Code agents

Cascade orchestrates AI agents (Claude Code, Codex, opencode, LLMist) across your workflows in GitHub, Trello, Linear and Jira.

Research Math Agents, Official code release for our paper RMA

AgentAPI is a lightweight Python framework for building agentic AI backends and chatbots with minimal configuration. It provides a plug‑and‑play developer experience for integrating multiple LLM providers, creating AI agents, streaming responses, managing tools, and handling conversation memory --- all on top of FastAPI.

Single source of truth for GenAI and agentic AI security incidents, mapped to OWASP LLM Top 10, OWASP Agentic Top 10 (ASI), NIST AI RMF, and MITRE ATLAS.

Autonomous AI experiment loop CLI -- run research overnight with any coding agent

Guardian Agent and Token Savings for Claude Code

AI coding agents comparison - 80+ agents, SWE-Bench leaderboard, pricing. Devin, Cursor, Claude Code, Copilot, and more. December 2025.

Achieve infinite conversation turns in a single API request via turn-mcp. Self-hosted MCP server with browser console for human-in-the-loop AI agents.

High-quality Agent Skills made to perform reliably in real workflows

Save 87% token usage for Claude Code. Zero install. 8 rules covering input+output+context. 6 months verified.

Auto-evolving LLM Agent Harness - Benchmark-driven evolution via Claude Code + self_evolution.md guide

Mission control for parallel Claude Code and Cursor agents. Local-first cockpit for desktop and phone.

FylloCode 是一个开源桌面应用，把 Claude Code、Codex 等本地 Coding Agent 接进项目工作流。派任务、审方案、追溯每一次改动，积累下来的规范和结论，换一个 Agent 也能继承。

Self-hosted web control plane for Codex, Claude Code, and AI coding agents running on your own machines.

Transparent logging proxy for LLM API traffic that auto-configures clients and records every request and response to Claude, OpenAI, and other providers for debugging, auditing, and analysis.

Massive multi-source academic literature search for Claude Code — one skill fans out subagents across 20+ scholarly databases (arXiv, Semantic Scholar, Crossref, OpenAlex, PubMed, …), merges into a deduplicated ranked corpus, and acquires the original PDFs.

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime.

Self-hosted AI workout tracker. Bring your own LLM (Anthropic or OpenRouter): weekly debriefs, a chat coach, and AI-generated programs.

申根签证 AI Agent 技能 — 按身份定制清单、跨会话记忆，带你跑完办签全流程

A native, performance-first ADE built with Flutter, Rust, and Ghostty. Run Claude Code, Codex, Amp, and other CLI coding agents in parallel. No Electron.

An autonomous agent for open-source repository management — triages issues, reviews PRs across iterations, watches your sites, and escalates only the decisions that are yours

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

Self-hosted AI agent that builds apps. Chat with a coding agent (Claude Code or Codex) that builds mini-apps, modifies its own UI, and gets sharper the more you use it. Your personal AI operating system, on your own server.

TwinCAT coding agent for Beckhoff PLC development, with strict rules for Structured Text, naming conventions, PLC-aware tooling, syntax checks, and safe project validation workflows.

面向 Codex、Claude Code 与 AI Agent 的考研择校导航 Skill：联网调研复试线、统考名额、推免和拟录取数据，生成避坑提示与冲稳保建议。

The most comprehensive open-source library of 600+ installable AI agent components: skills, MCP servers, workflows, subagents, hooks, plugins, prompts, and tools. Install via npx. Works with Claude Code, OpenCode, Codex, Cursor, Gemini CLI, Copilot, and 30+ agents.

AI-powered multi-agent workflow orchestration with built-in safety intelligence for OpenCode

📈 Claude Agent Skills for A股分析 | 29个即插即用 Skills 覆盖数据采集/大盘分析/资金流向/涨停追踪/技术面/基本面/估值/财报/多因子/回测/风控/智能报告 | 含自选股监控 | akshare+tushare+东财 | Claude Code 首选搭档

Claude skills to run ads: advertising & marketing strategy, campaign structure, targeting, creative, and budgets for Google Ads, Meta Ads, TikTok & more.

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

MCP server for parametric 3D modeling in Autodesk Inventor - drive Inventor with AI in natural language. Includes Agent Skills and undocumented Inventor 2026 COM API knowledge.

Ask your video library anything — an AI agent that watches, reasons in a tool-use loop, and answers with playable clips and charts.

transformers pytorch text-generation custom_code en arxiv:2312.13286

transformers pytorch gguf codeshell text-generation wisdomshell

transformers pytorch tf jax gpt2 text-generation

transformers safetensors internlm feature-extraction chemistry text-generation

transformers safetensors qwen3_moe text-generation unsloth conversational

transformers safetensors qwen2 text-generation code codeqwen

gguf text-generation base_model:Qwen/Qwen3-Coder-Next base_model:quantized:Qwen/Qwen3-Coder-Next license:apache-2.0 endpoints_compatible

transformers safetensors qwen2 text-generation code codeqwen

Claude Code skill that deploys 8 radically different visual direction demos in an existing Next.js + Tailwind project, from Swiss Minimal to Neo-Brutalist. Compare them side by side, pick one, and it extracts the Tailwind config, CSS variables and base components.

