outsourc-e/hermes-workspace

Native web workspace for Hermes Agent — chat, terminal, memory, skills, inspector.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 21 minutes ago
Added to GitGenius on September 1st, 2026
Created on March 16th, 2026
Open Issues & Pull Requests: 148 (+0)
GitHub issues: Enabled
Number of forks: 1,045
Total Stargazers: 6,579 (+0)
Total Subscribers: 35 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 16.0 hours
Mean response time: 2.1 days
90th percentile: 6.0 days
Tracked items: 237

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 25% of tracked open issues have had no activity in three months. Only 17% of issues opened in the past year have been closed. Three people close 93% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 51
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 66 days
Stale 30+ days: 44
Stale 90+ days: 14

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • bug (2)
  • help wanted (2)
  • question (2)
  • enhancement (1)

Most active issues this week

Detailed Description

Hermes Workspace is a web-based interface for orchestrating and controlling Hermes Agent instances, providing chat, terminal, memory, skills, and agent management in a unified workspace.

The tool addresses the challenge of managing multiple AI agents and their workflows without requiring manual task routing or custom forks of the underlying agent system. It works by connecting to vanilla Hermes Agent installations and providing a control plane that can dispatch tasks across multiple persistent agent instances. The workspace includes an orchestrator chat interface for decomposing missions, a multi-agent control plane for monitoring agent state and routing, a kanban-style task board for workflow planning, and checkpoint reporting for tracking agent progress. When a dashboard mission API is available, it uses that for dispatch; otherwise it falls back to native swarm mode using workspace-native orchestration.

Teams managing multiple Hermes Agents should consider this tool if they need centralized visibility and control without maintaining a fork of the base agent system. It suits projects requiring role-based task routing across specialized agent lanes—such as builders, reviewers, documentation, research, operations, and QA—and those needing persistent context across agent tasks. The tool is designed to keep humans focused on judgment calls while the agent swarm handles autonomous execution, including autonomous PR and issue handling, lab experiments, and repair workflows.

Development activity shows consistent engagement with the codebase through issue tracking and feature refinement. The project maintains active communication about architectural decisions, as evidenced by detailed issue discussions around fallback behavior and orchestration modes. Work spans both core functionality and operational concerns, with attention to both new capabilities and system reliability. The maintainers demonstrate responsiveness to integration requirements, particularly around maintaining compatibility with vanilla Hermes Agent installations and supporting multiple dispatch modes.