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

RAM per additional session (headless)

Tool	First session	Each additional session	Comparison (additional)
jcode	71.3 MB	~3.3 MB	baseline
OpenCode	637.1 MB	~5.9 MB	1.8× more RAM
pi	84.0 MB	~79.6 MB	24.1× more RAM
Claude Code	272.9 MB	~169.3 MB	51.3× more RAM
Codex CLI	398.6 MB	~194.1 MB	58.8× more RAM

Reproduce.

Time to first input

Time until typed text appears on screen, across 10 interactive launches.

Tool	Time to first input	Comparison
jcode	19.1 ms	baseline
pi	596.4 ms	31.2× slower
Codex CLI	905.8 ms	47.4× slower
OpenCode	1047.9 ms	54.9× slower
Claude Code	3512.8 ms	183.9× slower

Full numbers on jcode.sh.

Swarm

Spawn two or more agents in the same repo, and they will automatically be managed by the server to allow native collaboration. When agent A edits a file that agent B has read (code shifting under its feet), the server notifies agent B. Agent B can ignore it if it is not relevant, or it can check the diff to make sure that it doesn't conflict. Each agent has messaging abilities, capable of DMing just one agent, broadcasting to all other agents hosted by the server, or just agents working in that repo. This allows you to spawn multiple sessions in the same repo, and have all conflicts automatically resolved.

Agents are also able to spawn their own swarms autonomously. They have a swarm tool which allows them to spawn in their own teamates to accomplish tasks in parallel. Doing so turns the main agent into a coordinator and the spawned agents into workers. Groups of agents, their messaging channels, their completion statuses, etc are all automatically managed. This can be done headlessly or headed.

OAuth and Providers

Supports a wide range of providers, including Claude OAuth and OpenAI Codex OAuth.

Customizability / Self-Dev

Jcode is inventing a new form of customizability. One that doesn't limit you to what a plugin or extension can do. Tell your jcode agent to enter self dev mode, and it will start modifying its own source code. Jcode is optimized to iterate on itself. There is significant infrastructure around self development, which allows it to edit, build, and test its own source code, then reload its own binary and continue work in your (potentially many) sessions, fully automatically.

Other

• Token optimization
• KV cache
• Hill-climbable measurements