oh-my-hermes
⚚ The ultrawork agent with AI coworkers wired into you
What is oh-my-hermes?
⚚ The ultrawork agent with AI coworkers wired into you
Overview of oh-my-hermes
What it is
oh-my-hermes is an operating layer for Hermes Agent. It is described as an ultrawork agent with AI coworkers wired into the user. It runs on top of Hermes Agent by Nous Research and is an independent, unofficial layer. The project is open source under the MIT license.
Key features
- Each lane is tagged with a work category (ultrabrain, deep, visual-engineering, quick, etc.) and picks that lane's model chain and reasoning effort; when a provider rejects a model, the chain moves to the next one.
/dag-ulwgraph runs: a goal becomes a graph of small nodes that run in parallel, each on its category's model and effort; a separate node checks the goal, and failed nodes are repaired before the report.- Over a hundred
omh-*specialist skills (frontend, backend, Rust, security review, verification gates) are loaded into the run as tool calls by the router. - LSP in the loop: definitions, references and renames come from the language server, not text search; off by default, enabled via
lsp_toolsin the OMH plugin settings. - Long-term memory: nothing is remembered silently; each candidate is kept, refused or deferred with a written reason; the next session gets a recall pack ranked for its task and cut to a token budget; Hermes' own memory is never read or patched.
- OMH Native TUI: bare
omhopens OMH's own TUI on Hermes' gateway;/dag-ulwprints the box graph and a live lane tree; steer or interrupt an agent from the agent list, run a!shell line, and rewind with Esc Esc. - Evidence before 'done': every status names its stage and how sure OMH is about it; a run counts as verified only when a test, review or CI gate actually passed.
Use cases
oh-my-hermes is intended for users who want to run multiple AI coworkers in parallel, each with its own model and skill set, on top of Hermes Agent. It is suited for complex tasks that can be broken into parallel nodes, such as software development, code review, research, and quality assurance. The project provides workflows like ulw-context, ulw-interview, ulw-research, ulw-plan, ulw-work, dag-ulw, ulw-maestro, ulw-loop, ulw-qa, and ulw-perf.
Getting started
shcurl -fsSL https://omher.app/install | shomh setupFor Windows (PowerShell 5.1+):powershellirm https://omher.app/install.ps1 | iexOther installation methods include Homebrew, Bun, npm, and a Hermes skill tap path. See the repository README for details.
License and pricing
The project is licensed under the MIT License and is open source. No pricing information is stated.
Based on the project's public README and repository metadata.