AgentToolDrop

26 of 66

Atlas

Desktop app that links each agent commit to the session, prompts and tool calls behind it

  • score 47
  • 9.6k stars
  • 60.6 stars/day since creation
  • pushed
  • alpha-0.3.4 on
  • Apache-2.0

Download, no command

Download the macOS or Windows app

Why you'd want it

Atlas records every agent session locally in .atlas/sessions.db and links each commit back to the session that produced it as a checkpoint, with the prompts, tool calls and file changes kept together. You can select a checkpoint and chat with it, and it answers from what happened in that session. It runs Claude Code, Codex, its own native agent or agents from the ACP registry side by side against the same codebase. Shared agent memory, matched with on-device embeddings, puts a decision made by one agent into the next agent's prompt. The README says local mode works with no account and that secrets are scrubbed before anything is written to disk.

Best for

  • Tracing which agent made which commit and why
  • Running Claude Code and Codex on one codebase
  • Sharing context between agents

Use it when

You run more than one coding agent on a project and want each commit tied to the prompts, tool calls and reasoning behind it, with memory shared between the agents.

Skip it if

Releases are tagged alpha (latest alpha-0.4.1), and the README says QA on the long tail of registry agents is ongoing. Only macOS 13+ and Windows 10+ (x64) are supported; the README calls Linux untested. It runs agents that execute commands, can run through your existing Claude Code or Codex subscription, and has anonymous usage analytics on by default (the README points to TELEMETRY.md for turning them off); signing in to an organization syncs across devices and teammates.

Editor's note

The README offers a .dmg for macOS (Apple Silicon or Intel) and an .msi for Windows, and also documents building from source with Bun and Rust. The alpha label comes from the release tags, not the README.

Related tools

Same category or shared tags.

  1. Rank 30

    Munder Difflin

    Devtool

    Desktop app that runs Claude Code, Codex and other agent CLIs as a team coordinated by one agent

    • score 45
    • 8.9k stars
    • 35.3 stars/day last 4 days
    • pushed
    • v0.5.5 on
    • MIT

    Build from source

    git clone https://github.com/chaitanyagiri/munder-difflin.git
cd munder-difflin
npm install        # postinstall rebuilds node-pty against Electron's ABI
npm run dev        # launches the Electron app with hot reload
    Use it when, skip it if, stats for Munder Difflin

    Why you'd want it

    Munder Difflin is an Electron desktop app that wraps terminal agent CLIs such as Claude Code and Codex, each running as a real process in its own pseudo-terminal. You brief one orchestrator agent, which the README calls Michael or the GOD agent, and it assigns work and routes messages between agents through mailboxes in a shared hive of plain files. Spend, scope and destructive operations are escalated to an approvals queue for you, and the README says each agent has configurable autonomy and a circuit breaker for loops. Agents keep markdown memory with an optional semantic recall index, and per-agent git worktrees are available as optional isolation. It uses the subscriptions you already have for the CLIs, with bring-your-own keys and local models as options.

    Best for

    • Running several Claude Code and Codex agents in parallel
    • Briefing one orchestrator instead of many agents
    • Watching and steering agent terminals from one window

    Use it when

    You already use agent CLIs such as Claude Code or Codex and want several running on your own machine, coordinated by one orchestrator agent with human approval for spend and destructive operations.

    Skip it if

    The README calls it pre-release software, and it is an Electron desktop app that needs at least one agent CLI already installed, not a library or a headless tool. It runs real agent CLIs as processes you configure the autonomy of, stores provider keys and custom secrets, accepts inbound webhooks, and its dictation feature asks for Microphone and Accessibility permissions on macOS, so review the autonomy and permission settings before use. Official builds send anonymous usage events (opt out in Settings, with DO_NOT_TRACK, or by building from source), and the Pro tier with the Stapler and new sidebar is paid.

    Stats

    New and rising score
    45 of 100
    Stars per day, last 4 days
    35.3
    Release
    v0.5.5,
    License
    MIT
    Pricing
    Free tier + paid
    Works with
    Claude Code, Codex, Gemini CLI, Cursor, macOS, Linux, Windows
    Forks
    1,238
    Open issues
    255
    GitHub checked

    Full stat block for Munder Difflin

  2. Rank 9

    Orca

    Devtool

    Runs several CLI coding agents side by side, each in its own git worktree, in one desktop app

    • score 62
    • 99k stars
    • 1,211 stars/day last 5 days
    • pushed
    • v1.4.232 on
    • MIT

    Download the app, or install with Homebrew on macOS

    brew install --cask stablyai/orca/orca
    Use it when, skip it if, stats for Orca

    Why you'd want it

    Orca is a desktop app for running Claude Code, Codex, OpenCode, Pi and other terminal agents in parallel, each in an isolated git worktree, so you can fan one prompt across several agents, compare the results and merge the one you want. It combines terminal splits, VS Code's editor, an embedded Chromium with a Design Mode that sends an element's HTML, CSS and a screenshot into a prompt, GitHub and Linear task views, SSH worktrees on remote machines and inline comments on AI diffs. A CLI lets agents drive Orca themselves, and iOS and Android companion apps notify you when an agent finishes and let you send follow-ups.

    Best for

    • Comparing several agents on one task
    • Managing many worktrees in one place
    • Steering agents from a phone

    Use it when

    You run several CLI coding agents at once and want one window for their worktrees, terminals, diffs and reviews instead of juggling terminal tabs.

    Skip it if

    You prefer a terminal-only setup or use one agent at a time. It collects anonymous usage data unless you opt out, its Computer Use feature lets agents operate desktop apps, and it ships releases almost daily with a large open issue and pull request backlog.

    Stats

    New and rising score
    62 of 100
    Stars per day, last 5 days
    1,211
    Release
    v1.4.232,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor, macOS, Windows, Linux
    Forks
    6,307
    Open issues
    8,569
    GitHub checked

    Full stat block for Orca

  3. Rank 42

    CC Safety Net

    Devtool

    Blocks destructive git and file commands and reads of secret files before a coding agent's tool call runs

    • score 39
    • 1.7k stars
    • 12.9 stars/day last 5 days
    • pushed
    • v2.6.16 on
    • MIT

    Install into your coding CLIs with npx

    npx -y cc-safety-net@latest install
npx -y cc-safety-net@latest doctor
    Use it when, skip it if, stats for CC Safety Net

    Why you'd want it

    CC Safety Net installs as a pre-execution hook in coding CLIs including Claude Code, Codex, Cursor, Gemini CLI, OpenCode and Copilot CLI, and parses what each command does, so wrapping it in bash -c or python -c or reordering flags does not hide it. It blocks commands such as git reset --hard, git push --force and rm -rf on dangerous targets, and access to SSH keys, .env files, ~/.aws and coding CLI credentials. Presets are tuned in a local GUI, official rulebooks add blocks for Terraform, AWS, gcloud and Azure, and committing .cc-safety-net/ shares the policy through git.

    Best for

    • Stopping agent force pushes and hard resets
    • Keeping agents away from .env files and SSH keys
    • Teams running several coding CLIs

    Use it when

    You let a coding agent run shell commands and want a check that refuses destructive git and file operations before they execute.

    Skip it if

    You need containment: the README says it is not a sandbox and does not contain processes, set filesystem permissions or watch network egress. It is maintained mostly by one developer and needs Node.js 18 or higher.

    Stats

    New and rising score
    39 of 100
    Stars per day, last 5 days
    12.9
    Release
    v2.6.16,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor, Gemini CLI, macOS, Linux, Windows
    Forks
    88
    Open issues
    1
    GitHub checked

    Full stat block for CC Safety Net

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/atlas.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'