Code agents

Visual management dashboard for AI Agent skills, workflows, and rules. VS Code extension with 4,300+ downloads. Open-source (MIT). Built by the ChronicleCore A1 Expert System.

Claudito: A web interface for Claude Code that interacts with the CLI. Use it with your plan. No need for an API key!

Cortex is a desktop app for running Ollama models locally. No cloud processing, no remote servers, and no data leaving your machine. Micro harness built in for safe, local code execution.

Google Gemini Clone 2024

Local LLM coding assistant extension for Visual Studio

Code for the AI Agents blog series—covering agent design, architectures, multi-agent systems, and evaluation.

Working code repository for the paper "SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction"

Threat hunting command system for agentic IDEs

Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the workflow. Works with Cursor, VS Code, Claude Code, and Windsurf across Claude, GPT, Gemini, Grok, and DeepSeek.

😈 OSINT AI - CHAT << Leak Finder >>

One API, any AI

Fake API Server for AI-Bypass

Simple verification experiments codes for multi-agent RL using OpenAI MPE environment

yoink is an AI agent that removes complex dependencies by reimplementing only what you need.

100+ subagents for gemini-cli

Edge-native AI API gateway — cost-optimized routing across providers, multi-protocol support, built on Cloudflare Workers.

Automatic support for (Claude) Skills for any coding agent that supports AGENTS.md

Argus Automation — SOTA desktop automation for AI agents. Works with Claude Code, Codex, and OpenClaw.

Spec-driven dev workflow MCP for Cursor & AI agents — start_feature/bugfix orchestration, auto Skill+AGENTS bootstrap, memory, GitNexus. npx -y mcp-probe-kit@latest

Free OpenClaw security scanner. 3,000+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.

Understand your GitHub Copilot plan, quotas, and limits at a glance

AgenticSeek is a fully local, voice-enabled AI assistant designed to autonomously browse the web, write code, and plan tasks while ensuring complete privacy by keeping all data on your device. Tailored for local reasoning models, it runs entirely on your hardware, eliminating any cloud dependency.

The validation layer for solo founders. Research, strategy, and validation on Claude Code - decide before you build. 3 agents, 29 skills. MIT.

Orchestrate agents with a peer network of state machines. Supports checkpoint/restore, persistence, and more. BYO cli, or agent, or use flatagents with API. Batteries included.

OxyJen is an open-source Java framework for orchestrating LLM workloads with graph-style execution, context-aware memory, and deterministic retry/fallback. It treats LLMs as native nodes (not helper utilities), allowing developers to build multi-step AI pipelines that integrate cleanly with existing Java code.

Agentic LLM CTF to test prompt injection attacks and preventions

Svelte 5 reimplementation of react-grab — Alt+Click any element to inspect components, state, styles, accessibility, errors, and performance. A complete dev tool suite for coding agents.

Community-driven Claude Code marketplace with specialized AI agents for the full SDLC. Features multi-agent coordination, workflow orchestration, and 100+ API integrations. Includes code review, security scanning, deployment automation, performance optimization, and more. Production-ready tools built by developers, for developers.

Local-first, auto-injecting context + memory layer for Claude Code, Codex and MCP. Per-prompt hook injection, explicit freshness/Trust Contract, AST indexing, call graphs, hybrid search, wiki + architecture dashboard. Everything stays on your machine.

Browser-based AI coding workspace for Claude Code and Codex. Run long tasks, supervise progress, and switch across desktop, tablet, and phone.

VERITAS OS is an AI agent governance runtime for decision control, policy enforcement, approval workflows, audit trails, and replayable evidence before real-world actions.

SPEC-first multi-agent framework for Claude Code.

Agent skills for building, shipping, and growing software products

Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.

Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.

Agentic Memory for Claude Code

Claude Code v2.1.88 源码深度分析笔记 — 架构解析 + 面试八股

Multi-Agent System built with Google ADK and OpenRouter models, coordinating specialist agents to query PostgreSQL (via MCP Toolbox) and Data Commons for HDB resale data and global statistics.

Ignition (8.3 and above) MCP server work with the new REST API

A modern, user-friendly terminal emulator designed to enhance your AI pair‑coding experience.

Give your agents a cute office. Multi-device, multi-user, multi-agent collaboration.

Cloak your Claude. Switch identities in seconds.

An open canvas workspace for AI coding agents

A team of specialized Swift agents for Claude Code. Swift 6.2 concurrency, Apple Foundation Models, on-device AI, SwiftUI, accessibility, security, testing, and App Store compliance — enforced on every prompt.

《深入 OpenCode》。全网第一本介绍 OpenCode 的书，用 OpenCode + Opus 写成。A book introducing OpenCode, written by OpenCode + Opus

A FastAPI-powered workflow orchestration system that integrates LangGraph to design, run, and manage AI Agents workflows

Browser engine for agents. HTML in, structured Semantic Object Model out. Native MCP and AWP with a supported CDP subset. Apache-2.0.

Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted game development.

Multi-account Google Workspace (Gmail, Drive, Calendar, Sheets, Docs) + Slack MCP servers for Claude Code. Setup guide with CLAUDE.md for AI-guided installation.

MCP server for Outlook email, calendar, and contacts — let your AI assistant manage your inbox directly from the conversation.

