rlaope /oh-my-hermes
⚚ The ultrawork agent with AI coworkers wired into you
★ 5,702⑂ 466👁 16⑃ 2,383● 522▤ 41
+30
日增长
+619
周增长
5,702
stars
466
forks
16
watchers
2,383
prs
522
issues
41
releases
README
omher desktop @ beta Your Hermes bots and coding agents, in one window. macOS (Apple silicon) · macOS (Intel) · Windows · All releases → The ultrawork agent with AI coworkers wired into you. Just type dag-ulw. English | 简体中文 | 日本語 | Русский | 한국어 | Español | Français | Deutsch | Português (Brasil) | Italiano oh-my-hermes is an operating layer for Hermes Agent. You keep talking to Hermes. OMH puts a coworker with its own skill and model on each lane, in parallel. It never patches or replaces Hermes, and it never reports planned work as done. Install sh curl -fsSL https://omher.app/install | sh omh setup Windows and other options → What you get - The right model for every lane. Each lane is tagged with a work category: ultrabrain, deep, visual-engineering, quick and more. The category picks that lane's model chain and reasoning effort, and you can edit every chain. When a provider rejects a model, the chain moves to the next one instead of silently downgrading. omh model opens the picker; see which model runs each lane. - /dag-ulw graph runs. Your goal becomes a graph of small nodes, and the ready ones run in parallel. Each node runs on its category's model and effort; nodes running at once never share a write scope. A separate node checks the goal, and failed nodes are repaired before the report. - Expert skills on demand. A hundred-plus omh- specialists: frontend, backend, Rust, security review, verification gates. You never call them; the router loads the right ones into the run as tool calls. - LSP in the loop. Definitions, references and renames come from the language server, not text search. Aliases, re-exports and shadowed names are renamed by meaning, not by matching text. Off by default; enable lsp_tools in the OMH plugin settings. - Long-term memory you can trust. 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. Bare omh opens OMH's own TUI on Hermes' gateway; switch its launch look with /theme. /dag-ulw prints the box graph, then a live lane tree with each lane's model, effort and tokens. 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. Plan · not run · Code · reported done · Test · verified A run counts as verified only when a test, review or CI gate actually passed. DAG-ULW Just type /dag-ulw, and you're a graph engineering master. Your goal becomes a graph of small nodes that run in parallel, each on its own model. A separate node verifies the goal before you get the report. Built on Hermes Agent by Nous ResearchThe agent OMH runs on. OMH is an independent, unofficial layer on top. OmO by @code-yeongyuWher
Top issues
#1056Run the paid-live benchmark for the four new family calibrations (mistral, llama, codestral, solar)6 comments · 2026-08-21#1836Measurement path for the Claude composer calibration2 comments · 2026-09-23#1333[Benchmark]: Hermes alone vs Hermes + OMH on this repository's own merged PRs, four quotable numbers2 comments · 2026-09-05#1817[Feature]: Shadow, decline, refuse and replay — turning an OMH decision surface on from the owner's own traffic1 comments · 2026-09-22#1692[Feature]: Relational database work has no owner (index sizing, online migration, lock-safe DDL, N+1)1 comments · 2026-09-19#1327[Benchmark]: measure what a calibration changes, on tasks that provoke the trait it counters1 comments · 2026-09-05#1815[Feature]: Measure the routing-questions lane's model and decision-model arms0 comments · 2026-09-22#1789No chat trigger reaches the story close: the token set over-fires and the phrase list cannot be made precise0 comments · 2026-09-20
Latest release
v4.0.8 v4.0.8 2026-11-15- The OMH TUI shows a compression as one gauge row, and a prompt typed meanwhile goes on by itself. /compact (or /compress) no longer prints the long "Compressing: Hermes summarizes the older turns…" notice above a second spinner row. One row now reads ✻ Compacting conversation… ━━━━━━──── (30s), with a blank row between it and the composer. Hermes sends no progress for a compression, so the gauge follows the time waited, never fills on its own and shows no percent; Hermes' ✓ Compressed: … report closes it. A prompt sent during the compression waits in the ⧗ queue (Ctrl+Enter has no