Code agents

Anvil-code — autonomous coding agent that runs entirely on your machine. 32B local models + structural-anchor edits, no cloud.

Autonomous Project Manager plugin for Claude Code that orchestrates parallel worker sessions via channels to fetch, implement, verify, and merge Linear tasks end-to-end.

Agent development rules for Claude Code, Cursor, and Windsurf. Build better OpenClaw agents with AI-assisted coding.

Smart Codex OAuth routing for OpenClaw - add more accounts, route work to the best available one automatically, and keep serious workflows moving without API keys or manual account juggling.

Agent orchestration kit — NOP reference implementation for multi-agent task dispatch. Runtime-agnostic at the protocol layer. Apache 2.0.

A playbook for orchestrating multiple AI coding agents on a single codebase

Universal PrMaat bridge — runs your LLM brain locally, posts to rooms remotely. The runtime for cryptographic AI identity on prmaat.com.

A production-grade GO client for the Swarms API, providing a simple and intuitive interface for creating and managing agent swarms.

(OpenCode + Obsidian) ^ Ntizar Mastermind - Multi-agent AI orchestration system with persistent memory, Ebbinghaus decay, and multi-model routing

🤖 My Agent 2.0 — 基于 LangGraph 的 Multi-Agent 对话系统。Supervisor 编排 + 主 Agent 全能 + Coder/Planner 子 Agent 协作

A Claude Code skill for tiered model orchestration across configurable Advisor/Planner/Executor layers

基于混合 AI 引擎的智能演示文稿生成平台。支持风格参考图复刻、全局视觉配置与智能大纲生成，让小白也能零门槛产出高颜值、专业级的 PPT。

A multi-persona reasoning framework with extensible strategies. Run AI analysis through diverse personas, with CLI, API, and Rust core support.

Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination

Semantic RAG pipeline that ingests personal data sources and delivers context-aware briefings. Built with FastAPI, Weaviate, Neo4j, and a 3-provider LLM cascade.

A crew of AI agents that diagnoses and fixes real infrastructure problems — Guardian-controlled, safety-first, built in Rust.

Windows-first local agent supervision skills for Claude Code, Codex, and Kimi Code. 本地 Agent 委托审查与可追溯监督。

MEng Final Year Project - Reinforcement Learned Collision Avoidance

Enables you to convert a PettingZoo environment to a Gym environment while supporting multiple agents (MARL). Gym's default setup doesn't easily support multi-agent environments, but this wrapper resolves that by running each agent in its own process and sharing the environment across those processes.

Voice-first AI agent for retail returns. One command. 🦞 Live demo — click the green orb: https://kelleyhuntpllc.github.io/returnclaw

Autonomous Claude agent fleet in Docker — one orchestrator, N workers, a Redis queue, a north star, and a supervisor that halts polish loops. Rides your Claude Max plan, zero API spend.

Your AI that learns, protects, and works while you sleep. Free, open-source desktop AI platform built in Rust.

🤖 Optimize lead management with an AI-powered CRM assistant that delivers insights and analysis through Google Gemini AI and LangGraph.

A multi-agent blog engine powered by LangGraph, performing deep web research and automated visual asset generation.

PersistenceAI by Leo Louvar - Terminal AI IDE and Agentic Coding Multiplexer. Enterprise-grade terminal IDE with multi-agent AI integration, AI agentic coding, vibe coding, terminal-first design, and full IDE features.

End-to-end generative AI pipeline: text prompt to finished video. Multi-API orchestration (OpenAI, Gemini, ElevenLabs, Sora 2), batch processing, 44 projects shipped.

One prompt, one app. Multi-agent AI engine that builds software projects autonomously.

🏗️ Universal 8-phase methodology for planning and building enterprise-grade, mission-critical software with AI coding agents. Supports Cursor AI, Claude Code, Kimi Code, Windsurf & Google Antigravity. Includes ADR validator, microtask linter & CI/CD templates. ≥99% test coverage. MIT.

Production-ready multi-agent customer support system built with LangGraph. Features supervisor routing, human-in-the-loop approval, async checkpointing, and 3 specialist agents (SQL, FAQ, escalation).

Multi-agent orchestration system with pipeline workflows, shared memory, and cooperative task execution

Multi-agent AI sandbox simulating the 2026 Strait of Hormuz crisis. 4 nations × independent LLM agents × adjustable parameters = emergent geopolitics.

