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
outsourc-e avatar

outsourc-e/hermes-workspace

0
View on GitHub↗
hermes-workspace.com↗

Hermes Workspace

Hermes Workspace is a browser-based workspace for chatting with, supervising, and managing Hermes AI agents. It brings a streaming chat interface, a file browser with a code editor, a browser terminal, and panels for agent memory and skills into one web app. Chat replies stream as they are written, with tool calls, thinking content, and highlighted markdown rendered inline. The interface can connect to a stock agent gateway, OpenAI-compatible servers, or local model runtimes such as Ollama, LM Studio, and vLLM.

Beyond single-agent chat, the workspace works as a multi-agent orchestration dashboard. Missions can be split into tasks and routed to specialist workers such as builder, reviewer, QA, and researcher. Persistent swarm workers are tracked on a kanban board, and their output is gated at checkpoints where a person can approve, reject, or request revisions. Rejected checkpoints roll the working tree back to its prior git state. Recurring agent jobs can be scheduled, and memory can be searched and edited as markdown. Skills can be browsed in a marketplace and scanned for suspicious patterns before installation.

Access control is a notable part of the surface: optional password login, authenticated API routes, rate limiting, path-traversal checks, and a refusal to bind to external interfaces without a password. Risky agent commands can pause for manual approval.

It is self-hosted and installable as a progressive web app. Deployment options include a one-command installer, Docker and Docker Compose, a Nix flake and NixOS service, and desktop installers for macOS and Windows. Remote access is supported over a private Tailscale network.

