awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
hardbeat920 avatar

hardbeat920/monocode

0
View on GitHub↗
usemono.dev↗

Monocode

Monocode is a native desktop application, written in Rust, that runs several installed AI coding agent command-line tools from one interface. It reuses each tool's existing sign-in and the user's own subscriptions rather than selling tokens. Sessions live in tabs and split panes grouped by project, and each parallel task can run in its own Git worktree, so several agents can work on the same project without overwriting each other's files.

Beyond running a single agent, it supports splitting work across up to four worker agents, handing a session to another model with a recap, and continuing past provider usage limits by pausing queued prompts and resuming later or on another account. Persistent agents keep memory and standing instructions and can run recurring or event-triggered tasks. Agents can also be given opt-in command-line access to manage sessions, worktrees and notes. Sessions can run on a remote Windows, macOS or Linux host reached over SSH, so work continues if the desktop closes, and a paired phone can monitor and send prompts to desktop sessions.

The workspace also includes a file tree and code editor with diff view, embedded terminals, and checkpoints to keep or undo each agent turn. Staging, commits, branches and pull requests are handled in the app, and an inbox gathers issues, pull requests and failed CI checks from several code hosts and can send failures to an agent for repair. Supervised mode prompts for approval of file edits, though enforcement depends on each provider's own permission policy. The native app is built and run from a separate preview workspace, with Linux build dependencies documented for Debian-based and Fedora-based distributions.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Parallel Agent Runs - Runs several installed, logged-in coding agent tools side by side from one interface using the user's own subscriptions, without selling tokens.
  • AI Desktop Clients - Provides a native desktop client that runs several installed AI coding agent tools from one interface using the user's own sign-ins.
  • Coding Agent Workspaces - Runs installed, signed-in coding agent command-line tools from one native desktop interface using the user's own subscriptions.
  • Multi-Provider Orchestrators - Runs coding agents from several providers side by side in separate sessions, splits work across workers, and hands context between models.
  • Parallel Worktree Development Sessions - Creates and manages Git worktrees as independent working copies so multiple agent sessions run in parallel, with guarded deletion and orphan recovery.
  • Installed Agent CLI Launching - Launches coding agent command-line tools already installed on the machine and reuses their existing sign-ins so no separate credentials are needed.
  • Parallel Coding Sessions - Offers tabs and split panes for running, comparing and queueing many coding agent conversations side by side, grouped by project.
  • Subprocess Agent Adapters - Launches each installed coding agent tool as a child process and reuses its existing sign-in, so no separate credentials or token resale are involved.
  • Project and Session Organization - Organizes agent conversations as tabs and split panes grouped by project, so several sessions can be viewed side by side.
  • Local Agent Session Managers - Provides a desktop chat workspace over installed coding agents, with tabs as sessions, a composer, and several providers side by side.
  • Worktree Isolation Tools - Creates separate Git worktrees so parallel agent tasks work on the same project without interfering with each other's files.
  • Agent Session Parallelization - Treats each tab as a separate agent session, with split panes to compare sessions side by side and conversations grouped by project.
  • Remote Agent Session Hosting - Executes coding-agent sessions on a separate Windows, Linux or macOS host that owns the processes and database, so work continues if the desktop closes.
  • Worktree Isolations - Gives each parallel task its own Git worktree so several agents can edit the same project without overwriting each other's files.
  • Agent App Control Interfaces - Give an agent opt-in command-line access to start, read, message, stop, and archive sessions, manage worktrees and folders, and write notes.
  • Recurring Agent Scheduling - Runs agents on hourly, daily, weekday or weekly schedules, on demand, or on inbox events, with run history and isolated workspaces.
  • Autonomous Task Scheduling - Offers long-lived agents with memory and standing instructions that run scheduled tasks across projects.
  • Agent Usage and Account Trackers - Shows usage windows, percentages and reset times for each provider account and lets users switch accounts from the model picker.
  • Worktree Isolation - Gives each parallel agent task its own Git worktree so several sessions can edit the same project without overwriting each other's files.
  • Agent Switching Interfaces - Lets users choose among many supported coding agents per project and send messages to the selected one from a single interface.
  • Cross-Provider Session Sharing - Hands a session to another provider in a split pane with a recap card so context carries over.
  • Custom Agent Provider Connections - Discovers installed agent command-line tools and connects to eleven providers through stream-json, app-server, ACP, RPC and HTTP with server-sent events.
  • Parallel Sub-Agent Workers - Splits work across up to four worker agents in one checkout, with editable assignments, dependency handling, result review and grouped sidebar status.
  • Persistent Agent Hosting - Creates long-lived agents with their own conversation, assigned projects, standing instructions, memory and habits that survive restarts.
  • Scheduled and Event-Triggered Agent Wakeups - Runs persistent agents with memory and standing instructions on schedules or on inbox events such as failed CI checks.
  • Usage Limit Recovery - Detects provider usage limits, pauses queued prompts, and resumes after reset or on another model, provider, or saved account.
  • Agent Change Review Editors - Opens project files for editing and shows diffs inside the app so users can review what an agent modified.
  • Agent Turn Checkpoints - Captures changes before and after each agent turn, shows the exact diff, and offers keep and undo controls that preserve earlier edits.
  • Project File Previewers - Offers a project file tree, code editor with diff view, full-text search, command palette, preview tabs and image viewer.
  • Agent Command Line Interfaces - Exposes a local command-line interface for session, worktree and note operations so one agent can supervise others when the user opts in.
  • Agent-Driven CI Bug Fixes - Shows pull request check results with expandable job steps and sends failed checks individually or together to an agent for repair.
  • Agent Run Scheduling - Runs long-lived agents on hourly, daily or weekly schedules or in response to inbox events, with run history.
  • Mobile Companion Session Control - Lets a paired phone send text, start sessions and stop running turns on the desktop, keeping failed-send drafts instead of queuing offline.
  • Mobile Companion Session Followers - Pairs a phone with the desktop app to monitor conversations, send prompts, start sessions and stop turns on desktop agent sessions.
  • SSH Remote Sessions - Installs a verified host package on a remote machine through an existing SSH login, pairs the desktop and opens an auto-reconnecting private tunnel.
  • Pull Request and Issue Triage - Gathers issues, pull requests and failed CI checks from several code hosts into one inbox with filters, comments and a panel to start work.
  • CI Failure Repair Inboxes - Gathers issues, pull requests and failed CI checks from several code hosts into one inbox and sends failures to an agent to fix.
3,737 stars·416 forks·Rust·MIT·0 views

