Jean
On your own server, Jean runs a team of AI coding agents, each in its own git worktree, and lets you steer them all from a browser tab. Every task starts from real context: a GitHub issue, pull request, workflow run, Dependabot alert, security advisory, Linear ticket, Sentry error, or a plain prompt. Jean creates an isolated worktree with its own chat sessions, terminal, and diff, so several agents can edit one repository without colliding. Choose the backend per task from Claude, Codex, Cursor, OpenCode, Pi, Command Code, Grok, and Kimi Code, using your own subscriptions and CLI logins. Plan, Build, and Yolo modes, plan approval, and session recaps keep long runs reviewable. Magic commands handle commits, pull request descriptions, AI code review with tracked findings, merge conflict resolution, and release notes, and every prompt is editable with its own model and reasoning effort. A split or stacked diff viewer covers uncommitted changes, branches, commits, and checkpoints, with line comments. Mr. Robot, a beta sweeper, polls open issues and drafts plans in fresh worktrees. Linked projects share context across repositories, and MCP servers can be switched on per project or per session. Token-protected web access works from a laptop or a phone, and the desktop app can attach to the same server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Shep
Type one sentence about a feature, and Shep spins up an AI coding agent on its own branch and worktree, then carries the work through commit, push, CI, and a draft pull request. Run three features, five, or ten at once, with Claude Code, Codex, Copilot, Cursor, Gemini, Kimi Code, Cline, or local models picked per feature. A control center draws every repository and feature as a live graph with a fleet bar that counts what is cruising, queued, waiting on you, or failed. When an agent is unsure it asks a blocking question with a recommended answer and a deadline, and you reply from the web, the CLI, chat, or the terminal console. Optional spec-driven mode writes requirements, research, and a plan as YAML for you to approve before any code exists. CI watch reads failing logs and pushes fixes, a checkpoint follows every agent step so you can diff or restore it, and nothing merges without your approval. Tool pages, skills, plugins, webhooks, project memory, and per-feature chat round out the workspace, and an app starter plans a brand new project from a prompt. State stays in a local SQLite database, and usage metrics can be switched off. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.