High-performance framework for coding agents
Developed with the Rust language, jcode offers a framework for testing and evaluating coding-oriented artificial intelligence agents. It provides a standard infrastructure to measure the performance of agents used in software development processes.
Updates
- September 19, 2026: Stars 19,260 → 19,885, latest release v0.85.0 (September 19, 2026).
- September 7, 2026: Stars 19,190 → 19,260, latest release v0.84.0 (September 7, 2026).
- September 6, 2026: Stars 19,126 → 19,190, latest release v0.82.0 (September 6, 2026).
- September 5, 2026: Stars 19,081 → 19,126, latest release v0.81.7 (September 4, 2026).
What you get
- High resource efficiency in multi-session workflows
- Low memory usage and fast startup time
- Testing infrastructure for coding-focused artificial intelligence agents
Installation
curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bashbrew tap 1jehuang/jcode
brew install jcodeRunning it
ollama pull llama3.2
jcode login --provider ollama
jcode --provider ollama --model llama3.2 run 'hello'If you don't write code
I want to test the performance and multi-session management ability of my coding-focused AI agent. Allow me to optimize my agent's resource usage and set up a standard testing environment using the jcode framework.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-21: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.