Back to directory

MiniCode

A lightweight, Claude Code-like terminal coding assistant built for learning and experimentation, implementing a compact agent loop, tool calling and a terminal interface.

Visit website (opens in a new tab)liumengxuan04.github.io
MiniCode

MiniCode is a terminal-first coding assistant built around a practical agent loop: it accepts a user request, inspects the workspace, calls tools when needed, reviews file changes before writing them, and returns a final response in the same terminal session. The project keeps its control flow, tool model and terminal-interface behavior intentionally compact so they stay easy to read and extend, which the maintainers frame as being useful for learning and for building custom tooling rather than for large-scale production use.

It supports up to three concurrent read-only sub-agents while the root agent retains sole ownership of code changes, and keeps an in-memory todo plan shared across turns of a session, along with a long-session context system that handles usage accounting, automatic compaction and context collapse.

The project is implemented in TypeScript, with additional Rust, Python, Go and Java ports maintained by different contributors, and is released under the MIT license.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.