GStars
    1jehuang

    1jehuang/jcode

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

    ai
    cli
    llm
    ai-agent
    ai-coding-agent
    claude
    coding-agent
    mcp
    Rust
    MIT
    21.4K stars
    2.5K forks
    21.4K GitHub watchers
    Updated Nov 2, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest 4 days ago, with 49 contributors on GitHub.

    Peaked at #6 in the weekly ranking the week of Jul 26, its best in the past year.

    Use Cases & Benefits

    • Provides a highly RAM-efficient AI coding agent harness optimized for multi-session workflows and infinite customizability in Rust.
    • Delivers superior performance with minimal memory usage and ultra-fast startup times compared to similar AI coding agents.
    • Use for running multiple concurrent AI coding sessions on resource-constrained machines without performance degradation.
    • Use for enabling autonomous multi-agent collaboration with automatic conflict resolution and messaging in shared codebases.
    • Use for integrating various AI model providers via OAuth and custom endpoints to flexibly leverage preferred LLM services.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    The next generation coding agent harness to raise the skill ceiling.

    Built for multi-session workflows, infinite customizability, and performance.

    Need Windows, Homebrew, source builds, provider setup, or tell your agent to set it up for you? Jump to detailed installation.

    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.

    Excerpt from the 1jehuang/jcode README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Aug 5: +199Aug 6: +107Aug 7: +172Aug 8: +120Aug 9: +150Aug 10: +170Aug 11: +385Aug 12: +172Aug 13: +114Aug 14: +104Aug 15: +85Aug 16: +106Aug 17: +100Aug 18: +94Aug 19: +79Aug 20: +77Aug 27: +78Aug 28: +48Aug 29: +31Aug 30: +49Aug 31: +61Sep 1: +35Sep 8: +29Oct 14: +73

    +5,552 stars over 90 days across 33 snapshot days; best day +385 on Aug 11.

    Forks

    2.5K+752

    Open issues

    805+581

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    1jehuang/jcode compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    D4Vinci/Scrapling101.1K+6.3K756 days ago
    thedotmack/claude-mem115.8K+4.7K75today
    heygen-com/hyperframes82.3K+4.0K75today
    harry0703/MoneyPrinterTurbo142.0K+3.8K753 days ago
    github/spec-kit149.2K+2.6K75today
    1jehuang/jcode21.4K—604 days ago
    Category median115.8K+4.0K75—
    Compare jcode with Scrapling, claude-mem, hyperframes →

    Discover Repositories

    Search across tracked repositories by name or description