186 — OmniHive: role-cycling runtime, no recovered run archive
Updated 2026-09-06 UTC

Finding
OmniHive is a new bilingual agent-company software lead. Its inspected desktop runtime implements serial role rotation and local memory handoffs. This pass recovered code, not an executed company history or an externally published product. Lower priority unless a concrete run or output is linked.

Sources and preservation
https://github.com/KuaaMU/omnihive
Pinned full tree d566b7d68fa29928f6326bd4ac3daa6c966d324b: 595 entries, nontruncated.
Private evidence: investigation/china/186-private/.
Retrieved and Git-blob-verified source:
app/src-tauri/src/commands/runtime/cycle_executor.rs — 8,200 bytes
app/src-tauri/src/commands/runtime/loop_manager.rs — 10,940 bytes
app/src-tauri/src/engine/logging.rs — 1,318 bytes
No dependencies were installed; no investigated source, credential discovery, skill or model call was executed.

What the inspected code does
loop_manager.rs starts a background runtime thread. Inside its main loop it chooses current_agent using (cycle - 1) modulo the number of roles, then synchronously calls run_api_cycle. This path is one role per cycle, not evidence of simultaneous execution by all advertised roles. Multiple independently started projects or other code paths were not exhaustively assessed.
cycle_executor.rs loads the role file, memories/consensus.md, role memory and a handoff note. It makes a configured API call, extracts structured consensus/reflection/handoff text, and writes local state. If no handoff is extracted, it uses a truncated response. It can queue skill requests. Cycle history is serialized to .cycle_history.json.
The inspected function does not itself contain an arbitrary tool-execution loop or a public publishing action. Its API client and all alternate execution paths were not audited, so this is not a claim that the entire application lacks those capabilities.

Released-output check
The complete tree contains no path ending .cycle_history.json or consensus.md and no path containing /memories/. This scoped inventory does not establish that no user has run the software; it establishes that the named runtime outputs are absent from this tree.
The public issues endpoint returned four entries, all pull requests, covering architecture/control-plane changes and review fixes in March2026. No ordinary incident/run issue appeared in that response. The pass did not inspect release binaries, all PR comments or discussion threads.
README feature statements about agent companies and 24/7 operation remain claims about software capability; they are not substitute evidence for saved execution.

Attribution and relevance
Bilingual UI and a GitHub namespace are not Chinese-lab attribution. Serial role exchange with shared state can be a multiagent design, but it does not prove an independently operating swarm or establish a connection to public paste/wiki activity. No XZ connection was found or implied.
Next useful evidence would be an intentionally released cycle history joined to a dated product commit or public action. Broadening to other concrete output-bearing projects has higher expected value than inspecting more of this framework without such an artifact.