1jehuang /
jcode
A terminal coding agent written in Rust, built to use little memory and start fast
- 21.1k stars
- 876 stars since 3 Oct
- Rust
- Updated today
- Some experience
- Coding agents & dev tools
A coding agent harness is the program that connects a language model to your files, shell and tools so it can work on code. jcode is one of these, with a terminal interface, written in Rust. It runs on Linux, macOS and Windows.
Its main pitch is resource use. Sessions share one daemon, so each extra session adds only a few megabytes. The README says Claude Code runs a separate process per session. It includes benchmarks against Claude Code, Codex CLI, OpenCode, Copilot CLI, Cursor Agent and others, measured on the author's Linux machine. Treat those as the author's numbers, not independent results.
It also has an agent memory system. Each turn is turned into a vector and compared with a graph of stored memories, and relevant ones are put into the conversation without the agent calling a tool. A side agent extracts new memories, and a background mode tidies old ones.
What it does
Low RAM across many sessions
Sessions share one daemon. The README reports about 3 MB per extra headless session, against roughly 164 MB for Claude Code in its own test.
Fast startup
The README measures about 14 ms to first frame and about 49 ms to first input, much quicker than the other tools it compares.
Automatic agent memory
Each turn is embedded and matched against a memory graph by cosine similarity. Relevant memories are injected into the chat, optionally checked first by a side agent.
Explicit memory and session search
The agent can search or store memories on purpose, and can search earlier sessions in a RAG style.
In-app updates and side panels
The /update command or jcode update fetches the latest release and keeps your session. A panel tool opens Markdown or PDF content in a side panel.
What you could build
- Run many agent sessions in parallel on a laptop without using up memory.
- Fan out headless swarm workers for repo-wide tasks such as search and summarising.
- Keep an agent that remembers earlier decisions and facts across sessions.
- Compare the startup time and memory use of coding agent CLIs using the README's benchmark script.
- Open Markdown notes or PDFs in a side panel while the agent works.
Get started
Run the first command on macOS or Linux, or the second in PowerShell on Windows 11. Then launch jcode and set up a model provider; the README points to a detailed installation section for that. Run /update later to upgrade.
curl -fsSL https://jcode.sh/install | bashirm https://jcode.sh/install.ps1 | iexCommands are copied from the project's README. Read it on GitHub for the full setup.
More in Coding agents & dev tools
rea
MCP server that lets AI agents reverse engineer apps, binaries and websites locally
opencode
Open source AI coding agent for your terminal, with a beta desktop app
claude-code
Terminal coding assistant that reads your codebase and takes plain-English commands
codex
A coding agent from OpenAI that runs in your terminal on your own machine
pi
A minimal terminal coding agent you extend with skills, extensions and packages
orca
Desktop and mobile app for running many coding agents side by side
Understand-Anything
Turns a codebase or wiki into an interactive graph you can search and ask questions about
screenshot-to-code
Turns screenshots, mockups and screen recordings into front-end code with AI models
warp
Rust terminal that adds a built-in coding agent and runs other CLI agents
free-claude-code
Local proxy that lets Claude Code, Codex, Aider and others run on free or cheap models