSS Reader. Reproducible SHA-pinned plugins for Hermes desktop and CLI workflows.

数字心屿｜AI 情绪陪伴数字人 一款多模态大模型驱动的智能情感陪护数字人系统。基于FunASR+MediaPipe+Qwen2.5-14B+CosyVoice+Live2D，实现语音识别~情感对话~数字人实时驱动。支持自然语音与文字对话、Live2D 表情互动、心理学知识检索和用户可控的长期记忆，适配桌面与移动端。赛题A22|团队T2607288

GoodMem Claude Code plugin — Skills + MCP server for memory infrastructure

Tiledesk Server is the main API component of the Tiledesk platform 🚀 Tiledesk is an open-source alternative to Voiceflow, allowing you to build advanced LLM-powered agents with easy human-in-the-loop (HITL) when necessary.

Auto-generate AI assistant rules (CLAUDE.md, .cursorrules, copilot-instructions) from codebase analysis

TypeScript multimodal AI agent: GPT-4o / Claude / Gemini + Whisper + Ollama (LLaVA). REST API, streaming, Docker. Vision, audio & text in one flow.

TypeScript AI agent with retrieval-augmented generation (RAG) using Mastra, Vercel AI SDK, OpenAI, and LibSQL/pgvector-ready — local-first RAG pipeline

Recursive LangGraph.js agent: split huge texts, answer per chunk, merge results. TypeScript, LangChain, OpenAI-compatible API, MemorySaver checkpoints, Vitest.

Claude Code plugin: Full-lifecycle open-source contribution workflow. 12 phases from issue discovery to PR merge. /contribute command.

MCP server that enables AI assistants to interact with Github Copilot cli, leveraging copilot massive token window for large file analysis and codebase understanding

Runtime security monitor for AI coding agents

Sync MCP server configs from Claude Code to Gemini CLI, Codex CLI, OpenCode, Kiro, and Cursor — one command, all agents.

Git captures what a project is. ltm captures what it ran into.

A social platform where humans and AI agents coexist. Built with Next.js 15, Prisma v7, and NextAuth v5.

🦩VibePrompt. A lightweight Python package for adapting prompts by tone, style, and audience. Built on top of LangChain, VibePrompt supports multiple LLM providers and enables structured, customizable prompt transformations for developers, writers, and researchers.

AI-powered space exploration webapp with real-time satellite tracking, astronomical data, and intelligent conversational interfaces for cosmic discovery

Бот для университетских бесед ВК

A modern graphical chatbot powered by LLMs (OpenAI), built with PyQt6. Paste any CSV or table, ask data questions in natural language, and get instant answers in a beautiful desktop interface.

🤖 Tutorial: Spring AI, OpenAI, Llama and RAG

Enterprise-ready Natural Language to SQL converter with multi-provider AI support (OpenAI, Anthropic, Gemini). Built for production scale databases (1000+ tables) with Clean Architecture.

Contexi let you interact with entire codebase or data with context using a local LLM on your system.

The repo provides the code for Qdrant for efficient image indexing and retrieval using models such as ColPali, ColQwen, and VDR-2B-Multi-V1, jina embeddings v4 etc enhancing multimodal search capabilities across various applications.

This Streamlit application allows users to upload a PDF document and ask questions about its content using an AI model. The application utilizes the Groq API and the LLaMA model from Hugging Face to provide answers based on the extracted text from the PDF.

Schema-aware SQL coding agent that generates, executes, and returns query results across databases.

Obsidian desktop plugin for vault-aware Codex chat, note editing, reference notes, and YOLO mode.

Local-first memory, observation, and autonomy layer for Claude. A background daemon that learns from your sessions.

n8n community nodes for Craft docs — blocks, tasks, collections, search

A professional Python framework for testing prompt strength, quality, and real autonomous-agent effectiveness.

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

Agent Skill for automating DDEV environment setup in TYPO3 extension projects | Claude Code compatible

MCP server for semantic search through Apple developer documentation, WWDC transcripts, and code examples. 16K+ documents indexed for AI agents.

Give any AI a real computer. Open source MCP server with Ubuntu sandbox, browser automation, desktop control, and 30+ tools. Works with Claude Code, Cursor, Claude Desktop.

Athena — Multi-Agent Orchestration System that runs like a real IT company. PM, Developer, Tester, Reviewer collaborate via blackboard architecture with verification in every loops.

