logo

1jehuang/jcode

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

View on GitHub ↗Jump to charts ↓Open shareable report →

1jehuang/jcode has 21k+ stars and 2k+ forks on GitHub, is written in Rust, and was last pushed on Oct 18, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 50 minutes ago
Type:ApplicationCategory(s):AI Coding AgentsAgent Frameworks & SDKsAI Agents & LLM Apps
Added to GitGenius on May 28th, 2026
Created on January 5th, 2026
Open Issues & Pull Requests: 728 (+2)
GitHub issues: Enabled
Number of forks: 2,436
Total Stargazers: 21,010 (+1)
Total Subscribers: 110 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 14.5 hours
Mean response time: 3.1 days
90th percentile: 4.9 days
Tracked items: 1,233

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

1 person did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

About 9% of issues opened in the past year have never received a reply. 96% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 58% of issues opened in the past year have been closed. Three people close 90% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 562
New in 7 days: 48
Closed in 7 days: 58
Avg open age: 12 days
Stale 30+ days: 356
Stale 90+ days: 53

Recent activity

Opened in 7 days: 45
Closed in 7 days: 39
Comments in 7 days: 94
Events in 7 days: 390

Top labels

  • bug (667)
  • triage: needs-decision (436)
  • autonomous: no (344)
  • enhancement (342)
  • triage: reproducible (289)
  • priority: medium (245)
  • priority: high (234)
  • autonomous: clear (187)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

jcode is a CLI tool and AI coding agent harness built in Rust that emphasizes RAM efficiency and intelligent code generation capabilities.

The tool addresses the resource constraints of running AI-powered coding agents by optimizing memory usage and startup performance. It integrates with large language models and supports the Model Context Protocol, allowing developers to leverage AI assistants like Claude and OpenAI for code generation and automation tasks through a terminal interface.

Developers should consider jcode if they need to run multiple concurrent AI coding sessions with minimal resource overhead, or if they work in environments where RAM is constrained. The project positions itself as both the most RAM-efficient and most intelligent harness in its category, with documented performance benchmarks available. The tool provides an SDK for integration and detailed documentation on its website.

The project maintains a substantial base of real-world adopters, as evidenced by the fact that nearly all open issues originate from outside users rather than the core team. Maintainers typically respond to new issues and pull requests within a day. Work in the issue tracker centers on bug fixes and reproducible issues marked with medium priority.