Star history

Star history chart for hardbeat920/monocodeStar history chart for hardbeat920/monocode

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Projects sharing features with Monocode

These projects share indexed features with Monocode. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • stablyai/orcastablyai avatar

    stablyai/orca

    118,546View on GitHub↗

    Orca is a cross-platform desktop workspace for running several terminal-based coding agents at once on a single repository. Each agent runs in its own embedded pane and gets its own isolated Git worktree, so parallel edits don't overwrite one another and merge later through normal Git. It hosts any command-line coding agent under the user's own subscription and credentials, and it shows how much of each agent's usage limit has been consumed and lets the user switch accounts without logging out. Orca also supports lead-and-helper delegation: one agent splits a large task, spawns workers in sep

    TypeScriptagent-ideai-agentsautomation
    View on GitHub↗118,546
  • getpaseo/paseogetpaseo avatar

    getpaseo/paseo

    9,118View on GitHub↗

    Paseo is an LLM coding agent orchestrator and multi-agent workflow manager designed to coordinate multiple AI agents across isolated git worktrees. It provides a unified control interface for managing these agents and their associated environments to execute complex programming tasks. The system distinguishes itself through a remote agent daemon that enables secure access to local coding agents via encrypted relays. It employs a git worktree environment manager to isolate parallel tasks into dedicated directories and branch-based server URLs, preventing file collisions and network port confli

    TypeScriptadeagentsclaude-code
    View on GitHub↗9,118
  • smtg-ai/claude-squadsmtg-ai avatar

    smtg-ai/claude-squad

    6,065View on GitHub↗

    Claude Squad is a terminal-based orchestrator for running multiple AI coding assistants in parallel. It manages the lifecycle of AI agent sessions from a single keyboard-driven interface, allowing users to launch, monitor, pause, resume, and terminate agents without leaving the command line. The tool isolates each agent's work in separate git worktrees, so changes remain on independent branches and never interfere with each other. Before any modifications are committed or pushed, users can review a diff preview of what each agent produced and approve or reject the changes. This diff-based app

    Goaiderclaude-codecli
    View on GitHub↗6,065
  • nightly-labs/openbotnightly-labs avatar

    nightly-labs/openbot

    6,235View on GitHub↗

    OpenBot is a local-first desktop workspace for running persistent AI agents. Each agent has its own instructions, avatar, dedicated workspace, task queue, memories, and file sharing, so ongoing work carries across sessions. It runs Codex, Claude, Grok, and custom OpenAI-compatible or ACP agents side by side and lets them collaborate through shared channels, with per-agent access levels set by role. A headless server build keeps agents running when the desktop is off. It can run in Docker, on a Linux machine, on a cloud instance, or in a managed sandbox that sleeps when idle and wakes on deman

    TypeScriptai-agentsbuncodex
    View on GitHub↗6,235
Compare all 30 related projects→

Frequently asked questions

What does hardbeat920/monocode do?

Monocode is a native desktop application, written in Rust, that runs several installed AI coding agent command-line tools from one interface. It reuses each tool's existing sign-in and the user's own subscriptions rather than selling tokens. Sessions live in tabs and split panes grouped by project, and each parallel task can run in its own Git worktree, so several agents can work on the same project without overwriting each other's files.

What are the main features of hardbeat920/monocode?

The main features of hardbeat920/monocode are: Parallel Agent Runs, AI Desktop Clients, Coding Agent Workspaces, Multi-Provider Orchestrators, Parallel Worktree Development Sessions, Installed Agent CLI Launching, Parallel Coding Sessions, Subprocess Agent Adapters.

Which projects share features with hardbeat920/monocode?

Projects with overlapping indexed features include: stablyai/orca — Orca is a cross-platform desktop workspace for running several terminal-based coding agents at once on a single… getpaseo/paseo — Paseo is an LLM coding agent orchestrator and multi-agent workflow manager designed to coordinate multiple AI agents… smtg-ai/claude-squad — Claude Squad is a terminal-based orchestrator for running multiple AI coding assistants in parallel. It manages the… nightly-labs/openbot — OpenBot is a local-first desktop workspace for running persistent AI agents. Each agent has its own instructions,… michael-denyer/pstack-claude — pstack-claude is a plugin and skills pack for AI coding assistants. It bundles rigorous engineering workflows,… claude-code-best/claude-code — Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software…