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

  • Hermes Agent Desktop Clients - Offers a browser front end for chatting with, supervising and managing Hermes agents, with file editing, terminal, memory and skills panels.
  • Interactive Agent Chat Interfaces - Streams agent replies live in the browser with expandable tool calls, thinking content, and highlighted markdown across several chat backends.
  • Agent Session Terminals and File Browsers - Combines agent chat, a workspace file browser with editor, a browser terminal, and memory and skills panels in one web interface.
  • Agent Chat Interfaces - Provides a single browser-based conversation view to send messages to the agent and read its replies.
  • Agent Orchestrators - Dispatches tasks to long-running tmux-backed agent workers by role, with orchestrator chat, kanban lanes, checkpoint reports, and a review gate.
  • Skill and Memory Managers - Provides panels to search, edit, and organize agent memory as markdown and to browse and install reusable skills.
  • Mission Dispatchers - Takes a single task, decomposed mission, or broadcast and routes the pieces to the appropriate agent workers automatically.
  • Multi-Agent Orchestration - Splits missions into tasks, routes them to specialist workers, tracks them on a kanban board and reviews output at approval checkpoints.
  • Multi-Agent Task Orchestrators - Coordinates planning, delegation, and task tracking across specialized worker agents using todo lists, kanban boards, and sub-agent dispatch.
  • Agent Swarms - Coordinates groups of persistent worker agents with autopilot orchestration, lifecycle handling, shared memory, and parallel task execution.
  • Agentic Workspaces - Combines chat, file browsing, terminal, memory, and skills panels into one browser workspace where an outside agent can be paired and managed.
  • Review Approval Workflows - Collects checkpoints, blockers and handoffs into reports and an inbox so a person approves, rejects or requests revisions on a few items.
  • Streaming Chat Interfaces - Streams agent replies in real time across several sessions, showing tool calls and highlighted markdown inline.
  • Recurring Agent Scheduling - Creates cron-style agent jobs with prompts and delivery settings, with pause, resume, trigger, edit, and delete controls and run output.
  • Agent Fleet Monitoring Dashboards - Aggregates sessions, model usage mix, cost ledger, and attention items into one agent overview dashboard.
  • Agent Gateways - Connects directly to an unmodified agent gateway through its standard model, session, skill, config, and job endpoints without a custom fork.
  • Agent Memory Editors - Lists agent memory files, searches contents line by line, and previews and edits each as formatted markdown.
  • Agent Mission Control - Starts missions, assigns workers, and shows live output and running costs from a single mission-control screen.
  • Agent Worker Monitors - Shows each worker as a card with role, state, current task, model, recent activity, and room membership.
  • Agent Change Reviews - Presents agent code changes as diffs with check results so reviewers can approve, open a pull request, reject, or request revisions.
  • Skill Marketplaces - Lists thousands of agent skills with origin badges and filters, and offers a built-in marketplace for discovering more.
  • Chat Session Management - Lets users create, rename, pin, fork, search, and delete conversations with auto-generated titles so past agent chats are easy to find.
  • Human Approval - Pauses sensitive agent commands and asks a person to approve them through an interface pop-up before they run.
  • Human Approval Gates - Pauses risky agent commands and asks a human to approve them through a pop-up before they run.
  • Language Model Backend Switching - Lets users switch between hosted providers and local servers such as Ollama, LM Studio, and vLLM for the agent backend.
  • Live Agent Controls - Lists registered agents and sessions with their role and model, and lets users pause, steer, or kill live agents.
  • Local Model Integrations - Connects the chat interface to locally running model runtimes so conversations run on models hosted on your own machine.
  • Model Provider Configurations - Configures hosted and local model providers through a guided wizard supporting API keys, OAuth flows and any OpenAI-compatible server.
  • Persistent Agent Roles - Provides distinct builder, reviewer, QA, researcher, and strategist workers, each with its own tools and skill bundle.
  • Specialist Task Routing - Breaks a mission into tasks and assigns each to the specialist agent whose role, capabilities, and task types fit best.
  • Shared Agent Task Boards - Tracks tasks across kanban lanes with status kept separate from assignee so work can be reassigned without losing progress.
  • Coordinator-Worker Orchestration - Takes one chat request and routes it to chosen workers, splits it into a plan, or broadcasts it, nudging drifting workers.
  • Work Tracking Boards - Tracks tasks across backlog, ready, running, review, blocked, and done lanes, with reports and an inbox for checkpoints.
  • Browser Terminals - Opens persistent shell sessions in the browser with full color support and live streamed output using the host platform's default shell.
  • Working Tree Checkpoint Restoration - Reverts the working tree to its pre-task git state when a checkpoint is rejected so later agents do not inherit broken code.
  • One-Command Deployments - Offers a single shell command that sets up the workspace, the gateway, and sensible defaults in one step.
  • Progressive Web App Installations - Installs the workspace as a progressive web app with an app-like window, keyboard shortcuts, and offline support.
  • Self-Hosted Agent Management Dashboards - Runs a self-hosted web console for managing agents via Docker, Compose, Nix, NixOS services and desktop installers, with private remote access over Tailscale.
  • Agent Endpoint Access Control - Requires authentication on every API route, with optional password login, rate limiting, path-traversal checks and manual approval of risky agent commands.
  • Password Access Restrictions - Offers optional password login for the workspace with authenticated routes, rate limiting, and a refusal to bind remotely without a password.
  • Interface Access Security - Protects the web interface with route authentication, password login, rate limiting, strict cookies, path-traversal guards, and a startup check against unprotected remote binding.
  • Tool Call Rendering - Turns tool-call markers in streamed output into compact inline pills in the chat, including when connected to a stock gateway.
  • Agent Interaction Streams - Streams agent output to the browser as produced, rendering tool calls, multiple open sessions, and highlighted markdown code.
  • Workspace File Previews and Editing - Shows a sandboxed file tree with previews, uploads, file operations, and a code editor, blocking access outside the workspace root.
  • Developer Tools and Workspaces - Web-based workspace with chat, terminal, memory browser, and manager.
  • Level-Up Blueprints - Feature-rich daily user interface cockpit for agents.
6,804 stars·1,059 forks·JavaScript·MIT·5 views

Star history

Star history chart for outsourc-e/hermes-workspaceStar history chart for outsourc-e/hermes-workspace

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.

