Back to directory

Hermes for Web

A Korean-language browser workbench for the Hermes coding agent, adding one-click setup packs, saved artifacts, a personalized start screen built from the agent's own memory, and support for both local and remote models.

Hermes for Web

Hermes for Web is a browser-based companion to the Hermes Agent command-line tool. Where the command line is described as the engine room and a messaging bot as a radio, this project positions itself as the cockpit: a workspace for creating, checking, saving and sharing work rather than only chatting with the assistant.

It reads the signed-in user's Hermes memory and profile to personalize its start screen, bundles setup packs that pre-configure common integrations such as Obsidian and Telegram sharing in one click, runs a simple quality check on results before they are used, and lets a user create, open, delete and share artifacts such as notes, briefs and memos from within the interface. It supports both local models, such as a project's own local model, and remote GPT-family models side by side.

A Cherry Blossom visual theme is the default, alongside two alternative themes.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.