awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
zai-org avatar

zai-org/ZCode

0
View on GitHub↗
zcode.z.ai↗

ZCode

ZCode is an AI coding agent harness that runs the agent loop on the user's own machine, coordinating large language model calls with local project files. It is available as a terminal command-line interface that needs no graphical environment, as a browser interface served by a local web server, and as a desktop coding workspace for macOS, Windows, and Linux on both x64 and arm64.

The browser mode hosts the interface and agent backend together, with optional token authentication and network binding for remote access. The agent can also work on codebases over SSH or WSL: on connecting, it uploads the runtime files it needs from the local machine, so the remote target requires no preinstalled setup.

Behavior is extended without changing the core. Reusable skill definitions are discovered from a dedicated skills folder at startup, and installable UI plugins use a page API and host integration to add features inside the application. Data directories, workspace paths, model provider settings, and download locations can be overridden through environment variables and local configuration files.

The repository is a monorepo that separates the agent runtime, user interfaces, and application shells into distinct packages that release together. Releases are built as per-platform archives with checksums, a version index, and an install script that sets up a runnable command.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Agent Harnesses - Provides a harness that runs an AI coding agent loop, coordinating model calls with local files, tools, and commands.
  • Coding Agents - Runs an AI coding agent harness that coordinates large language model calls with local project files to read, edit, and run code.
  • CLI Coding Agent Hosts - Provides an interactive terminal interface backed by a locally running coding agent, with no graphical environment or desktop shell required.
  • Developer AI Assistance - Helps write, edit, and refactor code by running an AI agent that reads local project files and performs multi-step tasks.
  • AI Coding Assistants - Runs an AI coding assistant whose agent loop stays on the user's machine and can operate on SSH or WSL workspaces.
  • Agent Command Line Interfaces - Ships a terminal command-line interface that runs an interactive coding agent on the local machine without any graphical environment.
  • Self-Hosted Agent Servers - Starts a local web server hosting a browser interface and agent backend, with optional token authentication and network binding for remote access.
  • Agent Server Hosting - Hosts the agent backend and browser interface on one local web server with optional token authentication and network binding.
  • Plugin-Extensible Agent Interfaces - Extends the agent application through installable UI plugins with a page API and host integration, alongside reusable skill definitions.
  • Skill Directory Configurations - Scans a dedicated skills folder at startup and registers each skill definition found, so new abilities need no core code changes.
  • Browser-Based Agent Interfaces - Serves a browser interface and agent backend from a local web server, with optional token authentication and network binding for remote access.
  • MCP and Agent Skills - Extends the coding agent through reusable skill definitions discovered from a skills folder, plus plugins and configurable providers.
  • Remote Work Toolkits - Connects to remote workspaces over SSH or WSL and uploads the runtime resources needed so the agent can work on remote codebases.
  • Terminal-Based Coding Workflows - Offers a terminal interface for working with the coding agent on a local machine with no graphical environment required.
  • UI Plugin Hosts - Exposes a page API and host integration so installable UI plugins can add features inside the application without modifying its core.
  • Remote Runtime Bootstrapping - Uploads the needed runtime files from the local machine when connecting to an SSH or WSL target, so remote use needs no preinstalled setup.
  • Local HTTP Servers - Runs a single local web server that serves the browser interface and agent backend, with optional token authentication and network binding.
  • SSH Remote Development Editors - Works on codebases over SSH or WSL, uploading the needed runtime files on connect so remote targets need no preinstalled setup.
  • Local-First Architectures - Runs the agent loop entirely on the user's machine, coordinating model calls with local project files and no cloud-hosted runtime.
  • Desktop Workspace Structuring - Ships a desktop coding workspace application for macOS, Windows, and Linux on x64 and arm64 to work alongside an AI agent.
8,544 stars·2,662 forks·TypeScript·Apache-2.0·2 views

Star history

Star history chart for zai-org/zcodeStar history chart for zai-org/zcode

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does zai-org/zcode do?

ZCode is an AI coding agent harness that runs the agent loop on the user's own machine, coordinating large language model calls with local project files. It is available as a terminal command-line interface that needs no graphical environment, as a browser interface served by a local web server, and as a desktop coding workspace for macOS, Windows, and Linux on both x64 and arm64.

What are the main features of zai-org/zcode?

The main features of zai-org/zcode are: Agent Harnesses, Coding Agents, CLI Coding Agent Hosts, Developer AI Assistance, AI Coding Assistants, Agent Command Line Interfaces, Self-Hosted Agent Servers, Agent Server Hosting.

Which projects share features with zai-org/zcode?

Projects with overlapping indexed features include: mvanhorn/cli-printing-press — Cli Printing Press is a generator that turns an API specification, documentation URL, website, or device into a… kirodotdev/kiro — Kiro is an AI-powered development tool and multi-agent workflow orchestrator. It functions as a context-aware code… cursor/cookbook — This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples… builderz-labs/mission-control — Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets… yetone/cumora — Cumora is a cross-platform team chat where AI agents join humans as teammates in shared rooms, direct messages, and… thunderbird/thunderbolt — Thunderbolt is an open-source, self-hostable AI chat client that runs on web, desktop (macOS, Linux, Windows) and…

Projects sharing features with ZCode

These projects share indexed features with ZCode. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • mvanhorn/cli-printing-pressmvanhorn avatar

    mvanhorn/cli-printing-press

    4,931View on GitHub↗

    Cli Printing Press is a generator that turns an API specification, documentation URL, website, or device into a complete command-line tool and a matching MCP server. The generated tools are built for AI agents: output switches to JSON when piped, a compact mode trims results to key fields, exit codes are typed for usage, authentication, not-found, service, and rate-limit errors, and a dry-run mode previews commands before they change anything. Both the command-line binary and the MCP server share the same HTTP client, authentication, and local store. What sets it apart is how it gets to a spe

    Goai-agentsclicli-generator
    View on GitHub↗4,931
  • kirodotdev/kirokirodotdev avatar

    kirodotdev/Kiro

    4,452View on GitHub↗

    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

    TypeScriptaiidekiro
    View on GitHub↗4,452
  • cursor/cookbookcursor avatar

    cursor/cookbook

    4,158View on GitHub↗

    This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples cover running agents from TypeScript code against local workspaces or cloud runtimes, streaming their output live, and launching them from a terminal. Other examples include a cloud agent kanban dashboard, a task graph orchestrator, an app-prototyping chat, and a realtime voice intake demo. Several samples go beyond a basic quickstart. The kanban dashboard lists cloud agents as cards grouped by status, repository, or branch, previews their artifacts, and launches new agents fro

    TypeScript
    View on GitHub↗4,158
  • builderz-labs/mission-controlbuilderz-labs avatar

    builderz-labs/mission-control

    6,461View on GitHub↗

    Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets operators register and monitor a fleet of agents across runtimes, dispatch tasks to them, review their runs, and track token spend, all from one interface backed by role-based access and an audit log. Work reaches agents through priority queues, direct assignment, cron-driven recurring templates, and multi-step pipelines that chain one agent's output into the next. Agents claim the highest-priority task atomically, and completed work can be routed through a quality-review gate

    TypeScriptagent-observabilityagent-operationsagent-orchestration
    View on GitHub↗6,461
Compare all 30 related projects→