Code agents

AUTO-S is a deployable, adaptive, and safety-aware AI system for Enterprise Terraform operations where Safety, Security and Scale matter most.

Standalone Pi coding harness with teams, chains, and safety controls

Local hostet LLM Agent/Chat/Autocomplete

Dineway is the skills for building agentic website for restaurants and local businesses. You don't need to write code. Just tell an AI agent your restaurant name and city, and it builds a professional website — with menus, blog, reviews, gallery, and local SEO — automatically.

Integrate the Assinafy API into your Python applications to manage electronic signatures, documents, and webhooks with a synchronous client.

🪐 10-agent WordPress Plugin QA team for Claude Code. 116 runtime-evergreen skills · CTO→PM→Dev→UAT→Security→Release · MCP discovery · Docker wp-env · WP.org zero-rejection · Brain-connected memory.

Blazing Fast Semantic Cache & API Optimizer for LLMs (OpenAI, Anthropic, Gemini)

An open-source, model-agnostic AI coding agent CLI — works with Google Gemini, Anthropic Claude, and any OpenAI-compatible provider

claude.ai chat in the terminal. vi keybinds, session management, file/skill attachments, command/file auto completions, & task handoff to claude code

The One Terminal you will need

Voice-driven desktop AI assistant for Windows: screen vision, app and system control, web search, reminders, and a phone remote. Built on the Gemini Live API.

Persistent memory and replanning for Claude Code. Checkpoints what Claude was doing and injects context at the start of the next session.

A full-stack AI assistant built with Flask, Groq, and Llama 3.3. Features real-time question answering, email summarization, responsive UI, and seamless API integration.

Local-first AI reading assistant for academic papers — Agentic RAG, citation tracing, Electron desktop app, fully offline

A working, tested memory engine for an AI chief of staff. Stage 1 of a staged public release.

🧠 弱智吧.Skill - AI弱智对话生成器 | 解压神器 | 搞笑AI工具 | Claude Code/OpenClaw/WorkBuddy Skill

Proactive AI Chief of Staff: A push-paradigm assistant that anticipates needs, filters noise, and manages your digital life through scheduled pulses and intelligent automation

Self-hosted, provider-agnostic personal AI assistant — Web UI, CLI & messaging bots with memory, multi-agent specialists, SOPs, scheduler & live dashboard. Defaults to Claude (Opus 4.8) on your Claude Max quota via Meridian — no per-token bills.

Turn vague customer questions into employee-reviewed, copy-ready replies. Includes workflow docs, prompts, schemas, and sanitized examples.

AI-enhanced enterprise school management system with OpenAI integration for automated student progress insights.

Capture and analyze Metal GPU frames from Unity on macOS — an Editor window + AI Assistant skill driving macOS 27 gpucapture/gpudebug (no Xcode): real GPU frame/pass timing, frame-budget gauge, GPU bottleneck classification, and deterministic Top-3 URP optimization insights.

Tiny local coding CLI

A Claude Code skill that acts as your personal code learning partner guiding you through programming problems using Socratic questioning and the 4Ds methodology, without ever just handing you the answer. Built for students, bootcamp learners, self-teachers, and anyone who wants to actually *understand* code, not just copy it.

Browse a curated directory of AI models, frameworks, and tools for modern development projects.

Syndrome AI — A desktop command center/GUI for Claude Code. Build custom AI agents, switch between cloud and local models in one click, track token costs live, and rewind any coding session. Local-first, no telemetry, open source.

A Retrieval-Augmented Generation (RAG) pipeline built with Python, Groq API, and BGE-M3 models to extract and answer questions directly from course materials.

Launch AI agents in a secure, disposable Linux runtime (Lima or Docker) — with one command.

Shoaku - Understanding-First Coding

A Windows WeChat chatbot powered by Gemini API, with wxauto/wxhook adapters, image input, group triggers, memory, and local knowledge base support.

🎨 Create stunning logos effortlessly with ai-logo-maker, your offline tool for designing unique identities while keeping your data secure and local.

Interactive career platform for students, employers, curators, and admins.

Memory that thinks. Local AI memory with hallucination firewall, 95% token savings, Cloudflare bypass, and P2P LAN bug sharing. 55+ tools. Zero cloud.

The Internship Matching System is a web-based platform designed to facilitate the process of internship placement for Data Science and Artificial Intelligence students. The goal of the system was to bridge the gap between students, companies, and academic supervisors by providing a centralized and organized environment for internship applications

A calm AI companion that quietly knows everything. Reads your mail, writes your morning, runs your terminal — and stays out of your way.

