Code agents

AI-generated animated explanations of code — paste any function, get a cinematic animation of what it does

No Termux required to use AGENTCODI. No WebView shell. No separate gateway setup.

AI session retrospectives — skills and prompts that let your AI agents bring their feedback to your retro

Autonomous web-app pentest engine — a multi-agent pipeline wielding 30+ offensive-security tools as skills, PoC-validated findings. Built on Anthropic's defending-code harness + Building Effective Agents.

DSH execution-discipline plugin suite: 11 plugins + 6 skills, zero dependencies, 426 tests. 让 DeepSeek Harness 变聪明的插件套件。

Sane policies for insane agents

A gateway + skill letting Claude Code agents collaborate across machines

Local coding agent with native Zhipu GLM / StepFun Step Coding-Plan support. Four hard gates — the agent can't claim done without running the tests. 本地 coding agent，原生支持智谱/阶跃 Coding Plan，四道门硬约束。

Ethics-aware OSINT investigation planning, collection, and risk evaluation, delivered as an MCP server. Classification, risk tiers, hard stops, and defensible documentation — driven by local YAML doctrine.

AMH Cloudflare Ops MCP by WT

Turn client feedback into pull requests automatically.

SNAFU. Agentic LLM flow to help you with "naming things" in source code.

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit human approval gates.

Talk to Claude Code instead of typing: a voice daemon + dashboard that records you, transcribes, routes to your agent sessions, and speaks the replies back - with per-voice avatars, push-to-talk hotkeys, and a live conversation HUD

A modular framework for agentic Bayesian optimization

把中文视频逐字稿转换为可执行 HyperFrames 分镜规格的 AI Agent Skill

Claude Code sessions and Codex CLI agents message one another by name, on one Mac or across your Macs over SSH. Native wake, receipts for every delivery.

Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.

transformers gguf text-generation-inference unsloth llama trl

Automate and document any website's underlying API and replay it with your agent.

Governed, repo-native AgentOps template for AI-assisted software projects, with cross-agent contracts, permission gates, durable state, and canonical verification.

Local-first control plane for coding agents, Git worktrees, and tmux sessions

Make AI agents finish authorized, non-trivial work and prove the requested outcome with direct, scope-matched evidence.

Interactive web app where you describe pathfinding strategies in plain English and an AI forges them into Python code. Runs in a secure Docker sandbox against mazes, race tracks, and weighted maps with real-time Canvas visualization. One algorithm, any terrain.

Prompt Engineering skill for Claude Code — rewrites and optimizes prompts using proven techniques (Anthropic, OpenAI, Gemini, The Prompt Report).

AegisAl：基于 Tauri 2、FastAPI 与 LangGraph 的跨平台桌面安全智能体

Research-grounded, harness-agnostic skills for AI coding agents

DeepSeek Harness (DSH) plugin for self-improving AI agents: continual learning, persistent memory, cross-session knowledge, review-and-refine workflows, and automatic rollback.

Multi-LLM development harness — local-first, test-gated, honest by construction. Requirements→spec→plan→build→review→release with real verification gates; operable by humans, CLI, desktop, or other agents via MCP.

Multi-account and usage manager for Claude Code and OpenAI Codex — switch logins, track quota, auto-rotate before rate limits

Open reproduction of NVIDIA's AVO paper (arXiv:2603.24517): evolutionary search where an autonomous coding agent IS the variation operator — Vary(P)=Agent(P,K,f). Runs on the Claude Code or Codex session you already have.

Production-grade RAG pipeline built from scratch (no LangChain) — hybrid FAISS + BM25 retrieval, cross-encoder reranking, evaluation harness, and AWS Lambda deployment.

safetensors jais Arabic English LLM Decoder

Portable AI coding-agent skills for source-attributed, human-approved context packages.

Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — ten composable plugins.

SIGPAZ | Sistema Full-Stack (Laravel + Angular) | Seguridad: JWT, RBAC, MFA, AES-256 | Arquitectura: SOLID, GoF, C4, FDD | Base de Datos: PostgreSQL + pgvector | IA: RAG (Chatbot semántico) | Backblaze B2

MCP server unifying 169 Google Workspace tools across Drive, Docs, Sheets, Slides, Gmail, Calendar, and Forms behind a single OAuth 2.0 flow. Read-before-edit guards, lazy auth, multi-account profiles, no telemetry.

Local proxy so Claude Code and grok-build (Grok CLI) can use Cursor models (Fable), plus Codex, Kimi, and Grok

A SKILL.md for AI coding agents that stops overengineering before it starts. Turns KISS, YAGNI, and DRY into a real decision system — not just a reminder.

gplay: publish to Google Play from CI or a coding agent. One static binary, JSON output that mirrors the Play Developer API verbatim, semantic exit codes. Replaces Fastlane supply.