Frequently asked questions

What does outsourc-e/hermes-workspace do?

Hermes Workspace is a browser-based workspace for chatting with, supervising, and managing Hermes AI agents. It brings a streaming chat interface, a file browser with a code editor, a browser terminal, and panels for agent memory and skills into one web app. Chat replies stream as they are written, with tool calls, thinking content, and highlighted markdown rendered inline. The interface can connect to a stock agent gateway, OpenAI-compatible servers, or local model…

What are the main features of outsourc-e/hermes-workspace?

The main features of outsourc-e/hermes-workspace are: Hermes Agent Desktop Clients, Interactive Agent Chat Interfaces, Agent Session Terminals and File Browsers, Agent Chat Interfaces, Agent Orchestrators, Skill and Memory Managers, Mission Dispatchers, Multi-Agent Orchestration.

Which projects share features with outsourc-e/hermes-workspace?

Projects with overlapping indexed features include: ekkolearnai/ekko-studio — Ekko Studio is a self-hosted AI agent workspace that runs several agents together in shared chats and keeps sessions… agegr/pi-web — pi-web is a self-hosted web interface for running and reviewing sessions with an AI coding agent from the browser.… mervinpraison/praisonai — PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and… fathah/hermes-desktop — Hermes Desktop is a cross-platform desktop application that acts as a graphical companion for installing, configuring,… lastmile-ai/mcp-agent — mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools… camel-ai/camel — This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified…

Projects sharing features with Hermes Workspace

These projects share indexed features with Hermes Workspace. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • ekkolearnai/ekko-studioEKKOLearnAI avatar

    EKKOLearnAI/ekko-studio

    11,715View on GitHub↗

    Ekko Studio is a self-hosted AI agent workspace that runs several agents together in shared chats and keeps sessions and data on the user's own machine. It streams replies, tool traces, and generated-file previews across persistent sessions, and it hosts group rooms where multiple agents answer when mentioned. It also detects, installs, configures, and launches third-party command-line coding agents from one interface, with built-in terminals, session history, a workspace picker, and file diffs. Beyond chat, the workspace includes a visual canvas for building runnable agent workflows with con

    TypeScriptagentai-agentchat-ui
    View on GitHub↗11,715
  • agegr/pi-webagegr avatar

    agegr/pi-web

    8,089View on GitHub↗

    pi-web is a self-hosted web interface for running and reviewing sessions with an AI coding agent from the browser. Coding-agent sessions run on a server against local project folders and Git worktrees. Replies and tool calls stream into a chat window as they happen, and conversations can be branched, forked, or compacted as the work continues. Sessions are organized by project and Git worktree. Checkouts of the same repository are grouped together, and each session remembers the directory it started in. Sessions can be resumed, renamed, pinned, archived, exported, and deleted. Past conversati

    TypeScript
    View on GitHub↗8,089
  • mervinpraison/praisonaiMervinPraison avatar

    MervinPraison/PraisonAI

    9,325View on GitHub↗

    PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

    Pythonagentsaiai-agent-framework
    View on GitHub↗9,325
  • fathah/hermes-desktopfathah avatar

    fathah/hermes-desktop

    14,548View on GitHub↗

    Hermes Desktop is a cross-platform desktop application that acts as a graphical companion for installing, configuring, chatting with and managing a Hermes AI agent. The agent can run locally on the user's machine or on a remote machine, reached through an API server URL and key or through SSH tunnels. A streaming chat interface shows replies, reasoning, tool progress and live token and cost counts as they arrive, supports slash commands, and lets users search and resume past sessions. Beyond chat, the app works as a management console for the agent. Users can create and switch between isolate

    TypeScriptaiai-agentautonomous-agents
    View on GitHub↗14,548
Compare all 30 related projects→