# jcode — Coding Agent Harness CLI + MCP

> A multi-session coding agent harness with fast local TUI, memory features, and MCP support; verified 6065★, pushed 2026-05-14.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

```bash
brew install jcode
# or (README):
curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash
jcode --help
```

## Intro

A multi-session coding agent harness with fast local TUI, memory features, and MCP support; verified 6065★, pushed 2026-05-14.

**Best for:** Builders running multi-session coding agents who care about performance and control

**Works with:** macOS/Linux/Windows; integrates with MCP-capable clients per README

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub: 6065 stars · 646 forks · pushed 2026-05-14.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `jcode`.

## Main

- Use jcode as a harness (not just a chat): keep separate sessions per task/branch to reduce context mixing and rework.

- Start with the README install script, then lock in your provider setup before running longer sessions.

- Treat performance as a feature: the README includes concrete RAM comparisons for multi-session workflows.

- When you need tools, prefer MCP-backed integrations so the agent can call structured actions instead of free-form shell guesses.

### README (excerpt)

<div align="center">

**jcode**

[![Latest Release](https://img.shields.io/github/v/release/1jehuang/jcode?style=flat-square)](https://github.com/1jehuang/jcode/releases)
[![License](https://img.shields.io/github/license/1jehuang/jcode?style=flat-square)](LICENSE)
[![Platforms](https://img.shields.io/badge/platforms-Linux%20%7C%20macOS%20%7C%20Windows-blue?style=flat-square)](https://github.com/1jehuang/jcode/releases)
[![Commit Activity](https://img.shields.io/github/commit-activity/m/1jehuang/jcode?style=flat-square)](https://github.com/1jehuang/jcode/commits/master)
[![GitHub Stars](https://img.shields.io/github/stars/1jehuang/jcode?style=flat-square)](https://github.com/1jehuang/jcode/stargazers)

The next generation coding agent harness to raise the skill ceiling. <br>
Built for multi-session workflows, infinite customizability, and performance. 

<br>

<a href="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-memory-demo.mp4">
  <img src="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-memory-demo.webp" alt="jcode memory demonstration" width="800">
</a>

<br>

[Features](#features) · [Install](#installation) · [Quick Start](#quick-start) · [Further Reading](#further-reading) · [Contributing](CONTRIBUTING.md)

</div>

---

<div align="center">

## Installation

</div>

```bash
**macOS & Linux**
curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash
```

Need Windows, Homebrew, source builds, provider setup, or tell your agent to set it up for you?
[Jump to detailed installation](#detailed-installation).

---


<div align="center">

## Performance & Resource Efficiency

</div>

jcode is built to be as performant and resource efficient as possible. Every metric is optimized to the bone, which is important for scaling multi-session workflows. Here we sample a few metrics to show the difference: RAM usage and boot up.

### RAM comparison

<div align="center">

<table>
  <tr>
    <td valign="top" align="center" width="50%">
      <strong>1 active session</strong>
      <table>
        <thead>
          <tr>
            <th>Tool</th>
            <th>PSS</th>
            <th>Comparison</th>


### Source-backed notes

- README includes an install script entrypoint `scripts/install.sh` and a Homebrew formula (`brew install jcode`).
- README lists a performance section with RAM comparisons for 1 vs 10 active sessions.
- GitHub topics include `coding-agent`, `mcp`, and `tui` (verified via GitHub API).

### FAQ

- **Is jcode free to use?**: Yes—it's MIT licensed per GitHub license metadata.
- **How do I install it on macOS?**: README shows Homebrew (`brew install jcode`) and a curl install script.
- **Does it support MCP?**: Yes—GitHub topics and README positioning mention MCP support; verify client configuration in the repo docs.

## Source & Thanks

> Created by [1jehuang](https://github.com/1jehuang). Licensed under MIT.
>
> [1jehuang/jcode](https://github.com/1jehuang/jcode) — ⭐ 6065

Thanks to the upstream maintainers and contributors for publishing this work under an open license.

