GitPad
How it works
Back to board

1jehuang/jcode

1jehuang · personal account · GitHub id 94247773
GitHub

High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows

swarmsaiai-agentai-coding-agentclaudeclicoding-agent
Verify the dev 948 followerson GitHub since 202161 public repos SF
@1jehuangjcode.sh

Straight from the GitHub profile. The social links are the ones GitHub shows on github.com/1jehuang: nothing here is submitted to GitPad.

Stars
21k
Velocity
71.8★/day
Forks
2.5k
Language
Rust
Created
2026-01-05 (10mo)
Last push
2026-10-28
Category
swarms
GitPad score
97/100
Fee lock

When this repo launches on GitPad, 100% of creator fees are locked on-chain to 1jehuang's GitHub vault. The split can never be changed after launch, by anyone. 1jehuang claims by connecting GitHub on pump.fun.

e7CwYA4cfKa17rEzPzdCs5JAwKjZZ9RkU8xzzmGTyES
vault not created
Vault on Solscan How the lock works

In short

jcode is a coding agent harness written in Rust, aimed at running many agents in parallel on a single machine. The project's README reports memory and startup benchmarks against several other coding agent CLIs, claiming lower RAM use per additional session and faster time to first input, though these figures are self-reported and the methodology is only partly described. Its distinguishing feature is a server-managed swarm mode in which agents working in the same repository are notified when files they have read are edited by another agent, can message one another directly or by broadcast, and can spawn worker agents to split up tasks, with the main agent acting as coordinator.

Written by GitPad research from the repo’s public material. The full text follows below.

README · straight from GitHub

1jehuang/jcode | Trendshift

jcode halftone donut logo

jcode

High-performance coding agents.
Run dozens of agents in parallel without melting your machine. More agents, less RAM, no lag.

Last Commit GitHub Stars GitHub Downloads

Discord Y Combinator X (Twitter)

jcode performance demonstration

jcode performance demonstration (1x speed)

jcode YC launch video

Installation

# macOS & Linux
curl -fsSL https://jcode.sh/install | bash

Benches

RAM per additional session (headless)

Tool First session Each additional session Comparison (additional)
jcode 71.3 MB ~3.3 MB baseline
OpenCode 637.1 MB ~5.9 MB 1.8× more RAM
pi 84.0 MB ~79.6 MB 24.1× more RAM
Claude Code 272.9 MB ~169.3 MB 51.3× more RAM
Codex CLI 398.6 MB ~194.1 MB 58.8× more RAM

Reproduce.

Time to first input

Time until typed text appears on screen, across 10 interactive launches.

Tool Time to first input Comparison
jcode 19.1 ms baseline
pi 596.4 ms 31.2× slower
Codex CLI 905.8 ms 47.4× slower
OpenCode 1047.9 ms 54.9× slower
Claude Code 3512.8 ms 183.9× slower

Full numbers on jcode.sh.

Screenshots

Browse the interactive gallery on jcode.sh.

Jcode rendering screenshots inline after reading image files
Inline images		 Jcode resume menu with a session list and preview
Resume menu
Jcode rendering LaTeX mathematics inline
Inline LaTeX		 Jcode warning that the prompt cache went cold
Cache cold notification

Swarm

Spawn two or more agents in the same repo, and they will automatically be managed by the server to allow native collaboration. When agent A edits a file that agent B has read (code shifting under its feet), the server notifies agent B. Agent B can ignore it if it is not relevant, or it can check the diff to make sure that it doesn't conflict. Each agent has messaging abilities, capable of DMing just one agent, broadcasting to all other agents hosted by the server, or just agents working in that repo. This allows you to spawn multiple sessions in the same repo, and have all conflicts automatically resolved.

Agents are also able to spawn their own swarms autonomously. They have a swarm tool which allows them to spawn in their own teamates to accomplish tasks in parallel. Doing so turns the main agent into a coordinator and the spawned agents into workers. Groups of agents, their messaging channels, their completion statuses, etc are all automatically managed. This can be done headlessly or headed.

OAuth and Providers

Supports a wide range of providers, including Claude OAuth and OpenAI Codex OAuth.

Customizability / Self-Dev

Jcode is inventing a new form of customizability. One that doesn't limit you to what a plugin or extension can do. Tell your jcode agent to enter self dev mode, and it will start modifying its own source code. Jcode is optimized to iterate on itself. There is significant infrastructure around self development, which allows it to edit, build, and test its own source code, then reload its own binary and continue work in your (potentially many) sessions, fully automatically.

Other