Code agents

Goal-driven Codex learning workspace with evidence-gated progress, reusable learning artifacts, trusted sources, and stage reviews.

The official Node.js SDK for Known Agents: AI agent analytics (bot traffic), LLM referral tracking, automatic robots.txt

Demo of a Fiber Cut Response Agent using Azure Content Understanding to process multi-modal field documents (PDFs, photos, diagrams, audio) and reason with Foundry models for incident triage. From Microsoft Build 2026.

Security-hardened GitHub repository template, designed to prevent supply-chain attacks. Includes vulnerability scanning and AI agent skills.

Complete AI agent collection for accelerating SaaS development - from MVP to scale

Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.

Oprina is an AI-powered conversational agent with real-time avatar streaming, featuring multimodal Gemini 2.0 Flash integration, Gmail/Calendar automation, voice controls, and enterprise-grade deployment on Google Cloud Vertex AI.

AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, and safety gates. TypeScript. Zero config.

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

AAPP-MART is a cybersecurity engine featuring AI-powered autonomous attack path prediction and multi-agent red team simulation. These features include adversary emulation, attack path analysis, threat modeling, security validation, risk assessment, and MITRE ATT&CK alignment.

First Try Works — vibecoding takes 47 tries, FTW takes one. Multi-agent validation workflow for Claude Code and OpenClaw.

Desktop multi-agent orchestrator for the Claude Agent SDK. Command a hierarchy of AI agents — chiefs, specialists, advisors, workers — with CodeGraph code intelligence, Claude-Code-grade context compaction and per-agent cost tracking. Open-source agentic AI / Claude orchestration.

An open-source agentic harness for scientific literature analysis. Coordinates frontier models to extract data, replicate findings, and perform systematic reviews with full provenance tracking.

AI-agent orchestration CLI for governed autonomy — drives your backlog to shipped PRs, with a policy gate (AGENTOWNERS-style) on every change.

⚡ Open source WhatsApp bot framework with 170+ commands, 20+ mini-games, economy system, AI auto-reply, downloaders, and auto-moderation.

Educational AI chatbot project for Aparsoft interns, built with Django 6+ & Next.js 16+. Learn RAG (Retrieval-Augmented Generation), LangChain/LangGraph, Celery, PostgreSQL with pgvector, and Redis. Complete Docker setup for easy development.

Code review, but with 5 models arguing first.

Open-source security intelligence engine for developers. Orchestrates nmap, nikto, semgrep, whatweb, trivy, cortex-crawler & curl. Builds attack graphs, narrates risk, and generates fixes. Runs fully locally, without any cost

Self-hosted, secured HTTP API around headless Claude Code — per-app keys, all tools locked off, zero deps. Use Claude from your own apps.

Hot-hatch turboquant powered whybrid vector + BM25 search for PostgreSQL on top of pgvector

AI-Powered Bug Diagnosis Agent with Experiential Memory — the more bugs it sees, the faster it gets.

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

🎭 AI角色蒸馏工厂 · Character Distillation Factory — 将公众人物炼成 Claude Code 智能体。Distill public figures into conversational AI agents. 收录: 张雪峰, Seto Kanna.

IRIS-Zero ⚡ — A private local-first AI terminal that listens 🎧, thinks 🧠, and executes on your machine in real time. Run commands ⚙️, manage projects 📁, and automate your workflow with zero APIs, zero telemetry, and full device-side intelligence 🔐.

Hands-on AI agent security resource: OWASP GenAI attack/fix/verify demos on a LangChain IT-helpdesk agent, deployed to the cloud.

Multi-agent AI runtime with OS-inspired primitives — job scheduling, DAG orchestration, memory, tool execution and real-time observability. Built with FastAPI, Celery, PostgreSQL and LiteLLM.

Amadeus-AI is python framework for autonomous AI agents with planning, execution graphs, and plugins.

a vendor-neutral runtime protocol for autonomous AI coding agents persistent memory, execution loops, verification, events, and handoffs inside your repo.

An artificial presence that lives on your machine. Permanently. Voice-native, sees your screen, remembers everything, controls your OS. Minimal cloud. No restrictions.

A candidate-side applicant tracking system. Three-stage local AI pipeline that scrapes job listings, filters them against your profile, researches the companies behind them, and drafts personalized outreach

Cross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot, Codex, OpenCode & 45+ AI coding agents. Safety scanner, content-hash drift detection. A package manager / dotfiles for AI coding agent skills.

