first-fluke/oh-my-agent
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
Quick read
Latest capture 2026-09-22 03:05
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
6 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 3
Claude Code 3
84 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +717
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks, and OmniServe APIs.
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.