Projects sharing features with Lazycodex

Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software engineering. It enables AI agents to perform codebase modifications, debugging, and Git workflow management while coordinating multiple specialized agents to decompose and execute complex engineering tasks in parallel. The system distinguishes itself through a high degree of isolation and safety, utilizing Git worktrees to create independent working directories for concurrent agents and implementing a tiered permission system that combines user rules, project policies, and OS-level

Lavish-axi is a review toolkit for HTML pages that AI coding agents generate. It opens an agent's HTML artifact in a local browser editor, with the page beside a conversation panel. A reviewer can annotate specific elements or selected text, and those notes go back to the agent as feedback. It ships as an installable skill and plugin package, and a command-line interface lets agents launch sessions, wait for reviewer input, and send replies. The feedback loop is built around long polling. The agent's command blocks until the reviewer sends queued input, ends the session, or disconnects. Outpu

Vibe-coding is an agentic workflow manager and AI coding orchestrator designed to guide autonomous agents through software development. It serves as a development framework that organizes the process of building software using large language models through structured planning, iterative validation, and a defined cycle of implementation. The project distinguishes itself through a focused context management system and project memory bank, which uses dedicated files to maintain consistent architectural context across sessions. It employs constraint-based guidance to enforce project-specific codi

Oh My Hermes (Hermes Orchestrator) is a workflow layer that sits on top of the Hermes agent runtime. It routes requests to staged skills, external coding executors, and verification gates, through chat or a terminal interface. Completion is evidence-gated: every status carries a stage and confidence, and work is marked verified only after tests, reviews, or CI checks have actually passed. It is also distributed as a catalog of installable workflow skills and plugin hooks, for Hermes and other coding-agent hosts. Its main focus is multi-agent coding delegation. Scoped tasks are handed to codin

gstack is an AI agent framework and development workflow system designed to automate the software development lifecycle. It coordinates specialized AI personas to manage tasks across product design, engineering management, and quality assurance, transforming product intent into technical specifications and final releases. The project is distinguished by its deep integration of headless browser automation and semantic code memory. It utilizes a persistent Chromium daemon for web scraping and visual auditing, and implements a searchable knowledge base that logs architectural decisions and repos

Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated

Chinese Novelist Skill is a plugin for coding agents that generates complete Chinese novels of 10 to 50 chapters from a rough idea. It is driven by prompts, templates, and helper scripts rather than a standalone application, and it walks the author through initialization, story questioning, planning, chapter drafting, and validation until a finished manuscript exists. Planning comes first. A short required set of questions covers premise, protagonist, and core conflict, followed by optional deeper preference questions, and any question can be skipped or filled in randomly. The answers become

This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for generating, refactoring, and debugging code. It functions as an AI agent framework and a Model Context Protocol client, connecting AI models to external data sources and tools to automate complex development tasks. The system is distinguished by its use of autonomous AI agents capable of multi-step task execution, including the ability to read files, modify code, and run terminal commands iteratively. It supports recursive agent orchestration through subagent delegation and employ

Kiro is an AI-powered development tool and multi-agent workflow orchestrator. It functions as a context-aware code generator and coding assistant that transforms natural language requirements into structured implementation plans and production-grade code. The system distinguishes itself through multi-agent task decomposition, where complex requirements are broken into sequenced tasks and assigned to specialized agents. It features multi-model orchestration to select specific language models based on reasoning complexity, cost, and latency, and includes a headless command-line interface for id

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

SuperPlane is an open-source, event-driven workflow automation platform that coordinates coding agents, source control, CI, review, and approvals so backlog issues can become review-ready pull requests. Workflows advance by reacting to events from external tools, agents, and people, pausing at each step until the next signal arrives, with humans staying in the loop for the final decision. The delivery pipeline covers planning, agent-driven coding, verification, and review. The platform can evaluate backlog issues to identify which ones coding agents can handle with high confidence, leaving am

This is a Markdown skill file for AI coding agents that reshapes how they reply, aimed at readers with ADHD. Replies open with the next action or answer, break multi-step work into short numbered steps, cap lists at five items, and drop preambles, recaps, closing pleasantries, and tangents. Each reply ends with a single concrete next step. The rules also cover how an agent reports on its work. It restates the current state each turn, gives time estimates in specific minutes, makes completed wins visible, and describes errors in a plain, matter-of-fact way. Side issues are deferred until the c

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

PI-Desktop is a desktop application that runs an AI coding agent on your own machine against a local repository. Projects, sessions, settings, and logs are stored locally, credentials are kept in the system keychain, model requests go straight to your chosen provider, and no telemetry is collected. It is a persistent workspace, independent of any particular editor or terminal, that remembers its state between launches. It is available for macOS, Windows, and Linux. The agent can work in agent, plan, or goal modes: delegate a coding task and review progress, study a project and approve an impl

