Johannes GrofDE
Back to projects
Betav2.1.0

PatchPilot

A terminal coding agent for local models, with configurable permissions.

PatchPilot works inside a repository with a model you run yourself: Ollama, LM Studio, MLX, llama.cpp or vLLM. Every file edit and shell command shows up in the transcript first, and the risky ones wait for your approval. Since 2.0 there are no cloud providers and no API keys.

Open source
Latest release
v2.1.0
Platform
npm / Terminal
Download
npm package
Updated
Nov 3, 2026
GitHub
★ 1 star
Stack
TypeScript · Ink · Ollama
~ $ gh repo view jx-grxf/PatchPilot
PatchPilot  A terminal coding agent for local models, with configurable permissions.

status   Beta
version  v2.1.0
stack    TypeScript · Ink · Ollama
platform npm / Terminal
repo     github.com/jx-grxf/PatchPilot

~ $ npm install -g @jx-grxf/patchpilot
~ $
Project data, read from GitHub at build time

Problem

Most coding agents send your code to someone else's server and hide the run behind a chat bubble. Small local models, on the other hand, tend to break tool calls and loop until the run is wasted.

What I built

A TypeScript terminal UI with nine focused tools, native function calling plus a validated fallback for smaller models, isolated child agents with narrow permissions, and a context meter that shows when the window is about to fill up.

Latest release

v2.1.0

Highlights

  • Local only: Ollama on your machine, your LAN or over Tailscale, plus OpenAI-compatible servers like LM Studio, MLX, llama.cpp and vLLM.
  • Every file read and shell command lands in the transcript before it runs, with plan, build and bypass modes and a workspace boundary.
  • Small models stay usable: tool calls are validated and repaired step by step when they break.
  • Resumable sessions, pinned and compacted context, and child agents that work in their own context.

Developer setup

install
npm install -g @jx-grxf/patchpilot
clone
git clone https://github.com/jx-grxf/PatchPilot.git && cd PatchPilot