LLM evaluation for Java — LLM-as-judge, RAG, agent-trajectory and structured-output evaluators for Spring AI and LangChain4j. A Java port of LangChain's OpenEvals.

市面上所有常见的项目，公司花百万研发的项目，现在统统免费获取！！！包括无人机智能巡检平台，数字孪生低代码平台，AI农业，MES，IOT，物联网，ERP，AI监控系统，AI医疗，模型训练，YOLO检测，舆情系统，数据中台，BI系统，CRM，企业级智能体，AI训练平台，数据标注，民宿管理系统，智能制造系统，应急管理指挥系统，AI短剧平台，AI小说，企业报表、财务，智慧工地，智慧工单，智慧矿山，安全检测，工业质检，AI客服，仓库管理，AI心理咨询，企业级大数据，智慧农业，固定资产管理，PCB缺陷检测，低代码-无代码开发，数据大屏，AI合同审查，智慧中医，多智能体中医，AI数字人，AI运维，企业安全生产管理，能源管理，园区综合管理，流程审批，电子签章，孪生智感预警，YOLO目标检测模型训练等等。

CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop.

Bring Zendesk deep into your AI assistant: find answers and draft, update and translate Help Center articles, and manage Support tickets end to end: comments, triage and attachments. All in plain language.

Multi-model orchestration engine. Combine any LLM providers (Gemini, OpenAI, Anthropic, Groq, local GGUF) into a single Ollama-compatible API. 24 tools, multi-agent, Docker ready.

An AI-powered resume tailoring web app that analyzes your resume and job descriptions to generate personalized LaTeX and PDF resumes and cover letters.

The missing OpenAI-compatible API for calling Cursor models. Point OpenAI clients at Composer models via your Cursor API key

A Model Context Protocol (MCP) server exposing ERP-style data (sales orders, inventory, purchase requisitions) to AI agents — with a real human-in-the-loop approval gate on write actions. FastAPI + FastMCP + PostgreSQL, Streamable HTTP transport, Dockerized, tested.

把 Claude Code、Codex 和 Hermes 接入工单、CI 与业务系统。自托管 Agent 执行服务，提供 Web 管理台、异步任务 API、独立工作区和结果回调。Self-hosted agent execution with a web console, async task API, isolated workspaces and signed webhooks.

transformers safetensors Dream feature-extraction text-generation conversational

♾️ Doubao Work alternative, chat agent to web apps with various UI and safe, quick, stable APIs. ♾️ 豆包工作开源平替，聊天即兴生成各种网页前后端，安全、快速、稳定。

Repository Context Layer — a git-native context.md standard for AI agents: consult before planning, write back what was learned

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.

Local-first, evidence-led security knowledge base with a model-neutral JSON CLI, immutable sources, and human-reviewed proposals.

Open-source AI film studio: director agent + Seedance 2.5 (Atlas Cloud MCP / MuAPI) + CapCut-style timeline editor. Generate, QA, assemble, and export cinematic videos from your photos.

Autonomous AI agent skill to position for the $FLOP airdrop. Install in your agent and prompt 'Help me with the $FLOP airdrop'

Self-hosted AI agent for terminal and Telegram, with Claude/Codex workers, live activity and a deterministic permission kernel.

First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.

dMoERA Creator Studio MCP Server: build, backtest, and deploy crypto trading strategies via AI agents

Native iOS DeepSeek Harness port: BYOK inference, on-device Agent tools, iSH sandbox, Cordis plugins, and trajectory.

AI Agent 开源书单/教程合集 | Awesome list of LLM Agent books & courses

OrCAD Capture TCL automation skill pack for AI agents (Claude Code / Codex / Gemini CLI compatible). Covers Cadence SPB 23.1+: schematic-side TCL, CIS probe, design cache recovery.

An MCP server that turns a Windows RAD Studio machine into a remote backend for programming agents: safe editing, real MSBuild builds, git, scaffolding, deploy & remote execution via PAServer, Android (adb), Linux and Windows desktop control, DelphiLSP semantic navigation (8 of 42 tools), persistent vault. Per-workspace security.

TikTok Shop Affiliate Scraper. Find creators promoting any product with verified data (product name, price, sales, creator followers). Apify actor.

CREATIVE · VIDEO — One raw facecam take → a finished short-form motion-graphics ad. Claude Code skill + playbook, rendered with HyperFrames.

Xposed module: expose Xiaomi Super AI (com.aios.osbot) as local OpenAI-compatible HTTP API

The shortest complete answer: an agent skill

Lightweight native Android application which connects directly to any OpenAI-compatible API endpoint (such as OpenAI, OpenRouter, or local llama.cpp instances).