This project is a comprehensive collection of Python programming education materials, including tutorials, exercises, and curated code samples. It serves as a learning curriculum and software engineering toolkit, utilizing Jupyter Notebooks to combine executable code with descriptive educational text. The repository provides practical implementation guides for building large language model applications, such as retrieval-augmented generation systems, stateful AI agents, and machine learning workflows. It distinguishes itself by offering a structured approach to agentic coding workflows, cover

ai-memory is a self-hosted long-term memory server for coding agents. It captures prompts, tool calls, and session boundaries through lifecycle hooks and compiles them into searchable, git-versioned markdown wiki pages that later sessions can recall. It also acts as a Model Context Protocol server, exposing search, recall, and page read and write operations over standard input and HTTP streaming, and it can run without any language model configured, using rule-based summaries. What sets it apart is that it works across vendors. An installer wires hooks, tool-server entries, routing instructio

Text-to-CAD is a toolkit that lets AI coding agents build parametric 3D models from scripts. Parts and assemblies are written as functions whose arguments are dimensions. Running the script rebuilds the model, which opens in a live browser viewer and exports to STEP, STL, 3MF, GLB or DXF. It is packaged as a set of skills plus a local CAD server that installs as a plugin or extension for Claude Code, Claude Desktop, Codex, Cursor, Gemini and Grok Build. A single-command skill install covers other coding agents. Beyond modeling, the toolkit generates dimensioned ISO engineering drawing PDFs fr

Hermes Workspace is a browser-based workspace for chatting with, supervising, and managing Hermes AI agents. It brings a streaming chat interface, a file browser with a code editor, a browser terminal, and panels for agent memory and skills into one web app. Chat replies stream as they are written, with tool calls, thinking content, and highlighted markdown rendered inline. The interface can connect to a stock agent gateway, OpenAI-compatible servers, or local model runtimes such as Ollama, LM Studio, and vLLM. Beyond single-agent chat, the workspace works as a multi-agent orchestration dashb

This repository is a static analysis of the Claude Code terminal coding assistant, based on a reading of its TypeScript source. It documents how the agent is built, from its startup path and a single shared execution core to the streaming tool-call loop, sub-agents, and terminal interface layers. It is a reference and study resource about the agent rather than the agent itself. The analysis centers on a few areas. One is the shared core that routes queries, sub-agents, tools, and permission checks through the same control flow. Another is memory: layered, file-based records that users can ins

This repository provides reference implementations and templates for multi-agent orchestration, retrieval-augmented generation systems, and human-in-the-loop patterns. It contains a collection of implementation patterns for coordinating multiple AI agents to automate complex business workflows and tasks. The project demonstrates how to decouple operational logic from setup by using structured text files for agent roles and task specifications. It includes guides for integrating vector search and document processing to build question and answer systems based on external knowledge bases, as wel

Scroll-craft is a packaged skill for coding agents such as Codex and Claude Code, and it can also be installed as a Claude Code plugin through a marketplace manifest. It guides an agent through a repeatable workflow for building scroll-driven websites, where scrolling controls video playback, pinned sections, sideways rails, text reveals and background color shifts. Openings are composed as layered parallax heroes, built from separate background, subject, foreground and atmosphere planes that move at different rates. What sets it apart is its emphasis on keeping each generated site distinct.

Anti-slop is a rulebook and skills package for AI coding agents. It loads 40 numbered rules, split into strictness tiers from an absolute hard gate down to purpose checks and quality locks, so that generated designs, copy, and code avoid generic, template-like patterns. Before anything is handed off, a mandatory pass-or-fail delivery report runs in four blocks and requires concrete evidence for each item. Any failure forces a fix and a rerun. The project can guide work while it is being created or audit existing pages, text, and code afterward, listing numbered findings for approval. The work

AgentScope is a multi-agent framework and orchestration platform designed for building and coordinating teams of language model agents. It provides a system for managing multiple agents that collaborate to solve complex tasks through structured communication and state sharing. The project distinguishes itself with a focus on production-ready deployment and security, featuring a multi-tenant hosting service that ensures session isolation between different users. It includes a sandboxed tool execution environment and fine-grained permission controls to manage how agents access system resources

Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran

Hugging Multi-Agent is an orchestration framework and educational resource designed for building collaborative systems of autonomous AI units. It provides a structured approach to defining individual agent roles, communication patterns, and specialized behaviors to solve complex, multi-step tasks. The project functions as a technical guide and tutorial for implementing multi-agent workflows, specifically focusing on the MetaGPT framework. It enables the design of automated software development processes by delegating tasks to specialized agents that interact through structured communication p

Eko is a framework for designing and deploying agentic workflows, featuring an LLM agent workflow orchestrator and a browser automation engine. It provides a server-side process manager for executing system-level operations and managing local files, alongside a human-in-the-loop agent controller for manual oversight and direction during automated decision processes. The system coordinates multi-agent collaboration through role-based partitioning and workflow orchestration, dividing complex tasks into distinct roles and managing execution handoffs. It integrates the Model Context Protocol to s

A2A is a standardized framework designed to enable interoperability, discovery, and orchestration among independent artificial intelligence agents. It provides a common communication protocol that allows heterogeneous agents to exchange data, verify identities, and collaborate across diverse programming languages and computing environments. By establishing a unified messaging standard, the project facilitates the creation of complex, multi-agent workflows where tasks are routed and managed between specialized services. The project distinguishes itself through a capability-based architecture t