Easily manage git worktrees, launch tasks and work on multiple features in parallel.

MCP server for managing git worktrees with synchronized branches. Provides tools for creating isolated development environments, tracking changes, and managing collaborative workflows.

Instant git worktree bootstrap with CoW node_modules, env copy, and port shifting for parallel agents

Instant git worktree bootstrap with CoW node_modules, env copy, and port shifting for parallel agents

Auto-sync Git worktrees with remote branches. Includes an MCP server so Claude Code, Cursor & other AI agents can inspect and manage worktrees.

Multi-repository git worktree workspaces from the command line, with an MCP server for AI agents.

Catch broken merges between parallel AI coding agents (Claude Code, Codex, cmux, Orca, git worktree). Combines worktree branches, checks conflicts and contract breaks, runs affected tests. Local CLI + MCP server.

Let agents manage Git worktrees via the wtp CLI.

Local merge queue for parallel LLM agents in Git worktrees. Test combined code changes, require approval for Git pushes, and recover interrupted pushes.

A control tower for parallel git worktrees + their PRs — TUI, CLI, MCP.

Queue committed branches from parallel LLM coding agents in Git worktrees. Test the combined tree in a local merge queue, require approval for Git pushes, and recover interrupted pushes.

Mergepond plugins for coding agents: Claude Code and Codex make and manage their own git worktrees through Mergepond's MCP server, pond.

Code search for AI coding agents over MCP: hybrid retrieval, structural search and shared indexing across Git worktrees.

MCP-based multi-agent dispatch hub for Claude Code — parallel worker orchestration with git worktree isolation

An MCP server for delegating repetitive coding tasks from Codex to Antigravity workers in isolated Git worktrees.

Deterministic, resumable multi-agent workflows — a harness-agnostic MCP server that orchestrates Codex, Claude, Cursor, and Kimi agents from plain JavaScript, with journaled resume, git worktree isolation, and personas.

MCP server that splits a task into plans with disjoint file boundaries and scaffolds a git worktree per plan — conflict-free parallel coding agents.

Codex MCP server: run parallel Codex CLI workers in isolated git worktrees, state on disk, web dashboard, auto-update.

A project-aware coordination workspace and MCP server for AI coding agents: shared plans, tasks, chat, Git worktrees, project-scoped access, and review handoffs.

Multi-agent coding coordination: shared tasks, conflict checks and handoffs across Git worktrees. MCP and Skills for Codex, Claude Code, OpenClaw and WorkBuddy.

Local coordination for parallel coding agents: scoped claims, isolated Git worktrees, shared resources and verified integration. MCP + VS Code/Cursor extensions. No hosted service.

Guard rails for AI coding agents: written specs, one git worktree per lane, a gate on exact commits, and a merge queue that only moves main to a gated merge.

AI coding agent orchestrator — resolve GitHub issues end-to-end with isolated git worktrees, quality gates, and an MCP server. Works with Claude Code or Aider.

Reclaims the disk AI coding agents leave behind (clones, worktrees, build output, caches), deleting only what it can prove is safe: dry runs, Git checks, verified archives, receipts. CLI and MCP server.

MCP server to orchestrate parallel AI coding agents (omp, Claude Code, any model) in Tern terminal tabs and git worktrees, from Claude Desktop or Claude Code.

Save on tokens: your expensive model plans and reviews while cheap pi agents write the code. MCP server with git-worktree isolation, file locks, and a shared board. Works with any MCP client.

Why is my disk full? A read-only disk and git-worktree doctor for developer machines (Docker, Xcode, Android, node_modules, caches). CLI + MCP server for AI agents.

Why is my disk full? A read-only disk and git-worktree doctor for developer machines (Docker, Xcode, Android, node_modules, caches). CLI + MCP server for AI agents.

Claude plans and reviews, cheap models type. An MCP server that hands coding jobs to OpenCode workers in isolated git worktrees — hard price ceilings, a daily budget, and nothing merges until you have seen the diff.

MCP server that delegates coding loops from Claude Code/Cursor/Codex to the local Grok CLI in an isolated git worktree and returns a verified receipt. Optional lazy tool loading. Unofficial.

Separate the live work from the dead weight on a developer machine: build daemons, caches, build output and stale git worktrees, with tiered safe cleanup. CLI, Claude Code plugin and MCP server.

Your whole stack, always running the code you saved, never a broken build. Every git worktree a lane, lanes on the team's servers, one CLI, dashboard and MCP server for your coding agents. Windows and Linux, native.

Claude Code plugin: the Opus supervisor plans, specifies and reviews; cheap workers (DeepSeek & co. via 9Router) write the code in isolated git worktrees. Server-side verification, a review gate, and merge-back as one squash commit. Fewer tokens, same quality.

macOS menu bar cleaner for AI coding agents (Claude Code, Codex, Cursor). Finds leftover dev servers, busy ports, simulators, Docker stacks and git worktrees, and cleans them up with a preview first. Native SwiftUI, open source, everything stays on your Mac.

Self-hosted platform for AI coding agents: Claude Code, Codex, Copilot, Cursor, Junie, OpenCode and pi work on your repositories in parallel git worktrees and open pull requests. Workflows, schedules, project memory and MCP integrations, in a web panel, a REST API and an MCP server.