Codebase for Hidden in memory: Sleeper memory poisoning in LLM agents

Python Web Security: OWASP Top 10 with Agentic AI Course

Design-first agentic systems in Go: declare agents, tools, MCP servers, policies, and structured model output in Goa, then generate the durable runtime.

Kaparthy Style LLM Wiki

A hyper-optimized, local RAG system built on Streamlit using Google's TurboQuant algorithm and Turbovec vector index for 4 GB RAM setups.

AI-assisted local-first reference prototypes for governed AI application controls, using fictional data and explicit evidence boundaries.

LynxMCP: local MCP server for the code questions grep can't answer. Call graph and blast radius, hybrid semantic + lexical code search on ONNX Runtime, library docs and PDFs as sources. No cloud, no PyTorch.

Agent Skills that help AI coding assistants build on Powabase — the AI Backend-as-a-Service (RAG, agents, orchestration, workflows) plus a Supabase-style BaaS layer.

Modern TypeScript patterns. Strict mode, discriminated unions, satisfies operator, const assertions.

A tiny, dependency-free Ralph-loop agent harness for small local models (VibeThinker-3B via Ollama).

MCP server for AI agents to record browser demos with animated cursor, auto-generated video, screenshots, and documentation

A 9-step pre-mortem skill that interrogates you before you build. Grounded in 《置身钉内》(DingTalk ONE post-mortem). Works with Claude Code, Hermes Agent, and any markdown-skill agent.

Free-first, model-adaptive coding agent runtime that makes local small LLMs work reliably with harness, checkpointing, verification, cache-aware context, and free-model fallback.

Jawcode (jwc) — coding-agent runner with IPABCD workflow. 46 providers, 3,600+ models, Bun-native.

Autonomous multi-agent parametric design + CFD optimization using free local LLMs (Ollama), CadQuery, and OpenFOAM. $0 API cost.

Autobots | A decentralized model agentic swarm powered by NVIDIA NIM. Orchestrating high-precision, end-to-end authenticated software development through a specialized 6-file control architecture. Features automated security auditing, non-redundant task routing, and autonomous state management.

Oh! My Agent Teams - VALP protocol for visible, evidence-backed multi-agent work.

Open-source coordination engine for AI agents, over MCP. Atomic claims, shared ledger, leases, presence, handoffs, tasks. Self-host it or use the hosted service at llm-bus.com.

Bring Fable-style design taste to any AI coding agent. Free MIT design system for Claude, Opus 4.8, Codex, Cursor, Gemini & Antigravity. By Dr. Antoniou, free from UploadCheck.

Agent Skills for BESSER — deep BESSER knowledge for AI coding agents: UML class modeling, code generators, troubleshooting, and contributor workflows.

Multi-account tool broker for AI agents — use tools on demand from the CLI or connect through MCP, with credentials kept local.

AI-powered Fortune 500 business operating system for Claude Code — 15 executive agents, governed initiative lifecycle, Decision Authority Matrix, and 17 slash-command workflows.

AI-901 (Azure AI Fundamentals) study buddy built natively for Claude Code: exam-realistic questions, Microsoft Foundry labs, and study plans, grounded in Microsoft Learn via MCP, with subagents, skills, slash commands, and deterministic hook guardrails.

Build an AI advisor SKILL from any YouTube channel — transcripts, BM25 + semantic RAG, verbatim quotes with timestamps.

You say the job; the playbook runs. 143 agent skills + 55 commands for Cursor, Claude Code, Codex, Gemini. React / Next.js / Supabase.

The official Decodo web scraper CLI for terminal web scraping and AI agent workflows.

AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库：选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿，30 个 skills 拆到步骤颗粒度，单个可独立运行、可自由组合（Claude Code / Codex）

MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.

Motion forensics for the animated web. A Claude Code & Codex plugin that reverse-engineers a live URL into React + Tailwind — pulling real CSS + animation params from JS bundles (GSAP/Framer Motion/Webflow IX2) and verifying with AE/SSIM diff, not screenshots.

Local-first codebase knowledge-graph MCP server for AI agents (Claude Code, Cursor, Codex). Symbol graph over MCP so agents stop wasting tokens re-scanning files. Watch-first · 21 languages · faster, leaner & more accurate than the incumbent.

A principal-level, 16-division multi-agent Council for Claude Code. Drop-in ~/.claude/ config: 15 Floor + 160 Library rules, 121 skills, 32 agents, 33 commands, 14 hook-enforced quality gates. Runs on any machine, any project, every IDE. MIT.

