FollowAgents AI AGENTS DIRECTORY
Home / All Agents / Helmor Local Agent Workbench
Dev & Engineering git-worktreecoding-agentscodexgithubgitlabmcp-serverpull-requests

Helmor Local Agent Workbench

Run coding agents in parallel in isolated Git workspaces, then review, test, and ship their work.

View on GitHub ↗ Quick start ↓
Source repo
dohooo/helmor
Stars
★ 1.3k
Last updated
3mo ago
License
Apache-2.0
Primary language
TypeScript
FA score
60/100 · Some gaps

At a glance

How it runs
Desktop appCLIMCP server
Works with
Universal · cross-platformCodex · Claude Code
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
Shell / CLINetwork accessLocal filesystemMCP Server
Typical use
A developer handling several bug fixes or features who wants a separate Git worktree and coding-agent task for each branch.
Not a fit if
  • Teams needing a Linux desktop build (only macOS and Windows x64)
  • Teams needing centralized deployment or shared team state
  • Users who want no sign-in to any coding agent
Source review
60/100 · Some gaps

What does this agent do, and when should you use it?

Helmor is a local-first workbench for multi-agent software development, with data and workspaces kept under ~/helmor/. It creates a separate Git worktree and branch for each task so coding agents can work in parallel without sharing a workspace. The application brings conversations, diffs, a Monaco editor, terminals, and PR actions into one window, with GitHub and GitLab flows for creating and merging PRs or MRs, fixing CI, and resolving conflicts. It supports bringing your own Claude Code, Codex, Cursor, OpenCode, or Kimi Code credentials, API keys, and custom providers. Helmor also exposes a helmor CLI and an MCP server over stdio; an experimental mobile companion uses a Cloudflare tunnel to start tasks from a phone browser.

A user adds a local repository through the app or with helmor repo add /path/to/repo, then creates an isolated task branch and worktree using helmor workspace new --repo myapp. Tasks are sent to a signed-in coding agent through the interface or helmor send --workspace myapp/feature-x "...", while Helmor presents the agent conversation, code changes, editor, and terminal for that workspace. helmor workspace status checks workspace state, and helmor workspace run-action runs available delivery actions such as creating a PR, merging, or fixing CI. helmor mcp starts an MCP server over stdio, and every CLI command supports --json.

  1. A developer handling several bug fixes or features who wants a separate Git worktree and coding-agent task for each branch.
  2. An engineer using Claude Code or Codex who wants to inspect generated diffs, edit code in Monaco, and use a terminal beside the conversation.
  3. A maintainer working through GitHub or GitLab delivery who needs to create or merge PRs/MRs, address CI failures, and resolve conflicts from a workspace.
  4. A command-line-oriented developer who wants to automate local task workspaces with helmor workspace new, helmor send, and helmor workspace status.
  5. A developer who wants a terminal or another agent to drive the local workbench through Helmor’s stdio MCP server.

How do you install or deploy this agent?

Download Helmor from GitHub Releases; the documented builds are macOS (Apple Silicon and Intel) and Windows x64. On first launch, connect GitHub or GitLab and sign in to a coding agent; the README states that agent CLIs are bundled. To install the CLI, use Settings → Experimental → Command Line Tool. For local source development, the documented commands are bun install && bun run dev.

How do you use this agent?

Add a repository, create a workspace, and send a task: helmor repo add /path/to/repo, helmor workspace new --repo myapp --name fix-auth, and helmor send --workspace myapp/fix-auth "Add tests for the token refresh path.". Check progress with helmor workspace status myapp/fix-auth, then use helmor workspace run-action myapp/fix-auth for an available shipping action. Workspace references use repo-name/directory-name; append --json to any command when machine-readable output is needed.

What are this agent's strengths and limitations?