Automate AI trading in Python with Claude agents for market analysis, entries, risk control, and live position management on MetaTrader 5

Multi-model, multi-agent OpenCode config for full-stack and AWS work. Specialist agents for frontend, backend, cloud, security, architect, QA, vision, and docs - with per-agent permissions and delegation rules.

AI 多模型协作任务引擎 — 多轮对话 · Agent团队 · 工作流编排 · 代码沙箱 · Skills系统 · 数据分析

Multi-agent LLM application featuring a simple chatbot, internet search–enabled chatbot, and agentic RAG for document reasoning. Integrates with external tools via Zapier MCP server to showcase orchestration and collaboration across specialized agents.

Bio-inspired optimization pipeline for Claude Code. 3 systems: Slime Mold (explore→prune) → PRISM (perspectives→compile) → Immune (scan→correct→learn). Domain-agnostic.

A structured development partner for Claude Code — learns your style, plans before coding, investigates bugs with Opus, and delegates to specialized agents. Opus-quality decisions at Sonnet-level costs.

Claude Code workhorse vessel with experience journal and task delegation

Stop burning API tokens. 9 algorithmic engines for real-time context optimization, infinite-loop detection, and smart prompt compression.

Novel multi-agent cooperative problem-solving protocol — collective intelligence through structured collaboration

AI-Powered Solana Trading Intelligence | Multi-Agent DeepSeek AI | Real-Time Rug Detection | Reactive Learning System | React Dashboard | 73 Tests

MCP server for the X (Twitter) API — with built-in safety rails for autonomous operation.

Local AI stack that observes a single space: currently runs YOLO for detection, Qwen-VL for vision captions, Whisper for audio, and Llama for reasoning. Logs to SQLite, builds summaries/analytics, and exposes an OpenAI-style chat API.

Autonomous development agent skill — picks tasks from your board, implements, tests, and opens PRs via MCP

Transform any LLM into an autonomous security testing agent with structured prompts for seven-phase vulnerability hunting.

Autonomous AI agent framework for Moltbook with persistent memory, strategic decision-making, and customizable personalities powered by local LLMs

🕹️ Play DevLies, a multiplayer social deduction game for developers, where teams clash as Developers root out hidden Hackers.

Self-hosted autonomous AI agent — runs on your PC, controls your environment, connects to any MCP server.

Autonomous coding agent for Discord — delegate tasks via slash commands, stream live progress in threads, with push approval gates and workspace isolation. Powered by GitHub Copilot SDK.

Assign a GitHub issue, wake up to a PR. Autonomous agent in ~630 lines of bash — cron, flock, and git worktrees on a $10/month VPS.

Agent Attribution Practice (AAP) — architecture decision records on accountability distribution in autonomous AI agents. 10 ADRs + 4 Business AI Quadrants + Phase Separation axis. Harness-neutral practice library extracted from contemplative-agent.

Enable autonomous reverse engineering and recompilation of PlayStation 2 games using a structured OS for LLM agents with persistent memory and workflows

A self-improving coding agent with episodic failure memory. Runs locally. No cloud. No API. Just gets better.

Phase-based iterative execution patterns for AI coding agents — Claude Code, Codex CLI, Gemini CLI

QBBot: A human-like AI UI/UX Inspector using Local VLM (InternVL2) and LLMs to autonomously audit web flows, detect visual bugs, and generate professional QA reports.

Autonomous AI cybersecurity agent — scans, detects, and fixes security vulnerabilities in your codebase continuously.

Safe, local-first autonomous coding agent. Policy-governed, audit-trailed, sandboxed. Works with any LLM.

Rapid Roll is a classic mobile game originally found on Nokia 1280 devices. In the game, the player controls a ball that continuously falls and must land on moving platforms while avoiding spike traps. The objective is to survive as long as possible by staying on platforms and avoiding hazards.

Subconductor is an MCP server that acts as a Persistent State Machine for AI agents. It prevents "context drift" during long refactors by externalizing the task list into a physical manifest. It enables non-linear execution, allowing agents to handle dependencies dynamically while maintaining a transparent, resumable audit trail.

LangChain integration for EnigmAgent — resolve {{PLACEHOLDER}} secrets at the LLM boundary so models never see real API keys

🤖 Build modular AI agents with Alphora, a production-ready framework that simplifies creating powerful and maintainable applications.

AI Agent Evolution Model --- AI Behavior Constitution Framework

Event-sourced persistence for AI agents — append-only journal, SHA-256 blob store, knowledge graph, memory API. Part of the Life Agent OS.

