The most intelligent agent harness for code
How to install jcode?
1jehuang/jcode
$git clone https://github.com/1jehuang/jcodeInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install jcode by running `git clone https://github.com/1jehuang/jcode`, then use it for the current task and follow its documentation at https://github.com/1jehuang/jcode.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | # jcode |
| 4 | |
| 5 | [](https://github.com/1jehuang/jcode/releases) |
| 6 | [](LICENSE) |
| 7 | [](https://github.com/1jehuang/jcode/releases) |
| 8 | [](https://github.com/1jehuang/jcode/commits/master) |
| 9 | [](https://github.com/1jehuang/jcode/stargazers) |
| 10 | [](https://discord.gg/nBe9vGyK9a) |
| 11 | |
| 12 | The next generation coding agent harness to raise the skill ceiling. <br> |
| 13 | Built for multi-session workflows, infinite customizability, and performance. |
| 14 | |
| 15 | <br> |
| 16 | |
| 17 | <a href="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-memory-demo.mp4"> |
| 18 | <img src="https://github.com/1jehuang/jcode/releases/download/readme-assets/jcode-memory-demo.webp" alt="jcode memory demonstration" width="800"> |
| 19 | </a> |
| 20 | |
| 21 | <br> |
| 22 | |
| 23 | [Website](https://jcode.sh) · [Features](#features) · [Install](#installation) · [Quick Start](#quick-start) · [Further Reading](#further-reading) · [Contributing](CONTRIBUTING.md) |
| 24 | |
| 25 | </div> |
| 26 | |
| 27 | --- |
| 28 | |
| 29 | <div align="center"> |
| 30 | |
| 31 | ## Installation |
| 32 | |
| 33 | </div> |
| 34 | |
| 35 | ```bash |
| 36 | # macOS & Linux |
| 37 | curl -fsSL https://jcode.sh/install | bash |
| 38 | ``` |
| 39 | |
| 40 | ```powershell |
| 41 | # Windows 11 (PowerShell 5.1+) |
| 42 | irm https://jcode.sh/install.ps1 | iex |
| 43 | ``` |
| 44 | |
| 45 | Need Homebrew, source builds, provider setup, or want an agent to set it up for you? |
| 46 | [Jump to detailed installation](#detailed-installation). |
| 47 | |
| 48 | --- |
| 49 | |
| 50 | |
| 51 | <div align="center"> |
| 52 | |
| 53 | ## Performance & Resource Efficiency |
| 54 | |
| 55 | </div> |
| 56 | |
| 57 | 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. |
| 58 | |
| 59 | ### RAM comparison |
| 60 | |
| 61 | <div align="center"> |
| 62 | |
| 63 | <table> |
| 64 | <tr> |
| 65 | <td valign="top" align="center" width="50%"> |
| 66 | <strong>1 active session</strong> |
| 67 | <table> |
| 68 | <thead> |
| 69 | <tr> |
| 70 | <th>Tool</th> |
| 71 | <th>PSS</th> |
| 72 | <th>Comparison</th> |
| 73 | </tr> |
| 74 | </thead> |
| 75 | <tbody> |
| 76 | <tr> |
| 77 | <td><strong>jcode (local embedding off)</strong></td> |
| 78 | <td align="right"><strong>27.8 MB</strong></td> |
| 79 | <td align="right">baseline</td> |
| 80 | </tr> |
| 81 | <tr> |
| 82 | <td><strong>jcode</strong></td> |
| 83 | <td align="right"><strong>167.1 MB</strong></td> |
| 84 | <td align="right"><strong>6.0× more RAM</strong></td> |
| 85 | </tr> |
| 86 | <tr> |
| 87 | <td><strong>pi</strong></td> |
| 88 | <td align="right"><strong>144.4 MB</strong></td> |
| 89 | <td align="right"><strong>5.2× more RAM</strong></td> |
| 90 | </tr> |
| 91 | <tr> |
| 92 | <td><strong>Codex CLI</strong></td> |
| 93 | <td align="right"><strong>140.0 MB</strong></td> |
| 94 | <td align="right"><strong>5.0× more RAM</strong></td> |
| 95 | </tr> |
| 96 | <tr> |
| 97 | <td><strong>OpenCode</strong></td> |
| 98 | <td align="right"><strong>371.5 MB</strong></td> |
| 99 | <td align="right"><strong>13.4× more RAM</strong></td> |
| 100 | </tr> |
| 101 | <tr> |
| 102 | <td><strong>GitHub Copilot CLI</strong></td> |
| 103 | <td align="right"><strong>333.3 MB</strong></td> |
| 104 | <td align="right"><strong>12.0× more RAM</strong></td> |
| 105 | </tr> |
| 106 | <tr> |
| 107 | <td><strong>Cursor Agent</strong></td> |
| 108 | <td align="right"><strong>214.9 MB</strong></td> |
| 109 | <td align="right"><strong>7.7× more RAM</strong></td> |
| 110 | </tr> |
| 111 | <tr> |
| 112 | <td><strong>Claude Code</strong></td> |
| 113 | <td align="right"><strong>386.6 MB</strong></td> |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
