Back to directory

DeepCode

An agentic coding system that turns research papers and natural-language descriptions into production-ready code, with terminal, desktop and web clients sharing one local background service.

DeepCode

DeepCode is an agentic coding tool built around multi-agent systems, aimed at turning research papers and natural-language descriptions into production-ready code through its Paper2Code capability. It works directly in a user's own repository rather than a sandboxed copy.

A terminal UI, a native desktop app and a web client all connect to the same local background service, sharing projects, session history, models, skills, permissions, goals and automations; closing one client leaves work running so another interface can reconnect to the same conversation. Its loop engineering is goal-driven and evidence-driven, meaning a task is checked against evidence before being marked complete, and multiple agents can work in parallel without colliding on the same files.

It is written in Python and 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.