🎨 Pick & apply a design style from 67 curated visual aesthetics — an agent skill for Claude Code, Codex, OpenCode. Preview + palette + CSS + prompts, all in one.

gguf GLM 4.7 Flash thinking reasoning NEO Imatrix MAX Quants

Real-time acoustic voice interruption and turn-taking manager with sub-150ms speech cutoff (Vapi style)

Find what is wrong with the AI agent configuration your repository already has.

The framework client-facing teams use to build internal & client apps with AI. Two agents — a Product Owner that advises what to build, and an AI Developer that ships it. Built by FuseBase.

Manage AI coding agents like human engineers. The open-source, self-hosted PR layer for AI software development.

Portable Command Center - Mobile app to control OpenCode AI agents

Physical AI harness your agents need. An open-source, continuously evolving collection of field-tested robotics expertise spanning the leading Physical AI frameworks, simulators, libraries, and developer tools. Install Robium as a plugin to empower your favorite AI coding agent with the robotics skills it needs.

Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance

Open-source Object Context for software teams and AI agents. Maps real code into business objects, logic and dependencies, shows change impact, serves relevant context over MCP, and verifies outcomes. Local-first.

Multiplayer Agent Management Platform — agents as infrastructure. Host teams of agents that work together and run your business.

开源微信公众号排版 Skill / AI 视觉主编：让 Agent 将主题、资料或 Markdown 转成 12 套可切换主题的微信兼容文章，支持 AI 配图、手机预览、富文本复制和公众号草稿箱发布。Open-source AI agent skill for Markdown to WeChat.

Open-source AI research workspace built with Electron and FastAPI, featuring provider-neutral agent workflows for DeepSeek, GLM, and other OpenAI-compatible models.

Local-first desktop AI agent platform built with TypeScript, Electron, React, and SQLite.

Converge — Dual-agent iterative convergence for plan/code review | 双 Agent 迭代收敛器，用于计划与代码的对抗式审查

CUMCM 国赛 AI skill 包：读题到交卷。C 题走数据契约，A 题走机理/PDE（单位、守恒、网格收敛）。支持 Claude/Codex/Grok/opencode。

A true Jarvis-like voice agent: zero dead air, no awkward silences, no lag - instant spoken replies with the intelligence of the most advanced LLMs behind them. Realtime voice + any frontier brain (Grok / Claude / GPT / Gemini) as one seamless persona. Discord push-to-talk on OpenClaw, Hermes Agent or any agent app. v2: true-jarvis-2.0

Uma agência de crescimento de YouTube guiada por IA que roda no seu terminal e conhece o SEU canal. Plugin do Claude Code · open source · qualquer nicho.

Lossless context folding for the Pi coding agent: only the oldest context changes; the fresh window stays untouched.

Comprehensive open-source study guide for mastering agentic AI — from LLM foundations through production system design and interview preparation. 60+ in-depth pages covering theory, design patterns, frameworks, runnable code, system design case studies, and interview questions.

See what Claude Code actually did. Local-first observability for every session: which tools ran, what each sub-agent was told, which turn blew the budget. Cost, tokens, error alerts, full-text search. SQLite on your machine, nothing leaves it.

🏪 Telegram-бот магазина на бесплатных ключах Google Gemini: ротация ключей при 429, каскад моделей, три личности продавца, каталог, корзина, QR-оплата

Windows用デスクトップ向けAPI/ローカルLLMクライアント。ペルソナが話しかけてくれたり、天気取得/ウェブ検索/URL読込みもできるよ。

Self-hosted, source-available Facebook & Instagram automation: publishing & scheduling, inbox auto-replies, drip sequences and a contacts CRM. A ManyChat / Buffer alternative you fully own.

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

1-Click Grok Bot 8 Man Crypto Trading Desk as seen on X

The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated floor, mail, task board, chat with the boss.

transformers safetensors llama text-generation unsloth codellama

Você não começa do zero — chega com impulso. Guarda as peças de site que você já fez e as encontra de volta antes de gerar qualquer coisa outra vez. Agent Skills para Claude Code, Codex, Gemini CLI e Cursor.

Use [Multi]ple AI agents for code-review, verifying and questions

Portable skills for coding agents — self-contained Markdown procedures that run the same under Claude Code, Codex, or any host that reads the format. Starting with investigate-codebase, which builds an evidence-backed model of an unfamiliar repository instead of a confident directory tour.

One delegation policy for Claude Code, Codex CLI and T3 Code: role-based headless workers, worktree locks, cross-vendor review, safety gate hook.