A stateful runtime middleware that adds FSM-based execution semantics, state-aware retry, and structured deterministic paths to browser agents. Designed to reduce redundant visual inference and improve reliability in multi-step web workflows.

A file-driven agent orchestration framework that enables technical startups to run their operations through Claude Code.

Map every integration point in your AI codebase — 13 CWE categories, attack surface score, test coverage gaps. SARIF 2.1.0. No API key.

Runtime approval gates for AI agent tool calls. Intercept payments and emails before execution

A light-weight framework for building AI agents with Native OpenAI API compatibility

Create evidence-bound AI-agent contracts, governed runtime flows, assurance reports, trace/evidence bundles, and falsification-aware IX-CognitionKernel Wave 6 cognition-contract handoff packages. No AGI claim.

The minniest of the mini openclaw-knockoff for protocol testing and micro-sized deployments

A data-driven, cryptographically signed, registry-backed AI operating system, with capability-scoped execution and graph-executable workflows — living inside your projects, running through a recursive MCP that goes as deep as you dare.

Turning API documentation into framework-specific tutorials and reusable example bundles.

Agent orchestration framework for Claude Code — domain experts, security hooks, and self-improving knowledge bases.

Cortex System: The Operating System for AI Engineering. Cure Technical Amnesia.

A centralized processing engine that decomposes big problems into sub-problems, builds solutions as composable building blocks, and uses a layered agent ecosystem (Thinker, Planner, Dispatcher, Orchestrator, Critic, Analyst, Judge, etc.) to break down, document, verify, and solve iteratively.

Autonomous AI agent platform with persistent cognitive memory — 49 MCP tools, OODA cognitive loop, browser automation, and multi-agent orchestration. Give your AI agents a brain that remembers, reasons, and learns.

Eval-driven Customer Support FTE using OpenAI Agents SDK. Multi-agent routing, guardrails, and systematic quality evaluation.

Deterministic, auditable, capability-safe autonomous agent framework in Rust. Event-sourced, replayable, with governed self-evolution.

🤖 Build adaptable AI agents with skill-based systems, enabling efficient context management and seamless integration across any framework.

A deterministic, distributed, capability-safe execution fabric for agent workflows with verifiable replay and certified audit trails

An agent composition framework that builds stacks and compiles specialized subagents for Claude Code

⚡ Next-gen autonomous agent framework with Rust core, time-travel debugging, Wasm sandbox, and 53+ Claude Skills. 100x faster than competitors.

Build and manage AI agents to automate data research, track markets, and run multi-agent workflows with an open-source framework.

Multi-agent specification-driven development (SDD) framework for Claude Code

A small code snippet as a part of "How to Write an Agent" Blog Post

An Agentic MCP server sshclient

QA-Auto is an automated QA testing framework powered by LLMs and browser automation. It reads BDD-style feature files, executes all scenarios, and generates Cucumber-style HTML reports.

AI agent skill for Redux-Saga — 25 rules: effects, fork model, channels, RTK integration. Works with Claude Code, Cursor, Codex, Windsurf.

Make Claude Code actually work like a senior engineer multi agents, token compression, safety hooks, UI pipeline.

Turn natural language into executable code — right in your browser. Lightweight AI chat powered by GPT-4o with sandboxed JavaScript execution.

Prove and compare the AI CLIs you already installed from one command surface or one MCP setup

One-shot host bootstrap for AI-agent-driven development. Sets up WSL2 / Linux / macOS with mise, Docker, Dev Container readiness, and AI agent CLIs (Claude Code, Codex, Copilot, Gemini) plus AI power tools (markitdown, ast-grep, yq, OCR/audio).

A compiler that turns connected knowledge into code, workflows, and agents.

AI-powered Staff Engineer. Automate architectural reviews, debt scanning, and multi-file migrations.

RAG playground test different rag configurations

An AI-agentic ecosystem and unified API integration layer for Laravel.

Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts

This is a Claude AI Skill that transforms Claude into a full-stack, end-to-end penetration testing co-pilot. Drop it into any Claude environment and you instantly have an expert partner that can automate your way.

Single-user agentic ops console — Next.js 15 web app with persistent SQLite memory, multi-agent missions, MCP-driven skills, Tailscale-powered cross-machine bridge, and a mobile PWA. Install: npx @aifusiomc/create-fusio

Scenario Testing for AI Agents