Convention-based persistent AI agents for Claude Code — autonomy model, session memory, intent-based communication

Track your AI coding-agent token burn across Claude Code, Codex, OpenCode, Antigravity, and more.

Sample solutions leveraging the Microsoft Graph API that provide an inventory of Copilot Agents in a given tenant.

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

Academic advisor due-diligence skill for Codex, Claude Code, and other agents | 学术导师调查评估

Pinned, hardened config stack for OpenCode + OpenRouter + oh-my-openagent (OmO). One install, OpenRouter-only routing, 19 models, deployment guards, content-aware uncensored routes, circuit breakers, cost-aware fallbacks.

A self-improving swarm of local-LLM agents that mine, smelt, build, farm, and fight their way through Minecraft as a coordinated team. Built on mineflayer + Ollama.

TRACE is a practical agentic jailbreak framework that leverages task decomposition, task-aware disguising scenarios and adaptive self-evolution to investigate emerging security risks of LLM-based agents.

RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.

Mobile AI Skills, Agents and workflow to help you build mobile apps and games faster. A collection of AI skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Use these ready-made tools to write code faster, fix bugs, review code, improve performance, automate tasks, and ship faster with AI.

AI 原生的本地与远程终端工作台：统一 Local/SSH/SFTP、远程文件编辑与传输、Docker/Podman/Compose、tmux、隧道与服务器监控，让 Codex、Claude、PI Agent 通过 MCP 直接操作实时终端与基础设施。

Ship AI-agent artifacts, not demo theater — verifier-gated, cross-family runs that learn which model wins. TRUE recursive self-improvement: its apply loop promotes changes to its own prompts and workflows with no human approval — real measurement required, nothing reviewed first. Run on a throwaway worktree; see docs/SAFETY.md.

Read-only Kubernetes troubleshooting agent in Go (client-go) — explains CrashLoopBackOff, ImagePullBackOff, OOMKilled, Pending/Unschedulable with P1-infra to P2-workload reports; guarded reversible --fix; optional AI --explain via Claude API.

Battle-tested agent skills and Cursor rules from real projects. Works with Cursor, Claude Code, and any agent.

一个 agent skill：把一个主题做成封面/目录/每章插画/精排俱全、可直接出片的 PDF 书。多 agent 调研→逐章写作→配图→Typst 排版→事实核查。工具无关(Claude Code / Codex)、风格可插拔

Autonomous offensive-security agent: recon, authorized pentest, vuln hunting, DFIR & multi-framework compliance from a single prompt. Local-first (llama.cpp), skill-based, deterministic-first.

AI agent browser for web reverse engineering

企业级多智能体AI管理系统 | 企业级智慧管理解决方案 | 基于MCP架构的财务分析、成本预测、知识管理、效能评估一体化平台|- 多智能体系统 (Multi-agent System) - MCP协议 (Model Context Protocol) - - AI决策支持系统 - 企业级AI应用 - Python + FastAPI + Streamlit

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

面向"面试官 × 简历主人公"场景的个人简历 RAG 问答 Agent：把简历、证书、荣誉、项目介绍放进知识库，面试官可对简历任意提问（自我介绍、项目深挖、技术八股、HR 素质、简历细节），系统以第一人称自然作答。核心设计是"宽松推理 + 诚实标注"——硬事实（数字/日期/证书名）必须来自检索，证据不足时强制标注"根据现有知识库推测"而非编造。支持多轮追问记忆、检索兜底链、置信度分级回答、访问码闸门与 IP 限流防刷。

Open-source, local-first desktop for AI coding agents and document work. Run Claude Code, Codex CLI, opencode, and Grok CLI in isolated Git worktrees.

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

The agentic debugger for Claude Code, Codex CLI and Gemini CLI: a token usage, cost and context-window tracker that shows what the tokens ARE — live memory map, per-file tokens, cache economics, compaction autopsies, PDF reports.

Unlimited FREE AI coding! Free AI API Gateway — 25+ models, no auth required, no api key, never hit limits.

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAGAS/DeepEval) and LLM scanners (garak).

Profession-specific AI plugins for Claude Cowork — pharmacists, PTs, real estate agents, and more

AI-assisted development toolkit for Magento 2 and Mage-OS. An MCP (Model Context Protocol) server that enables AI coding agents to interact with Magento and Mage-OS installations through introspection tools, code generation capabilities, and comprehensive Magento/Mage-OS knowledge.

