AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Code Assistant/
oh-my-openagent
oh-my-openagent logo

oh-my-openagent

Active·★ 71.0k·NOASSERTION·Updated 2026-11-18
★ Most Popular

oh-my-openagent (OmO) is an advanced terminal-first coding agent built on senpi (a fork of pi-mono) designed to eliminate manual intervention in complex engineering tasks. Centered around its signature 'ultrawork' (ulw) and 'mass ulw' directives, OmO transforms high-level prompts into multi-agent directed acyclic graphs (DAGs), where specialized sub-agents independently research, plan, execute, and verify code against real system surfaces before declaring a task complete.

Its standout architectural innovation is the 'Kibitzer' dual-agent memory model. Operating alongside the primary high-capability model, a lightweight auxiliary model continuously reviews a Git-backed repository of markdown memory notes. By proactively retrieving historical decisions and conventions, it prompts the lead agent before it can repeat prior errors, drastically reducing context re-explanation and preserving organizational domain knowledge across long development cycles.

Installation is streamlined via a one-line installer (curl -fsSL https://get.omo.dev/install.sh | bash) or the omo-ai npm/bun package. OmO natively supports unified subscription logins (/login) across Claude, ChatGPT, Kimi, and GLM, and features built-in tools such as browser automation and live configuration reloads. However, users should plan for substantial token consumption when dispatching massive parallel agent graphs on deep-reasoning frontier models.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-12.

License
Not detected by GitHub
Latest release
v5.1.69 · 2026-11-11
Last commit
2026-11-12
Contributors
378
Forks
5,842
Open issues and PRs
2,543
First published
2025-12-03
npm package
omo-ai 5.1.69 · 8,071 downloads last week

Source: GitHub, npm and PyPI public APIs.

#ai#ai-agents#anthropic#chatgpt#claude#claude-skills#codex#cursor
$ Install
$ npm i -g omo-ai
↗ Visit site★ GitHub
01

Features

01Graph-oriented work splits jobs into coordinated tasks.
02Markdown memory is stored in a Git repository.
03Configuration supports provider, model, MCP and skill choices.
02

Why choose it

+Ultrawork DAG workflow autonomously plans, executes, and verifies code before marking tasks complete.
+Kibitzer dual-agent memory keeps track of developer preferences and past mistakes via Git-backed markdown files.
+Flexible multi-model routing allows seamless switching between frontier and cost-effective models.
+Zero-config migration paths and live config reloading for custom skills, prompts, and settings.
03

Trade-offs

!Massive multi-agent orchestration (mass ulw) incurs very high token usage on frontier models.
!Licensed under SUL-1.0 (Source Available), which imposes usage restrictions unlike permissive MIT/Apache licenses.
!Highly autonomous multi-agent execution loops require active monitoring to prevent infinite build retry cycles.
!The npm package is registered as omo-ai, which can cause installation confusion with unrelated packages.
04

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-11
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v5.1.69 (2026-11-11)
Open issues
2543
Recent issues with at least one comment
2/21
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 607, 1156, 1068, 634, 849, 1562, 945, 2089, 2599, 2304, 1986, 899

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1397 [RFE]: Automated Learning Capture System76 comments · 2026-02-02
  • #8235 Release binary diet: --splitting + full minify, embedded payload slim, provider registration adoption, retired browser CLIs, dependency clea60 comments · 2026-09-13
  • #673 [Feature]: Disable oh-my-opencode via cli command25 comments · 2026-01-10
  • #854 [Feature]: Add `/omo-spec` — A Unified Spec‑Driven Workflow for Oh‑My‑OpenCode20 comments · 2026-01-16

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

cli
Native binary or omo-ai package; provider setup required
Verified via docs
06

Quick start

1
$ npm i -g omo-ai
07

Use cases

↳Coordinate a multi-part coding task.
↳Retain working context across sessions.
↳Migrate an existing supported agent setup.
08

Alternatives

⚡Top VS:
VShermes-agent★264.2k→VSGraft★11.3k→VScoplay-unity-plugin★167→VSclaude-mem★118.0k→
hermes-agent logo
hermes-agent★ 264.2k
The agent that grows with you
VSCompare→
Graft logo
Graft★ 11.3k
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
VSCompare→
t3code logo
t3code★ 64.1k
The best way to control Claude Code, Codex and more from any computer or phone
anythingmcp logo
anythingmcp★ 803
Self-hosted MCP gateway & API-to-MCP bridge. Convert REST/SOAP/WSDL/GraphQL/SQL APIs into MCP servers for Claude, ChatGPT, Gemini, Copilot, Cursor. OpenAPI/Postman/WSDL import, OAuth2, RBAC, audit log. 29 pre-built adapters (DHL, DATEV, Weclapp, Personio, Handelsregister, Shopware...). Source-available.
coplay-unity-plugin logo
coplay-unity-plugin★ 167
Unity plugin for Coplay
VSCompare→
claude-mem logo
claude-mem★ 118.0k
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
VSCompare→
humanizer logo
humanizer★ 70.4k
Agent skill that removes signs of AI-generated writing from text
VSCompare→
nuwa-skill logo
nuwa-skill★ 38.5k
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
code-yeongyu /
oh-my-openagent
↗

Multi-agent graph engineering CLI with Ultrawork and Git-backed markdown memory

71.0k5.8k
Last commitToday
StatusActive
CategoryCode Assistant
Contributors378
Latest releasev5.1.69
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.