Code agents

Your personal agent cloud: a local control plane and mesh network for coding agents.

Multi-agent orchestration harness for Claude Code + Codex — task lifecycle, handoff protocol, dashboard, and autonomous dispatch

Autonomous multi-agent AI penetration-testing engine: a governed tool sandbox, an immutable evidence-and-validation gate, and a reproducible security-agent evaluation environment.

Agent control plane and runtime access platform for enterprise systems — govern business APIs as Tools, compose Agents and Workflows, expose runtimes through AAP, and trace executions end to end. https://act-weave.grok.me

Runs a group of Claude Code agents on one project, with one of them in charge. Local, event-sourced, one person, a handful of agents.

This 4B Local AI Scores 96.9% on Coding! (NeoHorse Agent Setup) - Complete setup guide and python implementation for running NeoHorse 1-4B local autonomous agent with Ollama.

Multi-platform AI bot framework: 5 hot-swappable agent runtimes (Claude Code / OpenClaw / Kilo / Gemini CLI / DeepSeek Harness) across Discord, Feishu, DingTalk and a self-hosted web entrance, with shared memory, bot-to-bot collaboration and real-time voice.

Turn LLM coding agents (Claude Code, Codex) from next-token predictors into divergent thinkers. A research-grounded cognitive engine + drop-in Claude Code skills for creativity, reasoning & robustness, with 6 honest reproducible benchmarks and 137 verified papers.

Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

Persistent, federated meta-harness for AI agents. Continue, delegate, fork and merge work across Claude Code, Codex, Cursor, Kimi, OpenClaw and more.

Governed execution for AI agents, workflows and software.

Enterprise reference architecture for governed Agentic SOC, MSSP, MDR, Cloud IR, and private/local LLM-assisted DFIR operations.

Local-first agentic inference engine in C/C++. Multi-tier model routing, grammar-constrained output, MCP tool servers. Embeddable via C ABI.

AI IR Overlay™ — practical incident response framework for AI agents in production. Built on NIST SP 800-61 r3, mapped to NIST AI RMF, NIST CSF 2.0, OWASP Top 10 for Agentic Applications 2026, ISO/IEC 42001, EU AI Act.

An open database of real-world AI agent incidents.

Agent 测试转型手册：资深自动化测试工程师的 AI QE 学习路径 + 练手代码

Terminal-native Rust coding agent. Local-first: your code stays on your machine, and the model is yours to point at — Ollama, llama.cpp, a rented Colab GPU, or any OpenAI-compatible endpoint.

Repo-owned engineering memory for coding agents — preserve decisions, failures, domain knowledge, and deferred work across sessions, teams, and models.

AI-first engineering toolkit that turns coding agents (Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Aider) into Senior mobile engineers — agents, skills, workflows, checklists & standards for iOS/Android/Cross-Platform.

Forge — pipeline de développement Claude Code stack-agnostique

A contract-first Python framework for modernizing APIs for AI through exact application behavior and explicitly bounded agent-owned decisions.

Synapse CLI | MCP server generator to build agentic context

Open-source, multi-tenant AI agent platform on AWS Bedrock — visual agent builder, RAG knowledge bases, evaluation suite, and omnichannel delivery (SDK widget, REST API, WhatsApp, Telegram). Self-hosted, MIT licensed.

A high-performance native AI coding assistant configuration workbench built with Rust and GPUI. Supports Claude Code, Codex, Antigravity, Gemini, Grok, Pi, and more.

Drive your opencode from Telegram or a Web PWA — an in-process opencode plugin with token-auth pairing.

This TypeScript-based chatbot aims to streamline the process of booking and confirming appointments for an alternative medical clinic. The bot utilizes Google Calendar and OpenAI to automate the appointment booking process.

Voice-first Mac assistant that uses the computer for you. GPT-Live-1 voice behind a wake word; brains: Codex, Claude Code, an API or a local model; Swift hands in parallel threads; alarms and automations that fire while it sleeps; a notch island control surface; a Console into every coding-agent session; memory. Rewrites itself, with your yes.

High-performance, non-invasive, self-healing Chinese localization toolkit for Claude Desktop clients (Windows MSIX/Win32 / macOS / Linux).

LLM Gateway to Protect your Secrets — redacts secrets before they reach LLM providers, restores them locally

The most comprehensive agent skills for writing real, idiomatic Rust and porting code from other languages.

Claude Code skill for iOS 26 Liquid Glass SwiftUI design — glassEffect API reference, HIG principles, design tokens, motion and accessibility rules, a pattern library, and nine example screens that compile in Xcode 26.

Local-first AI provider manager — one-click takeover routes Claude Code / Codex through a local gateway with failover, quotas and usage analytics

Windows tray monitor for Claude Code and Codex usage, limits, and sessions

A Claude Code engineering template for reliable data warehouse AI development./面向数仓 AI 开发的 Claude Code 工程化模板：hooks、skills、subagents 与八步标准流程。

Agent Kaizen skill for Claude Code & Codex: faithful, identifier-preserving reference for Blender and the bpy Python API, operators, add-ons & extensions, .blend files, shader/geometry nodes, materials, F-curves, keyframes & animation, cameras, lights, rendering, linked libraries. Routes to six area subskills.