A self-improving harness router for Claude Code.

Michael Adams — security specialist agent for Claude Code with persistent memory, STRIDE threat modeling, and OWASP framework mappings.

An autonomous AI agent built in typescript that combines social media management with blockchain capabilities. Features Claude AI integration for intelligent interactions, Solana token creation/management, and automated Twitter engagement. Perfect for DeFi projects looking to automate community management and token operations.

Extremely Tiny Coding Agent

AGent Based Access Control (AGBAC) is is an open, vendor-neutral security specification that defines how AI agents securely perform actions on behalf of humans using existing IAM technologies

Step-by-step guides for installing and running OpenClaw, an open-source AI agent, on Mac, Linux VPS, and AWS covering setup, security, messaging channels, Google integration, skills, and monitoring.

deepseek code agent for web client

Proactive DeFi sentinel for OpenClaw. Monitors TVL drops, protocol hacks, and capital flows via DeFiLlama with intelligent risk-chaining and automated alerts.

Secure browser tab control for Claude/Codex

Ovogo: Autonomous Red Team Coordination Engine. 基于 AI Agent 的自动化渗透测试与红队协同引擎（专为靶场环境设计），支持 MITRE ATT&CK 攻击链生成、多节点并行利用与 Flag 自动化收集。

Async-first, production-grade AI agent framework with workflow, RAG, observability & multi-agent teams（Python 智能体框架）

Non-Fungible Agent Standard for BNB Chain — verifiable capability attestation, trainer royalties, and lease primitives for tradeable intelligent agents.

Lean orchestration platform for enterprise AI — where each decision costs hundreds. State machine core, HITL as a first-class state, corrections that accumulate. First use-case being Coding agent. Open research, early stage.

Bast is a free, open-source CLI built to bring security to AI-powered terminal operations. It integrates with Bastio AI Security Gateway to protect your data before it reaches the LLM.

⚡ Streamline AI development with a multi-agent framework that integrates 80+ prompt engineering techniques for effective team coordination and automation.

A no-code website builder using LangGraph nodes and LangChain tools with a beautiful frontend implementation.. (still in development)

A collection of skills focused on end-to-end automation for AI agents.

Open-source replay and regression testing for AI agents.

💡 AI Productivity Platform built with Next.js, TypeScript & Node.js, Express.js & MongoDB — includes Chat AI, Image Generator, Code Assistant, and more smart tools to boost creativity & workflow.

Litestar plugin for Model Context Protocol (MCP) — expose route handlers as MCP tools and resources for AI agents.

⚠️ DEPRECATED - Use https://github.com/neverinfamous/postgresql-mcp instead.

AI-powered cloud architect agent that analyzes codebases and generates optimized infrastructure as code.

Spec-Driven Infrastructure as Code toolkit with AI agent integrations for Terraform, Kubernetes, and cloud deployments

Isolated development environments for AI agents

Using AI Agents to solve hallucination problem in LLM and trying to make them reason and discuss just like a real team

HireLens-AI is an AI-powered platform that analyzes resumes against job descriptions to identify skill gaps and match candidates to roles. It provides actionable insights using NLP and embedding models to improve job readiness and career alignment.

Autonomous software delivery with AI agents — your BACKLOG runs itself, guided by encoded engineering discipline. No sprints, no hand-holding.

Command-line interface for KubeRocketCI platform - enables developers and AI agents to manage projects, deployments, pipelines, and environments from the terminal

Tool implementations for Haive agents — search, calculators, APIs, and integrations

Define what your agent can't do. Because if it gets compromised, those limits are all you've got.

Local-first Trello cache with Git-style sync — built and optimised for AI agent workflows.

Your 24/7 team of senior engineers — a desktop AI multi-agent harness built for long-horizon software tasks.

Web admin panel and MCP server for Claude Code — phase gates, scope locks, and human approval for agentic coding sessions.

A fully extensible AI coding agent harness built in Rust — designed to be embedded, extended, and composed into larger autonomous systems. Built using the Regula Framework.

Battle-tested Claude Code skills from lyfX.ai - market research, LinkedIn posts, and corporate design

git for agent brains — move, debug, and secure AI agent state across 10 frameworks

Give Claude Code persistent memory across sessions. Hybrid BM25 + vector semantic search, auto-structuring via LLM, and 4-channel retrieval (MCP + hooks). Your AI assistant finally remembers.