Skip to Main Content

CodexTree

Built at Global Codex Hackathon: [London] · Apr 15, 2026 · London, UK

Demo video · Most AI coding tools force complex development work into one long linear conversation. That makes it hard to explore multiple approaches, separate independent tasks, preserve the right context for each thread of work, and safely manage code changes across experiments. As the conversation grows, useful context gets buried, unrelated ideas get mixed together, and it becomes difficult to return to earlier points or combine parallel work cleanly. In many current workflows, if a developer wants to split work into a new feature path, they often have to open a new session and repeat the original prompt and context again, which is slow, repetitive, and error-prone. Codex Tree solves this by giving AI conversations the same kind of branching structure that developers already use in version control. Users can fork work into focused branches without duplicating prompts, keep each branch tied to its own workspace and history, roll back safely, and merge results intentionally. If part of the chat stops being useful or reaches a dead end, users can roll back to an earlier point and create a new branch from there rather than restarting from scratch. It also becomes easy to test two different approaches in parallel by creating a branch for each option, exploring both independently, and then continuing with whichever approach works better. Compared with using the regular Codex app fork and worktree features directly, this project reduces manual session management, keeps the branch relationships visible instead of letting forks disappear into separate chats, preserves the exact filesystem snapshot associated with each branch point, and makes branch history easier to understand and revisit. It also gives users a visual map of their branches and chats, improving visibility into what has already been explored and how the work evolved over time. This creates a more natural way to plan, delegate, compare alternatives, and coordinate larger builds with Codex./…

Codex Tree is a branch-aware environment for AI-assisted software development. It turns a normally linear Codex chat into a tree of connected conversations so users can split a complex task into separate branches, keep the right context in each branch, and still merge the results back together later. The project includes a VS Code custom editor that visualizes the workflow as a tree and a Python backend that manages the actual branch sessions against a target codebase. The core idea is that software work is rarely linear. A user might ask Codex to plan an app, then break that work into branches such as API, UI, tests, or bug fixes. Each branch inherits the relevant prior context, maintains its own chat history, and runs in its own git-backed worktree so filesystem changes stay isolated. This avoids the common workflow of creating a new feature branch, starting a brand new AI session, and then re-prompting the model with all of the same background context just to continue related work. When work is complete, Codex can merge branches back into a new combined branch using both the branch workspaces and the saved conversation histories as context. Key features include visual tree-based chat editing in VS Code, branch creation from the current tip, the root, earlier turns, or specific nodes, per-branch filesystem snapshots and rollback, persisted session state, Codex-driven branch merges, streaming runtime events for assistant output, commands, tools, and file changes, command and file-change approval handling, and the ability to adjust model and reasoning level across turns. Compared with the regular Codex app fork and worktree logic, Codex Tree adds a much more usable layer on top: branches are visible as part of one connected workflow, branch points are tied to conversation nodes rather than being managed as isolated threads, users can branch from historical points with matching filesystem state, and rolling back a branch restores both the chat history and the files together. In the regular Codex app, once a fork is made the relationship to the original chat is much easier to lose because it appears as a separate chat thread. In Codex Tree, that relationship stays visible as a linked branch in the same view, so related ideas, experiments, and follow-up work remain grouped together instead of being scattered across separate chats. The visual tree also makes it much easier to keep track of what branches exist, what conversations happened in each branch, what was done, and roughly when different lines of work diverged or were completed. Because the interface is graphical and user-friendly, it can also make complex coding workflows more accessible to non-technical or less technical users who may find a purely terminal- or chat-driven workflow harder to follow. The graphical display makes plans, ideas, and workflow structure easier to explain, present, and understand. Together, these features make Codex feel less like a single chat window and more like a structured workspace for managing parallel AI development workflows.

Team