1jehuang / jcode

jcode is the next-generation coding agent harness designed to raise the skill ceiling. It is built for multi-session workflows, infinite customizability, and high performance. jcode 是下一代编码代理（coding agent）框架，旨在提升开发者的技能上限。它专为多会话工作流、无限可定制性及高性能而构建。

Features · Install · Quick Start · Further Reading · Contributing

功能 · 安装 · 快速入门 · 进阶阅读 · 贡献指南

Installation

安装

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. 需要 Windows、Homebrew、源码构建、提供商设置，或者想让你的代理帮你完成安装？请跳转至详细安装指南。

Performance & Resource Efficiency

性能与资源效率

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. jcode 的构建目标是尽可能实现高性能和资源高效。每一项指标都经过极致优化，这对扩展多会话工作流至关重要。以下我们选取了一些指标来展示其差异：内存占用与启动速度。

(Note: Detailed performance tables comparing jcode with pi, Codex CLI, OpenCode, GitHub Copilot CLI, Cursor Agent, and Claude Code are provided in the original text, highlighting jcode’s superior efficiency in RAM usage and latency.) （注：原文提供了详细的性能对比表，将 jcode 与 pi、Codex CLI、OpenCode、GitHub Copilot CLI、Cursor Agent 及 Claude Code 进行了对比，突显了 jcode 在内存占用和延迟方面的卓越效率。）

Memory (Agent memory)

记忆（代理记忆）

Jcode embeds each turn/response as a semantic vector. Every turn 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 which verifies the memories are relevant, and potentially does more work for information retrieval before injecting into the conversation. Jcode 将每一轮对话/响应嵌入为语义向量。每一轮对话都会查询记忆图谱，通过余弦相似度检查高效查找相关的记忆条目。这些嵌入匹配结果会被输入到对话中，或者选择性地使用一个记忆辅助代理（memory sideagent）来验证记忆的相关性，并在注入对话前进行额外的信息检索工作。

This results in a human-like memory system which allows the agent to automatically recall relevant information to the conversation without actively calling memory tools or being a token burner. 这带来了一种类似人类的记忆系统，使代理能够自动回溯对话中的相关信息，而无需主动调用记忆工具或消耗大量 Token。

To have memories which are retrieved, they must also be extracted and stored. Every so often (semantic drift, K turns since last extraction, session end, etc), memories are extracted via a memory sideagent, and put into the memory graph. 为了实现记忆检索，记忆必须先被提取并存储。系统会定期（基于语义漂移、自上次提取以来的 K 轮对话、会话结束等触发条件）通过记忆辅助代理提取记忆，并将其存入记忆图谱中。

UI: Side panels, Diagrams, Info Widgets, rendering, scrolling, alignment

用户界面：侧边栏、图表、信息小部件、渲染、滚动与对齐

The side panel is a place for auxiliary information. Tell your jcode agent to load a file into the side panel and see it update in real time, or tell your agent to write directly to the side panel, or use it as a diff viewer. 侧边栏是存放辅助信息的地方。你可以让 jcode 代理将文件加载到侧边栏并实时查看更新，或者让代理直接写入侧边栏，亦或是将其用作差异对比查看器（diff viewer）。

The side panel (and chat) is able to render mermaid diagrams inline. To make this possible, I created a new mermaid rendering library to render diagrams 1800x faster. It has no browser or Typescript dependency. See https://github.com/1jehuang/mermaid-rs-renderer 侧边栏（以及聊天窗口）能够内联渲染 Mermaid 图表。为了实现这一点，我创建了一个新的 Mermaid 渲染库，使图表渲染速度提升了 1800 倍。它不依赖浏览器或 TypeScript。详情请见：https://github.com/1jehuang/mermaid-rs-renderer

To show you important information without taking space away from the screen that could be used for responses, I developed info widgets. Info widgets will only ever take up the negative space on the screen to show you information, and will get out of the way if there isn’t any. 为了在不占用屏幕响应空间的前提下展示重要信息，我开发了信息小部件（info widgets）。信息小部件仅占用屏幕上的空白区域来显示信息，如果没有信息，它们会自动隐藏。

Jcode can render at over a thousand fps. Your monitor will not have the refresh rate to show you, but this means you will not have silly flicker problems. Jcode 的渲染速度可超过每秒千帧。虽然你的显示器刷新率可能无法完全体现，但这确保了你不会遇到恼人的闪烁问题。

Swarm

集群（Swarm）

Spawn two or more agents in the same repo, and they will automatically… 在同一个仓库中生成两个或多个代理，它们将自动……