Switch Claude Code between Anthropic and any 9Router provider, in the terminal or the VSCode panel, on Windows, macOS and Linux.

An intentionally small, curated working library of proven operator workflows for AI-assisted software work.

Broomva agent-skills monorepo — 48 Tier-2 skills compatible with Claude Code, Codex, Cursor, Gemini CLI, Goose, Copilot. Layout follows anthropics/skills (agentskills.io spec). Install: npx skills add broomva/skills --skill <name>.

A Lightweight and Elegant Markdown viewer for MD files

Web Studio for Claude Code: tiered agents, pipeline skills, hooks, dated stack reference, agent testing framework

MCP server for kie.ai — 45+ image, 70+ video, 20+ audio models with built-in Averiguare model intelligence. Dual-mode (stdio + HTTP) for Claude Code & Cowork.

A Claude Code port of pstack: 46 skills and 2 agents for rigorous, parallelizable agent workflows. Orchestration, adversarial review, verification, and 21 engineering principles.

Universal Author Voice Engine — upload any author's texts, extract their voice, generate content in that style. PDF/HTML/TXT in & out. OpenAI, Claude, Ollama, Codex.

Tagout — the gate-verified issue → PR lifecycle for coding agents (create-issue, implement-issue, merge-pr, auto-dev), with a .NET migration add-on powered by RoselineMCP.

Claude Code plugin that cuts context tokens and model cost — output-truncation hooks, an Opus-plans/Sonnet-Haiku-implements workflow, and workflow-hygiene guards.

Claude Code 多模型代理 — 一键切换 DeepSeek、Qwen、GLM、Moonshot 等国产大模型，协议自动转换，零配置即用

Local, persistent and auditable memory layer for Claude Code,Cursor, Codex & GEMINI CLI. Your coding agent stops treating you like a stranger every morning.

SearXNG search MCP for Claude Code & Grok — privacy metasearch + page extract for agents.

A desktop search engine for everything you write, read, and keep. Connect your Obsidian vault, projects, Calibre library, and code repos, then find anything with local hybrid search and expose through MCP.

A trustworthy document-grounded RAG chatbot for solar and energy technical support, with manual upload, provenance, citations, fault-code lookup, and hallucination-aware answers.

Project context and memory for coding agents.

RAG Engineer interview questions & answers for 2026: retrieval, embeddings, chunking, re-ranking, eval, production & security. 100 Qs + worked designs. MIT.

Give Claude Code, Codex and opencode a 32M-token memory that never leaves your machine. Local LLM server (MCP + OpenAI API) that runs any GGUF model with a context far larger than its window - no cloud, no retraining, no vector database. Windows and Linux, one command.

transformers safetensors qwen3_5_text text-generation agentic-coding reasoning

OpenAI-compatible LLM proxy in Go: cost-optimised routing, response caching, batch API, RAG pre-stage (pgvector + sentence-transformers), agent-gateway sub-service for CLI agents (Claude Code/Anthropic SDK/Gemini CLI)

AI buddy that reviews your GitHub Pull Requests.

Paper Reading Agent Team 是一个基于多Agent协作架构的智能论文研读系统。它能够自动完成论文搜索、PDF下载解析、摘要生成、批判性分析、PPT生成等全流程任务，帮助研究人员快速理解和呈现学术论文内容。 系统采用模块化Agent设计，各Agent分工明确、协同工作：Scraper Agent负责论文搜索，Parser Agent负责PDF解析，Summarizer Agent负责摘要生成，Reviewer Agent负责批判分析，PPT Agent负责演示文稿生成，Memory Agent负责记忆存储。支持单篇论文研读和批量处理，可自动生成学术风格的汇报PPT。

High-performance MCP server for browser automation, web capture, and content extraction. Rust-powered CDP client for AI agents.

The Text-to-SQL Agent is designed to to interact with databases using simple, conversational language, eliminating the need for manual query writing.

This project uses the CrewAI framework to automate stock analysis, enabling AI agents to collaborate and execute complex tasks efficiently. Example stock: Nvidia. Technologies include Python, CrewAI, Unstructured, PyOWM, Tools, Wikipedia, yFinance, SEC-API, tiktoken, faiss-cpu, python-dotenv, langchain-community, langchain-core, and OpenAI.

A modular, extensible Rust-based server providing short-term, long-term, and latent memory services, a chat endpoint with a BaseAgent + Sentience DSL, and integration with ChromaDB and LLM services.

An agent native CLI wrapper around delve to verify or debug golang applications No MCP

Shadow agents for autonomous code work - a local-first agentic work orchestrator

remem provides agents with persistent, reasoned memory that spans across sessions. Whether you're using Claude Code, Codex, Cursor, Copilot, Antigravity CLI, OpenCode and more.

