Back to directory

Memcode

A terminal coding agent that keeps a persistent memory of a repository's layout, recent work and corrected preferences, so sessions do not start from zero.

Memcode

Memcode is one Go binary that runs two ways. Code is an interactive terminal coding agent that reads and writes a .memcode folder holding what it knows about a repository: its subsystems, what was worked on recently, approaches that failed and why, and preferences the user has corrected it on, so the memory travels with the repository and benefits the whole team. Agents is the same binary run as a self-hosted gateway that answers on chat surfaces a user already uses and runs agents given a standing objective to work on unattended.

Both modes run against a user's own API keys, a local endpoint such as Ollama, or a hosted memcode account. A session stays on one chosen model unless changed, while sub-agents and scouts can run on a cheaper model. A plan step researches the codebase and drafts an approach for approval before execution, side quests can run as background sub-agents, and the terminal UI supports multiline editing, streaming output, interrupts and a live context meter. It reads instructions from MEMCODE.md, AGENTS.md or CLAUDE.md.

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.