jcode

Name: 1jehuang/jcode
Author: 1jehuang

Coding Agent Harness

Subagents7k stars786 forks● RustMITUpdated today

Editor's note

jcode is a terminal-based coding agent harness written in Rust that wraps LLM providers, including Claude via the Anthropic API, inside a TUI (terminal user interface) designed for running multiple concurrent agent sessions. It supports multi-session workflows where several coding agents operate in parallel, and includes a local embedding system for memory that lets agents retain context across sessions. The tool connects to Claude through direct API access rather than Claude Code or MCP, and also supports OpenAI-compatible endpoints, making it provider-agnostic. A concrete standout is its resource efficiency: with local embeddings disabled, a single jcode session uses roughly 27.8 MB of RAM, compared to 386.6 MB for Claude Code and 3,237 MB for OpenCode at ten concurrent sessions, making it practical to scale parallelized agentic workloads on modest hardware. The primary audience is developers who want to orchestrate multiple AI coding agents simultaneously from the terminal on Linux, macOS, or Windows.

ClaudeWave Trust Score

100/100

✓ Verified

Passed

✓Open-source license (MIT)
✓Actively maintained (<30d)
✓Healthy fork ratio
✓Topics declared
✓Documented (README)

Last scanned: 6/11/2026

Install as a Claude Code subagent

Method: Clone

Terminal

git clone https://github.com/1jehuang/jcode && cp jcode/*.md ~/.claude/agents/

1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).

2. Start a new Claude Code session to load the agents.

3. Delegate work to them with the Task/Agent tool or by name.

Installable items

1 items in this repository

optimizationSkill

Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.

Install

Use cases

AI / ML Dev Tools Creative

About

Subagents overview

<div align="center">

# jcode

[![Latest Release](https://badgen.net/github/release/1jehuang/jcode?icon=github)](https://github.com/1jehuang/jcode/releases)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue?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)
[![Last Commit](https://badgen.net/github/last-commit/1jehuang/jcode/master?icon=github)](https://github.com/1jehuang/jcode/commits/master)
[![GitHub Stars](https://badgen.net/github/stars/1jehuang/jcode?icon=github)](https://github.com/1jehuang/jcode/stargazers)
[![Discord](https://img.shields.io/badge/Discord-Join%20Community-5865F2?style=flat-square&logo=discord&logoColor=white)](https://discord.gg/nBe9vGyK9a)

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>
          </tr>
        </thead>
        <tbody>
          <tr>
            <td><strong>jcode (local embedding off)</strong></td>
            <td align="right"><strong>27.8 MB</strong></td>
            <td align="right">baseline</td>
          </tr>
          <tr>
            <td><strong>jcode</strong></td>
            <td align="right"><strong>167.1 MB</strong></td>
            <td align="right"><strong>6.0× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>pi</strong></td>
            <td align="right"><strong>144.4 MB</strong></td>
            <td align="right"><strong>5.2× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Codex CLI</strong></td>
            <td align="right"><strong>140.0 MB</strong></td>
            <td align="right"><strong>5.0× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>OpenCode</strong></td>
            <td align="right"><strong>371.5 MB</strong></td>
            <td align="right"><strong>13.4× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>GitHub Copilot CLI</strong></td>
            <td align="right"><strong>333.3 MB</strong></td>
            <td align="right"><strong>12.0× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Cursor Agent</strong></td>
            <td align="right"><strong>214.9 MB</strong></td>
            <td align="right"><strong>7.7× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Claude Code</strong></td>
            <td align="right"><strong>386.6 MB</strong></td>
            <td align="right"><strong>13.9× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Antigravity CLI</strong></td>
            <td align="right"><strong>243.7 MB</strong></td>
            <td align="right"><strong>8.8× more RAM</strong></td>
          </tr>
        </tbody>
      </table>
    </td>
    <td width="24"></td>
    <td valign="top" align="center" width="50%">
      <strong>10 active sessions</strong>
      <table>
        <thead>
          <tr>
            <th>Tool</th>
            <th>PSS</th>
            <th>Comparison</th>
          </tr>
        </thead>
        <tbody>
          <tr>
            <td><strong>jcode (local embedding off)</strong></td>
            <td align="right"><strong>117.0 MB</strong></td>
            <td align="right">baseline</td>
          </tr>
          <tr>
            <td><strong>jcode</strong></td>
            <td align="right"><strong>260.8 MB</strong></td>
            <td align="right"><strong>2.2× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>pi</strong></td>
            <td align="right"><strong>833.0 MB</strong></td>
            <td align="right"><strong>7.1× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Codex CLI</strong></td>
            <td align="right"><strong>334.8 MB</strong></td>
            <td align="right"><strong>2.9× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>OpenCode</strong></td>
            <td align="right"><strong>3237.2 MB</strong></td>
            <td align="right"><strong>27.7× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>GitHub Copilot CLI</strong></td>
            <td align="right"><strong>1756.5 MB</strong></td>
            <td align="right"><strong>15.0× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Cursor Agent</strong></td>
            <td align="right"><strong>1632.4 MB</strong></td>
            <td align="right"><strong>14.0× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Claude Code</strong></td>
            <td align="right"><strong>2300.6 MB</strong></td>
            <td align="right"><strong>19.7× more RAM</strong></td>
          </tr>
          <tr>
            <td><strong>Antigravity CLI</strong></td>
            <td align="right"><strong>1021.2 MB</strong></td>
            <td align="right"><strong>8.7× more RAM</strong></td>
          </tr>
        </tbody>
      </table>
    </td>
  </tr>
</table>

