Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
The team focused on improving reliability when connections drop or sessions disconnect: offline hosts now recover pending messages, Databricks desktop sessions reconnect automatically after network issues, and several edge cases around session hydration and handoffs were fixed. On the interface…
Get this in your inbox every Monday →A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in omnigent's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
fix: keep unpinned Polly SDK parents on managed Claude credentials (#9293)
fix(web): keep same-page anchor links inside the HTML preview (#9239)
fix(harnesses): clarify startup configuration, MCP status, and navigation (#9283)
feat(host): report host daemon crashes and exits to the debug-log sink (#8911)
fix(web): invoke skills whose names contain spaces from the / menu (#9260)
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
