Back to directory

PersonalCode

A terminal-based AI coding assistant written in Python and Textual that runs multiple model providers, enforces permission modes before writing files or executing commands, and adds skills, memory, and team collaboration.

PersonalCode

PersonalCode is a terminal user interface coding assistant built with Python and Textual. It connects to Anthropic, OpenAI, and OpenAI-compatible providers such as DeepSeek, Kimi, GLM, and MiniMax, and reads each provider's context window automatically from its API, falling back to a built-in mapping when that fails.

It emphasizes human-in-the-loop control: four permission modes range from asking approval for every write and command to a fully automatic mode, backed by a dangerous-command detector, a path sandbox, and rule-based permissions at the global, project, and local level. It also supports project, user, and built-in skills, automatic memory consolidation and recall, multi-agent team collaboration over in-process, tmux, or iTerm2 backends, MCP tool access, Git worktree management, and a remote mode that controls the agent from a browser over WebSocket.

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.