AI Testing Agent Framework · 16 experts + 32 skills + 49 utils · Multi-LLM (Claude/OpenAI/Qwen/etc) · MCP-native · Open-source · Learn-while-using

Multi-agent orchestration system for OpenCode

Context Architecture is a software architecture for the age of AI agents: it structures a repository so that everything it claims about itself, its structure, its behavior, and who can change it, is legible to the agent writing the code and to the people who answer for it, and bound to a mechanism that fails when that claim stops being true.

Fast, model-agnostic AI coding harness and CLI in Rust — routes every task to the optimal model for cost × capability.

Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes specialized plugins, installer CLI, bundles, workflows, and official/community skill collections.

Persistent, self-updating memory for AI coding agents (Claude Code, Codex, Cursor, Gemini, Kiro, Hermes). Built on mcp-memory-service: a post-session distillation hook, a retrieval skill, optional Cloudflare multi-device sync, multi-user mode (private + shared memory on one shared account), and an interactive install wizard.

🔌 Hermes plugin for spawning AgentPlane as an external worker lane.

Experimental local-first memory CLI for MCP agents: read-only Gmail, calendars, iMessage, and files → cited local context

A governed, auditable workflow engine for an agent-driven software factory.

Multi-agent CodeQL vulnerability analysis pipeline for CVE research, source/sink tracing, query generation, and path selection.

High-performance async Python client for the private DeepSeek API

让 Claude Code 用 ChatGPT/Codex 订阅额度调内置 GPT Image 2 出图——不用 OPENAI_API_KEY、不计 API 费用 · A Claude Code skill: generate images on your ChatGPT/Codex subscription quota, no API key, no API billing

A Codex proxy with credential pooling and token refresh, deployable on Vercel.

免电脑 | 一条命令在安卓手机运行Claude Code AI Agent | 接入微信 | DeepSeek平替

AI-powered Bilibili video Q&A agent — ask anything about any video in the comment section. 在 B 站评论区 @机器人，即可对任意视频提问。

Infinite canvas for Claude Code & AI coding agents. Run claude, codex, gemini & opencode in parallel across git worktrees + remote SSH, with a markdown Kanban board agents read & update over MCP. Local-first, open source.

FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents

🛡️ Security scanner for MCP (Model Context Protocol) servers — prompt injection, credential exposure, SSRF, tool poisoning & source-level credential-handling flaws. pip install mcp-safeguard

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

An AI-powered store assistant built with Python, Flask, and Groq.

The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.

Local-first semantic search for your ChatGPT, Claude, and AI conversation history. Python CLI + MCP server for Claude Desktop. Uses sentence-transformers + ChromaDB. No API keys, nothing leaves your machine. Part of the Resonant ecosystem.

chad: a local Claude-Code-style coding agent for your laptop

Compile any Claude Agent Skill into a multi-agent Workflow — a meta-workflow that recovers the parallelism hidden in a skill's prose and emits a fan-out · pipeline · adversarially-verified Workflow.

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.

Local voice-driven AI operator (JARVIS) for Linux & Windows — Claude Pro / OpenRouter / Ollama, wake word, piper TTS, Iron Man-style HUD, Hyprland integration, WhatsApp & Telegram, Agentic Task Engine with live progress tracking.

Open-source agent OS for Claude Code that puts you in Builder Mode — and keeps you there for the whole life of a product. Claude Code setup that builds, launches, and learns. Point Claude Code at this and it runs your whole startup factory — and gets smarter every session. Works with Cursor, Codex & Windsurf too.

🪄 A terminal AI coding agent — BYOK, 12 providers, MCP, and a second-brain that gives the AI durable cross-session memory. Built from scratch in TypeScript.

A protocol for agent work that survives session boundaries — plan, implement, verify in sealed contexts, with proof bundles as the only currency between them.

gradio region:us

gradio region:us

transformers pytorch xverse text-generation custom_code arxiv:2009.03300

gguf text-generation en dataset:cerebras/SlimPajama-627B dataset:bigcode/starcoderdata dataset:OpenAssistant/oasst_top1_2023-08-25

gguf code codeqwen chat qwen qwen-coder

gguf quantized GGUF quantization imat imatrix

transformers gguf mistral quantized 2-bit 3-bit

gguf gemma4 coding code reasoning thinking

gguf text-generation license:other endpoints_compatible region:us imatrix