🤖 Enterprise multi-agent orchestration platform for autonomous content verification. Built with agentic AI workflows, MCP integration, AgentDB, and advanced deepfake detection. Features agent memory, learning, and collaboration.

Rust-native AI inference & training engine. Block AttnRes linear-time transformer with profile-driven GPU dispatch, TurboQuant, GGUF/SafeTensors, LoRA, multimodal (vision/audio/video), FerrisRes Armor security. 39K LOC, 951 tests. Adapts to any GPU via wgpu — Intel iGPU to H100. No Python.

Alternative to OpenClaw for macOS & iOS Swift builds; Openclaw vocal assistant with full machine access. 讓你的蘋果設備更加智能，以及個性化本地部署。

A smart CLI tool powered by OpenAI to assist with terminal commands, answer questions, and provide context-aware help. Automatically detects your working directory and supports piped input. Streamline your workflow with AI! 🚀✨

Automated PR reviews powered by AI. Plug into any GitHub repo in minutes. Supports Groq, Gemini, Anthropic, and OpenAI with multi-provider fallback and key rotation. Get actionable, context-aware code feedback on every pull request without slowing down your team. Zero dependencies beyond requests.

Code analysis CLI - code review, bugs, security, docs, refactoring. Multi-provider LLM, SARIF output, CI-ready.

Assistant IA souverain multiplateforme intégrant Albert, les API compatibles OpenAI, le RAG avec Qdrant et les serveurs MCP.

AI-assisted context management and prompt compression toolkit for developer productivity, ADR workflows, and LLM token optimization.

Open-source, security-first AI agent that runs 100% locally. Provider-agnostic CLI + dashboard for agentic workflows, encrypted secrets, deterministic execution traces, and multi-step automation.

Find your forgotten side projects and figure out what to ship next. Scans local + GitHub, diagnoses health with Claude, suggests next steps.

Python agent harness — 5 LLM providers, 7 real tools, sub-agent spawning, hooks, skills"

Observable AI agent runtime with built-in execution tracing. Inspect, replay, diff, and debug agent behavior step by step. Model-agnostic (Claude, Ollama, OpenAI, Gemini). Built on Strands Agents SDK.

Claude Code plugin for React/Next.js — multi-agent orchestration, Figma-to-code, TDD, Harness Engineering, RTK, Obsidian

VectorSEO is a local AI SEO analysis tool with web scraping, AI based seo report generation, fine tuned AI Prompts for chats and seo optimizations.

🦑 Hire a PM. Get a company. — Open-source AI PM for solopreneurs: dev team, marketing team, creator team, all from Telegram

Claude Code skill: decide when to render output as HTML over Markdown — based on Thariq Shihipar's html-effectiveness examples. Bilingual (zh-CN / en).

Neuroplex is a cutting-edge AI Agent platform that combines FastAPI, Vue.js, an AI Engine, Neo4j, and Milvus to enable smart knowledge management and intelligent Q&A.

Single-binary web scraper for AI agents. Headless Chrome + Readability → clean Markdown. Up to 99% token savings. Zero dependencies. Built-in MCP server.

AI-powered lakehouse platform for IT job market analytics

Local-first AI dashboard for med students. Lives on your Mac, drives your apps, knows your week. Real Anki / Outlook / iMessage / UWorld / Spotify integrations + a Claude agent with tool access.

Autonomous Claude Code agent — 14 specialized agents, 10-parallel execution, project-specific skill learning, mechanical checkpointing, wave-based planning with acceptance gates, caveman ultra (~75% token savings). One prompt → finished project.

🚀 Enhance Claude Code with Gemini CLI for better code generation, reviews, testing, documentation, and architecture analysis.

AI agent skills for onboarding merchants to UCP (Universal Commerce Protocol). Audit → Profile → Catalog → Checkout → Validate.

An issue-driven AI coding agent for reliable GitHub execution with plan-first orchestration and validator-gated completion.

Deterministic Go code editing for LLM agents. AST-based CLI and MCP server that replaces Edit, Read, and Grep on .go files for Claude Code, Cursor, and any agent.

An example of Amazon Bedrock Agent integration with external APIs via Lambda.

A ultra-lightweight AI agent that communicates with the OpenRouter API and executes shell commands.

The user sees text that doesn't exist = Chrome's font settings + a malicious OpenType font + an AI agent's legitimate permissions. Here's the full chain and why it's hard to operationalize.

A Model Context Protocol (MCP) server that exposes Kali Linux penetration testing tools as structured, callable tools for large language models. Designed for integration with VS Code GitHub Copilot and any MCP-compatible LLM client.

Secondary LANE | Windows version. Turn ChatGPT into a real coding agent on your machine.

A mobile-first VC brief agent that turns YouTube and RSS signals into explainable Feishu daily briefings.

A standalone desktop workspace for Ask, Plan, and Agent workflows, built on GitHub Models and the Copilot SDK.

A no-fluff system prompt for Codex and coding agents.

An AI-powered blockchain agent that can interact with the Abstract Testnet blockchain. Built with OpenAI's Assistant API and viem.