Pros
  • Each task receives its own Git worktree and branch, which is designed to prevent parallel agents from working over one another.
  • Conversation, diffs, Monaco editing, terminals, and PR/MR actions are co-located, supporting review and shipping in one workbench.
  • It explicitly supports Claude Code, Codex, Cursor, OpenCode, and Kimi Code while allowing users’ own logins, API keys, and custom providers.
  • The desktop workflow is complemented by a JSON-capable CLI and a stdio MCP server for terminal and agent-driven operation.
Limitations
  • The documented release platforms are macOS and Windows x64; the supplied evidence does not document Linux support.
  • Initial setup requires connecting GitHub or GitLab and signing in to at least one coding agent; the supplied material does not detail the authentication or permission model.
  • Workspaces and data are local under ~/helmor/; there is no documented evidence here of centralized deployment, shared team state, or remote workspace management.
  • The mobile companion is explicitly experimental and uses a Cloudflare tunnel to reach the desktop.
  • Slack and GitHub context, plan mode, and agent-driven orchestration are described as upcoming, rather than current capabilities.

How does this agent compare with similar options?

Helmor is not presented as a replacement for Claude Code, Codex, Cursor, OpenCode, or Kimi Code. It is a local workflow layer that can connect those coding agents to isolated Git workspaces, review surfaces, and PR/MR actions.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Helmor Local Agent Workbench This agent 60 · Some gaps Desktop appFree + model costs ★ 1.3k 3mo ago TypeScript Codex · Claude Code
wsp 59 · Major gaps Desktop appFree + model costs ★ 14 3d ago TypeScript Codex · Claude Code
Concord MCP 75 · Good — ★ 1k 3d ago TypeScript Codex · Claude Code
GitHub MCP Server 61 · Some gaps MCP serverFree ★ 34k 4d ago Go Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Some gaps
60/ 100 5-point scale 3.0 / 5
Trust 12/29
Reliability 6/14
Adaptability 14/18
Convention 13/18
Effectiveness 10/13
Verifiability 5/8
Why each dimension lost points
Trust12 / 29 · 2.1/5

The README presents a local-first product and describes local workspaces, storage, and CLI use; the sidecar source shows JSONL request, event, and logging flows. The product also involves agent logins/API keys, GitHub/GitLab, PR merges, and an experimental Cloudflare tunnel. The sample does not adequately explain permission scope, sensitive-data storage, confirmation for external effects, or rollback, so those areas receive partial credit.

Reliability6 / 14 · 2.1/5

AGENTS.md, package scripts, and CI describe multiple test targets, type checking, linting, and platform build paths; the sidecar also includes heartbeats, error logging, and cancellation handling. Documentation shows drift: the README mentions Cursor, Kimi, and GitLab, while the older CLAUDE.md architecture omits some providers. No execution was performed, and dependency availability is only partly supported by lock/build configuration.

Adaptability14 / 18 · 3.9/5

The product clearly targets developers orchestrating coding agents in parallel and reviewing, testing, and shipping code, with desktop, CLI, MCP, and experimental phone entry points. Some provider and environment details are documented, but the sample does not fully specify trigger conditions, per-provider capability boundaries, or platform differences.

Convention13 / 18 · 3.6/5

Repository structure, commands, architecture, tests, and development conventions are documented in depth; the README includes quick-start and CLI examples, and the license text is present. Package versioning and changeset/release procedures are described. Installation platform details are brief, FAQ and limitations coverage is incomplete, and maintenance responsibility is not clearly assigned; documentation also shows version drift.

Effectiveness10 / 13 · 3.8/5

Isolated workspaces, parallel agents, built-in diff review, and PR/MR operations provide a useful development loop, with actionable CLI examples. The desktop app and integrations add installation and maintenance costs; the sample does not quantify performance, cost, or the incremental cost of features.

Verifiability5 / 8 · 3.1/5

Architecture and command claims can be cross-checked against package scripts, CI workflows, the sidecar entry point, and E2E test samples; release steps are also concrete. However, not every README product claim is verifiable from this sample, and static test configuration does not establish runtime results. The rationale distinguishes visible file evidence from unverified outcomes.