Tailwind CSS for Flutter. Utility classes like flex, p-4 and dark:bg-gray-800 compose into optimised widget trees. 27 W-prefix widgets, a Claude Code skill and a hosted docs MCP server for AI agents.

Agent2 is a self-hosted, browser-based autonomous AI agent powered by aaravprogrammers that combines a coding assistant, real terminal access, security testing tools, persistent memory, and a workspace system into a single unified interface.

为 Cline、Codex、Claude Code、Droid、OpenCode、CodeBuddy 和 ZCode 提供 obra/superpowers 的中文友好适配，支持中文触发、中文文档输出和更稳的安装更新体验。

AI-powered interactive RPG engine with persistent memory, independent NPC minds, creativity-based combat, and a reactive world. Build scenarios, live adventures — the AI narrates everything. Supports DeepSeek, Anthropic, and OpenAI.

Build, deploy, and connect AI agents to SAP Joule via the A2A protocol on BTP Cloud Foundry — directly from Claude Code. Supports TypeScript (Express or CAP) and Python agents with LangGraph and SAP GenAI Hub.

Extract equations and context from research papers for LLM coding assistants (arXiv, LaTeX, RAG)

Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).

AI agent tooling for Loxone Miniserver — natural language → config-as-code → deploy

Hermes Agent plugin for Twitter search, monitoring, follower exports & approved X actions. Not affiliated with X Corp.

Connects any MCP-compatible AI assistant to Siemens TIA Portal via the Openness API

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

A research fork of opencode demonstrating Language Anchoring — making LLMs think consistently in your language. Verified: 95%+ Chinese thinking compliance.

Midnight MCP server giving AI assistants access to Midnight blockchain — search contracts, analyze code, explore docs

Axon reads the logs your AI coding-agent harnesses already write — Claude Code, Codex, OpenCode — and shows which harness, project, agent, and model is working, how fast, at what cost, and how much code it's producing.

Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap

Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.

Aileron Protocol: A strict system harness override enforcing deterministic AI behavior through codebase-first execution, strict token economics, and rigorous debugging limits.

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

AI 驾驶的自愈式 A 股模拟盘交易赛车 · Self-healing paper-trading race car driven by AI agents

AI skill package for paid social operators: Meta performance analysis, creative angle research, KPI workbooks, and UGC scriptwriting.

AI-powered code review agent for GitHub pull requests. Self-hosted GitHub App using PI.

Talk to your Claude Code by voice — a real voice call with your terminal agent. Local whisper STT, edge-tts voice, no API key.

Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.

AI agent skill for TR Dizin (trdizin.gov.tr) — search Turkish academic publications, journals, authors & institutions via the open JSON API, with advanced field search, references/citations, and PDF-to-text. No browser, login, or API key; works with Claude Code, Codex, and other agents.

A comprehensive collection of expert AI Agent Skills for Google Gemini, featuring a powerful CLI to convert and optimize Claude Code agents for the Gemini ecosystem.

Single-file, zero-dependency AI coding agent for the terminal.

CodeStory is a codebase grounding engine that preindexes code into a knowledge graph and enriches it with semantic context. Paired with coding agents, it results in fewer tokens, fewer tool calls, and remains 100% local.

Local-first daily job aggregator. AI review per job via your own LLM CLI, swipe-to-apply triage, and an MCP server for AI clients.

A structured agentic development pipeline for Claude Code — extends QRSPI with worktree parallelization, tiered reviews, integration verification, acceptance testing, and replanning

The operating system for Claude Code. Memory, accountability, journaling, knowledge graphs, pattern recognition — one install, every session compounds.

A visual, editable context management panel for Codex. Better context compression, smarter compression strategies, automatic context organization suggestions, and system prompt customization

🏗️ Run coding agents in a sandbox, not on your machine.

Unofficial source-linked AWS best practices for every AWS service, organized by Well-Architected pillar for Claude Code, OpenAI Codex, and AI coding agents.

WSP MCP - Free WordPress MCP For Connecting AI Coding Agents

一个用 C# .NET 10 写的 Agentic 框架，采用 ReAct 范式，支持渐进式技能 (Skill) 加载、 多个大模型 Provider、MCP Server、图像识别、流式 WebAPI、React WebUI、钉钉集成。

The official Rifteo agent skills library - a collection of reusable instruction sets for AI agents covering security testing, audit, and compliance workflows. Supports 53 agents

MCP server for Web3 protocol documentation — EIPs, ERCs, BIPs, SIMDs, Cosmos ADRs, Polkadot RFCs, contract registry

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.

Greater China Legal Agent Skills — 大中华区法律智能体Skill体系，基于Anthropic claude-for-legal适配，支持中国大陆/香港/澳门/台湾/新加坡，覆盖30个法律场景478个Skills

Solers is the AI native game engine built on Godot. Build, playtest, and iterate with an AI agent working directly inside the editor.

transformers safetensors qwen2 text-generation code codeqwen

transformers safetensors qwen3_5 image-text-to-text abliterated uncensored

mlx safetensors gemma4_unified image-text-to-text gemma4 coding

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

A small vibe-coded app to track agent status in claude.

Complexity-aware agentic coding pipeline for Claude Code

A coding agent built on LLM

Local-first AI agents for your Obsidian vault.

Academic research toolkit for AI gateway panel security studies (Sub2API / New-API / One-API): FOFA discovery, fingerprinting, credential-hygiene testing, artifact normalization. Authorized, defensive use only.