Local interview copilot web app and meeting overlay extension

A society of AI agents with impeccable standards and zero tolerance for 'fix stuff' commits.

A free AI assistant for real estate agents. Writes listings, ranks buyer fit, and builds defensible price bands — tuned to your local market in about 20 minutes. Three populated examples included: Jerusalem, Northern California, and Khao Lak.

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.

QuietPrompt is a local-first AI tool for coding. Capture screen text, voice, or typed prompts and run them offline with your LLM; no cloud 🐙

CAVRA - Controlled Agentic Verification & Runtime Authority. Before the agent acts, CAVRA decides. CAVRA is a runtime governance and authority layer for AI coding agents.

A self-hosted markdown blog system built with SvelteKit and Bun. Designed for personal writing, featuring an integrated DeepSeek AI assistant for seamless content editing and management.

Self-hosted AI personal assistant for businesses & freelancers — deploy a private, Claude-powered Telegram agent on your own Linux server in minutes. Host-isolated and fully yours.

Nexus: Autonomous AI agent platform combining OpenClaw's channel breadth with Hermes Agent's learning loop — plus graph memory, DID identity, privacy-as-config, and zero-API-key demo mode. Rust + Go.Please contribute to unlock the next era of agentic AI.

Lumi — an animated macOS desktop companion that fronts local coding agents (Codex, Claude Code) with streaming responses and human-in-the-loop approvals

A modern, feature-rich AI chat application powered by OpenRouter's API, providing access to hundreds of free AI models with an intuitive interface.

⚔️ Transform weak prompts into elite, production-ready prompts using NVIDIA Llama 3.1 70B. Built for Google Prompt Wars 2026. Features: 8 prompt engineering techniques, Power Level Meter (1-10), Warrior Rank System, typewriter animation. Powered by NVIDIA NIM API + Python Flask.

Stop re-explaining your project to your AI coding assistant. An open standard for project context in plain markdown, built on AGENTS.md. Tool-agnostic and free.

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

Telegram assistant for a small trusted circle — memory, routing, tools when needed (not Google Gemma)

The master context file for working with Claude. Drop it in your project root and Claude reads it on every session.

📊 Analyze and enhance GitHub repositories with a multi-agent system that delivers actionable recommendations for improving technical publications.

🏛️ AI-Powered Bid & Tender Management | 12-Step End-to-End Pipeline | World Bank·ADB·FIDIC·UNCITRAL·EU·US FAR | China + International Dual-Track | WuKong/Claude/OpenClaw Skill

AI pair-programming IDE for macOS — native SwiftUI app with a project-aware Claude Agent SDK runtime.

Scan and diagnose coding agent skills to find errors and improve quality with a clear scoring system and actionable feedback.

Telegram Business Save Mode & AI Assistant with local memory, deleted messages archive, edits history, reminders, summaries and Claude/OpenAI/Gemini support.

🚀 AI-powered Chrome Extension that generates context-aware LinkedIn comments using LangGraph multi-agent workflows, FastAPI, LangChain, and LLMGateway. Supports multiple comment tones, intelligent post analysis, and one-click comment insertion directly on LinkedIn.

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

CodeGraph fork with per-branch index management - instant branch switching without re-indexing | CodeGraph 分支版本，支持多分支索引管理 - 分支切换无需重新索引，秒级完成

🤖 Orchestrate AI agents at scale using the MCP framework, enabling seamless context sharing, communication, and integration for enhanced collaboration.

Per-project context file. One per project. Tells AI what each project is, where it's going, and what's happening right now.

VibeTools: a self-hosted developer toolbox that brings AI utilities and classic dev tools into one clean app

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.

Claude Code inside Unreal - the MCP layer Epic doesn't ship: real editor Python, viewport perception + scene diffing, one-command lighting moods, normal-aware spatial reasoning, and a lossless UE<->X3D round-trip harness. Honesty enforced by tests; coexists with Epic's Unreal MCP (UE 5.8). 58 tools, MIT.

A local UI for inspecting Claude Code session logs. Useful when developing subagents and skills

Image provenance for AI agents: the ChronoVerify MCP server. Verify a photo's capture time and provenance (C2PA validation, EXIF/XMP, pixel forensics). Tools: verify_image (typed verdict) and get_signed_report. Local via npx, or hosted at chronoverify.com/mcp/http.