See what your coding agents left on disk (Codex, Claude Code, OpenCode, Gemini CLI, Cline): worktrees, sessions, crash dumps, half-written git packs, bloated SQLite. SAFE/REVIEW/KEEP per item with the reason; dry run first; a guard hook stops the agent before the disk is full.

MCP server that dispatches and supervises parallel Codex CLI workers, one isolated Git worktree each, with a persisted work state machine.

Clone, commit, diff, branch, merge, rebase, cherry-pick, stash, tag, and manage worktrees in local git repos via MCP. STDIO or Streamable HTTP.

GitPeak's MCP server: git context for AI agents. Repo status, staged diff, commit log with AI-agent detection, repo health, merge-risk prediction, line history and worktrees. Read-only, zero dependencies.

A git-native issue tracker that lives in your repo: tasks as YAML files, a local web UI, an MCP server, and coding agents that work your tasks in their own git worktrees.

Filesystem-based, git-worktree-safe work-claiming locks for coordinating multiple Claude Code agents/sessions on the same repo — no database, just markdown+YAML under .git/

Multi-forge git repository organiser & MCP server for AI coding agents. Clones & structures repos from GitHub, GitLab, Gitea, Forgejo, Codeberg & Bitbucket by visibility & language, with fast cross-repo code & symbol search, worktree tooling, and TUI graph.

Orchestrate Claude Code, Kiro and Codex as task executors — isolated git worktrees, cross-validation with a verdict, and an MCP server.

Deterministic Self-Evolving Meta-Kernel for AI Coding Agents — Offline Git Worktree Evolution, Zero-Dep Deliverable Inspector, AST Cognitive Memory & 5-Tool Meta-MCP Gateway

MCP server that hands a task to another AI CLI (agy, codex) like a subagent, with model fallback, validated results, git worktree isolation, and background tasks.

Kanbanana replaces sprawling, merge-conflict-prone markdown coordination files (BOARD.md, GPU_LOCK.md, SKILL.md) with an atomic SQLite-backed HTTP MCP server, A2A (/.well-known/agent.json) agent discovery & task dispatch, isolated Git worktree provisioning and FIFO feature locks

Quorus AI: multi-agent rooms for Claude Code, Codex and opencode. Agents fix in their own git worktrees, review each other and push to your repo. MCP + CLI, MIT.

The terminal AI agents can drive — and the cockpit to run them from. 151 MCP methods, agent Inbox, git-worktree fleets, diff review & rollback, one-click updates. macOS / Linux / Windows, local-first, free, MIT.

AI coding agent orchestrator that proves its work — GitHub issues to merge-ready PRs with every acceptance criterion verified, isolated git worktrees, quality gates, an MCP server, and a human merge gate. Works with Claude Code or Aider.

MCP server for Google Antigravity CLI (agy): delegate long tasks to Gemini 4 Orchestrator in a git worktree, get read-only plans and reviews, digest whole codebases — from Claude Code, Cursor or any MCP client

A native GPU-accelerated terminal for autonomous multi-agent teams. Run 20+ CLI agents with in-memory tracking, guarded PTY, 38+ native MCP tools, Git Worktree isolation & Project collaboration. 100% local-first, zero telemetry, no cloud gates on macOS, Windows & Linux.

Kage manages your memory and agents. It briefs and runs agents in isolated git worktrees for a single run or a multi-wave goal, re-runs the checks itself instead of trusting the agent's report, and remembers what it learns so each brief is smarter than th

Deterministic, verifiable orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, Aider, Cursor and 40+ more), exposed over MCP. Bernstein runs orchestration tasks in isolated git worktrees, records a lineage and replay journal for every run, and can anchor task claims, progress updates and posted artifacts in an opt-in HMAC-chained audit log. Tools: 14 are advertised at the default `standard` tool tier. Set BERNSTEIN_MCP_TOOL_TIER to change the tier: `core` advertises 5, `standard` advertises 14 (default), `all` advertises 18. Transports: stdio (default), Server-Sent Events, and streamable HTTP. Install and run: uvx --from bernstein bernstein mcp or pip install bernstein && bernstein mcp HTTP transport: bernstein mcp --transport http Authentication: the stdio transport needs none. The HTTP transport accepts a static bearer token via BERNSTEIN_MCP_TOKEN or BERNSTEIN_AUTH_TOKEN, and binds to loopback only when neither is set. Documentation: https://bernstein.readthedocs.io Requires Python 3.12 or newer. Package `bernstein` on PyPI, version 3.9.0.

Your agent made four worktrees. Stackdeck runs them: starts, supervises, streams logs, shows every port on the machine, and drives it all over MCP. A browser and terminal board for local dev services — zero dependencies, never leaves 127.0.0.1.

Claude Code Multi-Worktree Helper - Single-session parallel worktree automation with MCP server

Local coordination for cooperating coding agents: work claims, isolated worktrees, shared resources, and verified integration without a hosted service.

Verify each git tree once. A stack-agnostic verification queue and cache for parallel coding agents: bounded concurrency, per-tree result cache, request coalescing, CLI for git hooks and an MCP server for agents. Rust.

Disk report and safe, reversible cleanup for AI coding agents: worktrees, checkpoints, node_modules, .godot. CLI + MCP server.

Proof-carrying project memory with multi-language graphs, session receipts, exact recovery, relevant cited recall, provider usage accounting, and optional client-encrypted shared knowledge.

Message bus, status board and file claims for coding agents (Claude Code, Codex) working on the same repo in parallel worktrees.