---

<!-- ZH -->

## Quick Use

```bash
brew install jcode
# or (README):
curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash
jcode --help
```

## Intro

jcode 是面向多会话的编码 Agent Harness：TUI + 记忆能力 + MCP 支持，适合把代码修改拆成可复用会话并减少上下文串台；已验证 6065★，更新于 2026-05-14。

**Best for:** 希望运行多会话编码 agent，并重视性能与可控性的开发者

**Works with:** macOS/Linux/Windows；可与支持 MCP 的客户端配合使用（见 README）

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub：6065 stars · 646 forks；最近更新 2026-05-14。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口：`jcode`。

## Main

- 把 jcode 当“harness”用：按任务/分支拆会话，减少上下文串台与返工。

- 先按 README 的安装脚本跑通，再把模型/Provider 配好，避免长会话中途断档。

- 把性能当能力：README 给出了多会话场景下的 RAM 对比数据，可作为选型依据。

- 需要工具调用时优先走 MCP：用结构化工具减少 agent 的自由发挥与误操作。

### README (excerpt)

<div align="center">

**jcode**

[![Latest Release](https://img.shields.io/github/v/release/1jehuang/jcode?style=flat-square)](https://github.com/1jehuang/jcode/releases)
[![License](https://img.shields.io/github/license/1jehuang/jcode?style=flat-square)](LICENSE)
[![Platforms](https://img.shields.io/badge/platforms-Linux%20%7C%20macOS%20%7C%20Windows-blue?style=flat-square)](https://github.com/1jehuang/jcode/releases)
[![Commit Activity](https://img.shields.io/github/commit-activity/m/1jehuang/jcode?style=flat-square)](https://github.com/1jehuang/jcode/commits/master)
[![GitHub Stars](https://img.shields.io/github/stars/1jehuang/jcode?style=flat-square)](https://github.com/1jehuang/jcode/stargazers)

The next generation coding agent harness to raise the skill ceiling. <br>
Built for multi-session workflows, infinite customizability, and performance. 

<br>

<a href="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-memory-demo.mp4">
  <img src="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-memory-demo.webp" alt="jcode memory demonstration" width="800">
</a>

<br>

[Features](#features) · [Install](#installation) · [Quick Start](#quick-start) · [Further Reading](#further-reading) · [Contributing](CONTRIBUTING.md)

</div>

---

<div align="center">

## Installation

</div>

```bash
**macOS & Linux**
curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash
```

Need Windows, Homebrew, source builds, provider setup, or tell your agent to set it up for you?
[Jump to detailed installation](#detailed-installation).

---


<div align="center">

## Performance & Resource Efficiency

</div>

jcode is built to be as performant and resource efficient as possible. Every metric is optimized to the bone, which is important for scaling multi-session workflows. Here we sample a few metrics to show the difference: RAM usage and boot up.

### RAM comparison

<div align="center">

<table>
  <tr>
    <td valign="top" align="center" width="50%">
      <strong>1 active session</strong>
      <table>
        <thead>
          <tr>
            <th>Tool</th>
            <th>PSS</th>
            <th>Comparison</th>


### Source-backed notes

- README 提供安装脚本入口 `scripts/install.sh`，并给出 Homebrew 安装方式（`brew install jcode`）。
- README 包含性能章节：对比 1 与 10 个活跃会话的 RAM 使用。
- GitHub topics 包含 `coding-agent`、`mcp`、`tui`（已通过 GitHub API 复核）。

### FAQ

- **jcode 是免费的吗？**：是的：仓库许可证为 MIT（已通过 GitHub 元数据复核）。
- **macOS 怎么安装？**：README 提供 Homebrew（`brew install jcode`）与 curl 安装脚本两种方式。
- **支持 MCP 吗？**：支持：仓库 topics 与 README 说明包含 MCP；具体配置以仓库文档为准。

## Source & Thanks

> Created by [1jehuang](https://github.com/1jehuang). Licensed under MIT.
>
> [1jehuang/jcode](https://github.com/1jehuang/jcode) — ⭐ 6065


---
Source: https://tokrepo.com/en/workflows/jcode-coding-agent-harness-cli-mcp
Author: MCP Hub