Risks and how to mitigate them
  • PR/MR creation and merging, agent credentials, and the experimental remote tunnel can affect external systems; check the product documentation or settings for permissions, confirmation steps, credential handling, and revocation paths before use.
  • The README and CLAUDE.md differ on supported agents. This review is based only on the supplied sample and does not claim execution or independent verification.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision a76cda188826
Review evidence README.mdAGENTS.mdCLAUDE.mdhelmor-bump-vendors/SKILL.mdhelmor-cli/SKILL.mdhelmor-debug-loop/SKILL.mdhelmor-debug-operate/SKILL.mdsrc/index.tssrc/index.tsquick-switch/index.tsLICENSEpackage.jsonworkflows/ci.ymlworkflows/publish.ymltests/composer-ime.spec.tstests/sidebar.spec.tstests/streaming-footer-overlap.spec.ts
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/helmor.svg)](https://followagents.com/en/agents/helmor)
<a href="https://followagents.com/en/agents/helmor"><img src="https://followagents.com/badge/helmor.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v0.46.0 Helmor v0.46.0
    Release notes excerpt
    Minor Changes - [#944](https://github.com/dohooo/helmor/pull/944) [76b21ad](https://github.com/dohooo/helmor/commit/76b21ad74ffafc5263fb70704705ab5e68937460) Thanks [@dohooo](https://github.com/dohooo)! - Add Claude Opus 5 to the Claude Code model picker and make it the default: - Opus 5 replaces Opus 4.8 in the default model set, with all five effort levels and fast mode support. - Opus 4.8 stays in the catalog and can be re-enabled from Settings, without disrupting existing sessions that use it. Patch Changes …
    View on GitHub ↗
  2. v0.45.2 Helmor v0.45.2
    Release notes excerpt
    Patch Changes - [#936](https://github.com/dohooo/helmor/pull/936) [5e95c3b](https://github.com/dohooo/helmor/commit/5e95c3b3c0ad6c74201fd3e363c8121ff192e7ad) Thanks [@dohooo](https://github.com/dohooo)! - Update the bundled Claude Code and OpenCode coding agents to their latest versions. - [#937](https://github.com/dohooo/helmor/pull/937) [bda8c15](https://github.com/dohooo/helmor/commit/bda8c15c4684d879c7fee000b82b0e17f78a03ac) Thanks [@dohooo](https://github.com/dohooo)! - Fix Codex code-mode tool calls failing in signed macOS builds.
    View on GitHub ↗
  3. v0.45.1 Helmor v0.45.1
    Release notes excerpt
    Patch Changes - [#901](https://github.com/dohooo/helmor/pull/901) [2c75929](https://github.com/dohooo/helmor/commit/2c75929b378f330e97ae5e719581b32285b03c47) Thanks [@dohooo](https://github.com/dohooo)! - Update the bundled Claude Code and Codex coding agents to their latest versions. - [#932](https://github.com/dohooo/helmor/pull/932) [21f9c77](https://github.com/dohooo/helmor/commit/21f9c77022edd329ba22ea4bb16b37c8d6ad23eb) Thanks [@dohooo](https://github.com/dohooo)! - Keep workspace setup and Run Action scripts out of the background task bar above the composer. …
    View on GitHub ↗

FAQ

Am I locked into one coding agent?
No. The README names Claude Code, Codex, Cursor, OpenCode, and Kimi Code, and says users can bring their own logins, API keys, and custom providers.
Where does Helmor put task work?
It creates fresh Git worktrees and branches under ~/helmor/workspaces/, with one workspace per task.
Can I operate it without the desktop interface?
Yes. The CLI can add repositories, create and inspect workspaces, send tasks, and run actions; helmor mcp provides an MCP server over stdio.
Does it cover post-code delivery work?
The documented actions include creating PRs/MRs, merging, fixing CI, resolving conflicts, and stacked PRs for GitHub and GitLab.
Was this page helpful?
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Open Source Coding Agents, Compared

Open source coding agents ranked by FARS review — score, trust, license, language and maintenance side by side, with what each one is and isn't good at.

Claude Code Agents, Compared

Claude Code agents ranked by FARS review — compatibility is read from each agent's own AGENTS.md and documentation, not assumed, and only full support is listed.

MCP Agents, Compared

MCP agents ranked by FARS review — agents that ship or consume Model Context Protocol servers, with license, maintenance and trust scores side by side.