Jcode — Getting Started

Jcode is an open-source (MIT) AI coding agent for the terminal, written in Rust by Solo Systems (backed by Combinator). It's built around three bets: massive parallelism, harness-over-model, and fully open dev tools. The result is the most RAM-efficient agent on the market — about ~10.4 MB per additional session (20× less than Claude Code) and a 48.7 ms time-to-first-input (72× faster than Claude Code).

Installation

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

# macOS via Homebrew
brew tap 1jehuang/jcode
brew install jcode

# Windows 11 (PowerShell 5.1+)
irm https://jcode.sh/install.ps1 | iex

Verify:

jcode --version

Uninstall (keeps config, auth, and sessions; add --purge to wipe everything):

curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/uninstall.sh | bash -s -- --yes

Provider Setup

Jcode supports subscription OAuth flows and direct API providers, so you can use the models you already pay for:

jcode login --provider claude     # Claude subscription
jcode login --provider openai     # OpenAI / ChatGPT / Codex
jcode login --provider gemini     # Google Gemini
jcode login --provider copilot    # GitHub Copilot
jcode login --provider azure      # Azure OpenAI
jcode login --provider ollama     # local Ollama server
jcode login --provider lmstudio   # local LM Studio server

Named profiles exist for popular OpenAI-compatible services: openrouter, deepseek, moonshotai, huggingface, nebius. For any unlisted OpenAI-compatible endpoint:

printf '%s' "$MY_API_KEY" | jcode provider add my-api \
  --base-url https://llm.example.com/v1 \
  --model my-model-id \
  --api-key-stdin \
  --set-default

Headless/remote machines use jcode login --provider <provider> --no-browser to print an auth URL. Verify everything with jcode auth-test --all-configured.

First Session

cd my-project
jcode

Common entry points:

Project instructions live in AGENTS.md at the repo root; machine-wide instructions in ~/AGENTS.md. Both load into every session in scope.

Essential Slash Commands

What Makes Jcode Different

• RAM efficiency — ~10.4 MB extra per session vs ~213 MB for Claude Code. Run dozens of agents in parallel on consumer hardware.
• Memory — every turn is embedded as a semantic vector; related memories are recalled automatically from a graph via cosine similarity.
• Swarms — coordinated multi-agent teams with file-conflict detection and model routing via .jcode/swarm-prompt.md.
• Self-dev mode — tell jcode to enter self-dev mode and it edits, builds, tests, and reloads its own binary.
• MCP that never blocks startup — MCP tools are advertised from an on-disk schema cache, so the prompt cache stays warm.
• Background tasks — run_in_background tasks survive reloads, render live progress cards, and wake the agent on events.
• Append-only context — stable prompt prefix keeps the provider KV cache hot, cutting cost and latency.

Next Steps

• Prompt Engineering in Jcode — hill-climbable goals, confidence, todo discipline
• Jcode Configuration Reference — config.toml, MCP, memory, remote
• Memory, Swarms & Self-Dev — advanced workflows
• Tool Comparison — jcode vs opencode vs pi vs Claude Code