</div>

### Time to first frame

<div align="center">

| Tool | Time to first frame | Range | Comparison |
|---|---:|---:|---:|
| **jcode** | **14.0 ms** | 10.1–19.3 ms | baseline |
| **Antigravity CLI** | **383.5 ms** | 363.1–415.4 ms | **27.4× slower** |
| **pi** | **590.7 ms** | 369.6–934.8 ms | **42.2× slower** |
| **Codex CLI** | **882.8 ms** | 742.3–1640.9 ms | **63.1× slower** |
| **OpenCode** | **1035.9 ms** | 922.5–1104.4 ms | **74.0× slower** |
| **GitHub Copilot CLI** | **1518.6 ms** | 1357.4–1826.8 ms | **108.5× slower** |
| **Cursor Agent** | **1949.7 ms** | 1711.0–2104.8 ms | **139.3× slower** |
| **Claude Code** | **3436.9 ms** | 2032.7–8927.2 ms | **245.5× slower** |

</div>

Measured on this Linux machine across 10 interactive PTY launches.

### Time to first input
(time until typed probe text appears on the rendered screen; Antigravity uses its internal input-ready log marker because the sign-in screen suppresses probe echo.)
<div align="center">

| Tool | Time to first input | Range | Comparison |
|---|---:|---:|---:|
| **jcode** | **48.7 ms** | 30.3–62.7 ms | baseline |
| **Antigravity CLI** | **383.7 ms** | 363.4–415.7 ms | **7.9× slower** |
| **pi** | **596.4 ms** | 373.9–955.2 ms | **12.2× slower** |
| **Codex CLI** | **905.8 ms** | 760.1–1675.7 ms | **18.6× slower** |
| **OpenCode** | **1047.9 ms** | 931.1–1116.9 ms | **21.5× slower** |
| **GitHub Copilot CLI** | **1583.4 ms** | 1422.8–1880.0 ms | **32.5× slower** |
| **Cursor Agent** | **1978.7 ms** | 1727.3–2130.0 ms | **40.6× slower** |
| **Claude Code** | **3512.8 ms** | 2137.4–9002.0 ms | **72.2× slower** |

</div>

Measured on this Linux machine across 10 interactive PTY launches. Antigravity CLI was unauthenticated for this run; its sign-in screen rendered normally and emitted an internal `CLI ready for user input` marker, but did not echo the typed probe.

### Additional clients / memory scaling

<div align="center">

| Tool | Extra PSS per added session | Comparison |
|---|---:|---:|
| **jcode (local embedding off)** | **~9.9 MB** | baseline |
| **jcode** | **~10.4 MB** | **1.1× more RAM** |
| **pi** | **~76.5 MB** | **7.7× more RAM** |
| **Codex CLI** | **~21.6 MB** | **2.2× more RAM** |
| **OpenCode** | **~318.4 MB** | **32.2× more RAM** |
| **GitHub Copilot CLI** | **~158.1 MB** | **16.0× more RAM** |
| **Cursor Agent** | **~157.5 MB** | **15.9× more RAM** |
| **Claude Code** | **~212.7 MB** | **21.5× more RAM** |
| **Antigravity CLI** | **~86.4 MB** | **8.7× more RAM** |

</div>
versions tested for this corrected memory rerun:

- `jcode v0.9.1888-dev (be386f2)`
- `pi 0.62.0`
- `codex-cli 0.120.0`
- `opencode 1.0.203`
- `GitHub Copilot CLI 1.0.24` for the 1-session rerun, `GitHub Copilot CLI 1.0.27` for the 10-session rerun
- `Cursor Agent 2026.04.08-a41fba1`
- `Claude Code 2.1.86 (Claude Code)`
- `Antigravity CLI 1.0.0`

<div align="center">

  <a href="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-performance-demo.mp4">
    <img src="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-performance-demo.webp" alt="jcode performance demonstration" width="900">
  </a>

  <p><em>jcode performance demonstration</em></p>

</div>


---

## Memory (Agent memory)

Jcode embeds each turn/response as a semantic vector. Every turn does queries a graph of memories to efficiently find related memory entries via a cosine similarity check. The embedding hits are fed into the conversation, or optionally uses a memory sideagent

Topics

aiclaudeclicoding-agentllmmcpopenairustterminaltui

Frequently asked

What people ask about jcode

What is 1jehuang/jcode?

1jehuang/jcode is subagents for the Claude AI ecosystem. Coding Agent Harness It has 7k GitHub stars and was last updated today.

How do I install jcode?

You can install jcode by cloning the repository (https://github.com/1jehuang/jcode) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is 1jehuang/jcode safe to use?

Our security agent has analyzed 1jehuang/jcode and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains 1jehuang/jcode?

1jehuang/jcode is maintained by 1jehuang. The last recorded GitHub activity is from today, with 91 open issues.

Are there alternatives to jcode?

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

1-click deploy

Deploy jcode to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Vercel Railway Render

Embeddable badge

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Markdown (README)

[![Featured on ClaudeWave](https://claudewave.com/api/badge/1jehuang-jcode)](https://claudewave.com/repo/1jehuang-jcode)

HTML

<a href="https://claudewave.com/repo/1jehuang-jcode"><img src="https://claudewave.com/api/badge/1jehuang-jcode" alt="Featured on ClaudeWave: 1jehuang/jcode" width="320" height="64" /></a>

More Subagents

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

214.4k32.9kJavaScript

Subagentsai-agentsanthropicInstall