Stars
Forks
Watchers
Developer links
Hermes Workspace
Hermes Workspace serves as a dedicated command center for orchestrating autonomous AI agents, combining multi-model conversational flows with direct system execution in a unified web environment. Operators can execute multi-turn agent missions while observing live reasoning paths, tool dispatches, and file system mutations as they occur in real time. The built-in memory browser lets users inspect episodic recollections, search indexed agent knowledge bases, and edit persistent recall records directly from the interface. A comprehensive skill catalog provides instant activation and parameter tuning for over one hundred modular tool capabilities, ranging from web scraping to programmatic code generation. The embedded browser terminal delivers pseudoterminal sessions alongside running agents, enabling human operators to execute diagnostic commands and inspect project workspaces without switching windows. Conductor and Swarm management panels coordinate parallel sub-agent workers to break down complex research directives into asynchronous subtasks with automated status tracking. Integrated model switching allows teams to route individual execution steps dynamically between Anthropic Claude, OpenAI, OpenRouter, and self-hosted Ollama instances. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Unified Autonomous Agent Control
- Orchestrate autonomous agent missions, observe live reasoning steps, and monitor external tool invocations directly through an interactive web interface without managing fragmented command-line processes.
- Transparent Memory System Auditing
- Search, inspect, and modify long-term agent memories and episodic knowledge stores to correct hallucinations, prune outdated records, and guarantee reliable recall across extended task executions.
- Embedded Browser PTY Terminal
- Execute interactive shell sessions directly inside the agent workspace environment, allowing operators to run builds, inspect file changes, and diagnose system states without leaving the browser tab.
- Flexible Multi-Model Routing
- Switch model providers seamlessly within active agent sessions, choosing between hosted APIs like Anthropic and OpenAI or local inference engines like Ollama and vLLM without context loss.
Features
- Streaming Agent Chat
- Renders real-time Server-Sent Events token streams with collapsible tool call cards, markdown formatting, and syntax-highlighted code blocks.
- Persistent Memory Browser
- Provides visual inspection and direct editing of structured episodic memory entries and agent persona configuration files.
- Modular Skill Catalog
- Manages a library of over one hundred agent skills, allowing administrators to enable, configure, and inspect tool capabilities.
- Multi-Agent Conductor Swarms
- Dispatches parallel sub-agents across distributed workloads with real-time status grids, error isolation, and aggregated mission results.
- Integrated Workspace Terminal
- Provides a full-color web pseudoterminal connected to the host environment for monitoring agent file modifications and running CLI commands.