Auto-trigger Webhook alerts (WeChat/Feishu/DingTalk) on stock profit/loss thresholds. A-share + HK unified. Bearer Token API for AI Agent integration. Zero-server, powered by Privora.

Persistent engineering context for AI coding agents. MCP server with auto-hydration on session start.

Chat with LLMs (Ollama, Claude, OpenAI, OpenRouter, DeepSeek, plus any OpenAI-compatible endpoint) inside Sublime Text 4. Secure external secrets storage for hosted providers.

MCP server for the Federal Reserve Economic Data (FRED) API. Covers the full API: series, categories, releases, sources, tags, and GeoFRED maps.

PACT is a runtime security layer for AI agents.

🔍 Enable real-time exploration of GitHub repositories with this high-performance Model Context Protocol (MCP) server built in Rust.

Ultra-fast codebase cartography for LLMs

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.

See what your AI coding agent actually did. Local audit of Claude Code session transcripts: leaked secrets, risky shell, unsafe edits, hook bypasses. Cursor + Windsurf adapters on the roadmap.

Deterministic code intelligence engine — compiler-grade symbol, call-graph, and CFG extraction from LLVM IR, Java bytecode, and tree-sitter. SQLiteGraph-backed graph store for grounded LLM coding workflows.

MCP server for PostEverywhere — let Claude Code, Claude Desktop, Cursor & other MCP clients schedule social media posts to Instagram, X, TikTok, LinkedIn, YouTube, Facebook, Threads

Software Developer at Cognizant | Full Stack Developer | DevOps & Cloud Enthusiast | Azure & AWS Certified | GenAI Explorer

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.

Navigation contract for AI coding agents in large repos. Templates, validation scripts, and a Python CLI for authoring three-layer context packs. Companion to the agent-recall research.

Remote MCP Server (WebMCP) for industrial vacuum exploration and configuration. 150+ products, ATEX, combustible dust, dust extraction and management, specific accessories, optionals. AI-native product explorer for any MCP-compatible client.

Cross-project second brain — typed-graph notes with hybrid retrieval and MCP integration for LLM agents

A local-first harness for testing and analysing LLM inference results.

Self-hosted SRE investigation copilot with LangGraph, YAML-defined SSH tools, SSE streaming, sanitization, and built-in secret redaction.

Computational verification of claims across chemistry, physics, math, statistics, code, biology, and governance. Four gates (RED → FLOOR → BROTHERS → GOD) enforce attestation and machine-checked verification independently — RED rejects on either. Built so an LLM can fact-check itself before answering.

토스증권 Open API(Toss Securities Open API)를 AI 에이전트가 쉽게 탐색·연동하도록 돕는 MCP 서버 (stdio). Claude·Cursor·Codex 지원.

MCP server for Grovs: manage deep links, attribution analytics, and campaigns from Claude Code, Cursor, Windsurf, and any MCP-compatible AI assistant. Open-source TypeScript, OAuth-based, no API keys required.

The agent-native document editor — docs, integrations, and agent skill files for Comment.io

🚀 Compress and decompress JSON with the ASON MCP server, maximizing efficiency through optimized token reduction for seamless data handling.

Fight AI context rot: keep Claude Code (and any LLM) sharp in long sessions with one living Checklist instead of lossy /compact summaries. Persistent working memory + context-window HUD + zero-keystroke auto-clear.

Spanish Codex skill for shorter answers, cleaner patches and token-efficient developer workflows.

simplr captures compiler build errors and explains them in plain English using local LLMs. Pipe your build output in, get the root cause, a suggested fix, and a list of other unrelated errors — no more digging through walls of template noise.

An MCP server that gives Claude Desktop structured access to your notes and past papers. Discovers topics, teaches in any style, quizzes you on grounded content, extracts PYQ patterns, and tracks mastery in local SQLite. Built with the official MCP Python SDK + FastMCP.

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

Local MCP server that turns Claude into a markets analyst over a live Wealthsimple portfolio. 28 skills, 107 tools, 15 data adapters, all free or free-tier data: no paid subscription, no API key. PII stays on your machine.

An MCP server that runs on a 1985 Apple II. Yes, that MCP. No, there was no reason to. Reads memory, writes memory, presses keys, all on hardware too old to understand why.

How I set up Claude Code workflows. A curated, source-attributed KB of patterns, updated when new ones land.

Karpathys Multiple languages guidelines