Automate your job search with your favorite coding agent. Skills, guides, and scripts that any agent (Devin, Claude, Cursor, opencode) consumes to search, apply, and track jobs on your behalf.

Type-aware, evidence-backed delivery contract for AI coding harnesses. Different agents in. One predictable human handoff out.

Phase-based AI development framework for AI Coding Agents. 17 specialized agents across 6 phases, handing off through files in your repo — and it reads the codebase you already have.

Skill Marketplace is the first open-source marketplace purpose-built for AI agent skills — the reusable, composable building blocks that power coding agents like Claude Code, Kiro, Cursor, Windsurf, GitHub Copilot, Cline, and more.

Local control plane for Claude Code on Windows and macOS: switch LLM gateways in one click behind a fixed endpoint, SSE keepalive proxies, key pools with live balances, GitHub accounts with TOTP, statusline, Telegram remote.

Free AI code reviews on every pull request. Bring your own key (OpenRouter free tier works), runs in your repo as a GitHub Action - no quotas, no per-seat fees.

Python desktop AI assistant for screen awareness, voice interaction, persistent memory, and computer automation

Local-first Electron cockpit for the Codex SDK, OpenRouter, multi-agent crews, and bounded computer access.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.

we love free stuff. ox alpha . glm-5.3-flash is here!.

Multi-account and multi-bot Telegram DM bridge for pi: allowlist multiple Telegram users and assign a separate bot to each pi session, so you can drive multiple coding-agent sessions in parallel.

Automated faceless YouTube video pipeline - clone any channel's style, generate videos on autopilot with Claude Code.

Claude Design in Claude Code, Codex, Cursor, and 20+ agents. Designs come from your real components, tokens, and states; approved revisions sync back.

Turn an approved product design, PRD, prototype, design system, or architecture brief into an AI-governed, deployable full-stack project with a pnpm monorepo, requirement traceability, canonical multi-agent rules, mandatory AI review, executable quality gates, CI, container deployment assets, and handoff evidence.

A multi-model Agent runtime built on Spring Boot 4 / Spring AI 2.0: model routing (Anthropic / DeepSeek / OpenAI / custom), thinking toggle, Task subagents, hot-pluggable Skills, Docker sandbox + Code Interpreter, MCP tools, dify/n8n integration, RAG with pgvector, Human-in-the-Loop approvals — all streamed as structured SSE events.

Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreading activation, and active forgetting.

Writ: An AI agent skill that catches AI writing tells and clichés using a self-edit checklist drawn from Wikipedia's Signs of AI Writing guide.

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk Hermes/Claude/Codex/opencode. Verified.

This repository contains the code for the paper "EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval"

Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines

AI recruiting & hiring engine for Claude Code. Job description optimization, batch resume screening, interview frameworks, salary benchmarking, offer letters, onboarding plans & PDF reports. 14 skills, 5 parallel agents. Recruiters charge $15-$30K per placement.

21 AI agent skills for the full B2B sales lifecycle. Works with Claude Code, Cursor, Windsurf, Codex, and any Agent Skills-compatible tool.

Build your AI Second Brain with Claude Code — companion starter kit for the ODSC Personal AI Agents Summit 2026

Harness-based Agentic RAG: search, understand, and answer questions over documents and code using an AI coding agent harness (Cursor, Claude Code, Codex, etc.) in a sandbox — no embeddings, no vector DB.

🔥 Save up to 96% cost — more than Caveman (65%) or RTK (80%). AI coding agent: chat, map, edit, multi-agent. Single Rust binary.

BoundaryBench: benchmark coding-agent harnesses (Claude Code, Codex, Terminus 2, Grok) on Terminal-Bench tasks under hardened NIST-derived sandbox policies. Inspect AI + Harbor compatible.

Sync AI coding-agent configs (Claude Code, OpenCode, Codex, and more) from one canonical, committable source.

Local-first command center for software projects: tasks, Git, terminals, and coding agents (Claude Code, Codex, Gemini CLI…) in one desktop workspace.

Universal skills and agents for every AI harness. Author once, wire anywhere: Claude Code, Cursor, Codex, Copilot, Gemini CLI, Windsurf, Cline, Aider.

Orbit is a native desktop workbench for the pi coding agent — a chat-style GUI rendered entirely in Rust on GPUI, the GPU-accelerated UI framework Zed is built on. It speaks the pi CLI's RPC protocol directly over stdio: no browser, no webview, no Node.

SWE-bench for your codebase — mine your merged PRs into local, contamination-free coding-agent benchmarks. Adapters: claude-code, aider (Opus 4.7 / GPT-5.5 / Sonnet 4.6 / Gemini 3.1 Pro).

Claude Code agent that routes to external LLMs (Grok, Gemini, GPT-5, etc.) via OpenRouter - just mention the model name