What is siGit Code in Glueprint?
siGit Code is a local coding agent built by smbCloud (Splitfire AB), written almost entirely in Rust and released under the Apache 2.0 license. It runs on the user's own machine with no API keys, cloud round-trips, or subscription, using the Onde inference engine and a GGUF model downloaded from Hugging Face on first launch (roughly 1 to 2 GB, then cached). It works both as an editor integration over stdio for Zed and other ACP-compatible editors and as an interactive terminal chat UI, and is installable via Homebrew, pip, uv, npm, or 'cargo install sigit'.
Local-first coding agent. Runs entirely on your machine with optional on-device LLM inference via Onde.
siGit Code connects over the open Agent Client Protocol. One generic adapter implements the protocol's client side, so siGit Code gets the same surfaces as every other harness.
Everything below works with the siGit Code CLI you have today — no migration, no new account for the model, no lock-in. Uninstall Glueprint and your terminal workflow is exactly as it was.
Set up siGit Code on a host.
Installation is host-specific: repeat these steps anywhere this agent should execute. Portal and mobile can control the session afterward, but the process remains on that host.
Open the ACP catalog
On each execution host, open Settings -> Agents -> Browse ACP catalog and choose siGit Code.
Install and initialize
Glueprint installs the registry distribution for siGit Code, starts it, and completes the ACP initialize handshake.
Start a project session
Choose siGit Code from a project or worktree and use the capabilities reported by that installed build.
How the connection works.
Glueprint adds orchestration and shared surfaces without taking ownership of the coding agent or its provider account.
Glueprint finds the siGit Code binary you installed and spawns it, then speaks the Agent Client Protocol — JSON-RPC 2.0 over stdio — to drive it. Same CLI, same authentication; Glueprint just wraps the session.
Message chunks, tool calls, and tool-call updates from siGit Code arrive as protocol notifications and render as the same live, typed timeline every Glueprint session gets — watchable from desktop, browser, or phone.
When siGit Code asks to write a file or run a command, the protocol's permission request surfaces as an inline approval card on whatever device you're holding. Approve, deny, or auto-allow per tool.
Because siGit Code speaks ACP, adding it is a catalog entry, not an engineering project — the same adapter runs every other agent in the registry, so you can tile them side by side.
Capabilities and discovery.
The status labels separate guaranteed integration behavior from features owned or announced by the installed agent.
| Capability | Status | Behavior |
|---|---|---|
| Local-only: no API keys, cloud, or subscription | Runtime | Confirmed when the installed agent connects. |
| Apache 2.0, written in Rust | Runtime | Confirmed when the installed agent connects. |
| Onde inference with GGUF models from Hugging Face | Runtime | Confirmed when the installed agent connects. |
| Works as editor integration or terminal chat | Runtime | Confirmed when the installed agent connects. |
| Installable via Homebrew, pip, uv, npm, Cargo | Runtime | Confirmed when the installed agent connects. |
Authentication, ownership, and limits.
Glueprint is the environment around the agent. Credentials, model access, and vendor-specific behavior stay where their owner designed them.
Watch every siGit Code prompt, tool call, and diff stream in real time — desktop, web portal, iOS and Android. The session runs on your machine; the view follows you.
Permission prompts arrive as approval cards wherever you are. Kick off a refactor at your desk, approve the file writes from the couch.
Run several siGit Code sessions side by side, each in its own git worktree, with diffs, history, and a three-pane conflict resolver alongside.
Tile siGit Code next to Claude Code, Codex, and the rest of the ACP fleet in the Command Center. The protocol differs; the surface doesn't.
Promote it to an assistant: persona, constitution, long-term memory, and a daily journal on disk, loaded into every wake.
Wake it on cron: triage the inbox every 30 minutes, sweep PRs at 9am, run the nightly cleanup. Quiet hours and watermarks prevent re-fires.
Messages, sessions, and output tokens computed from session logs — compare siGit Code against Claude Code, Codex, and your other ACP agents.
Remote viewing rides AES-256-GCM envelope encryption. The relay routes; it cannot read.
Common questions
Can I run siGit Code with Glueprint?
Yes. siGit Code is registered in the official Agent Client Protocol registry, and Glueprint implements the protocol's client side. It spawns the siGit Code CLI you already installed and drives it over JSON-RPC 2.0 — adding live sessions, inline approvals, worktrees, and remote control.
Do I need a separate siGit Code subscription or API key?
No. Glueprint doesn't resell model access. siGit Code authenticates exactly the way its vendor designed — its own login, subscription, or API key. Glueprint spawns the binary and speaks the protocol; it doesn't sit between you and the model provider.
Can I run siGit Code from my phone?
Sessions always run on your machines — a laptop, a desktop, or a server with the headless daemon. The iOS and Android app streams siGit Code sessions live, lets you send follow-ups, and handles permission approvals from anywhere.
Can I run siGit Code next to Claude Code and Codex?
Yes — that's the point. Each harness is an adapter; sessions from all of them tile into the same Command Center, share the same task boards, and roll up in the same per-harness analytics.
Is my session content private?
Yes. Remote viewing routes AES-256-GCM-encrypted envelopes through the relay, which stores a wrapped key it cannot open — decryption happens on your devices. On the free local tier, session content never leaves your machine at all. See security.