Repository Issue Activity (beta)

#435 docs: feature AIUI Sports Agents in use cases

#434 Undocumented 1024-dim embedding floor fails asynchronously while /health still reports embed: true

#433 memory/add always 500s on default memorize.mode = "agent" — DetectionResult missing should_wait (everalgo-boundary 0.3.0 vs agent/user-memory 0.4.0)

#428 docs: update Elliot Chen's X handle

#423 [Feature]: Easier for a new user/developer to play.

#413 [Governance] Separate ecosystem integrations from EverOS core

#415 [Bug] flush crashes with TypeError: DetectionResult.__new__() missing 1 required positional argument on fresh pip 1.2.3 install — recall always empty

#414 Docs suggestion: add an AnyLLM provider quickstart (single OpenAI-compatible endpoint for 24+ models)

#406 [Proposal] Memory for EverOS agents — 97.5% fewer tokens (ViBo)

#404 issue test

#402 [Bug]: English timestamped messages produce Chinese/German profile output

#398 OME: SkillClusterUpdated persists a 1024-dim vector, inflating run_record ~18x

#397 Agent-pipeline e2e is the only coverage of the skill chain and CI never runs it

#396 OME holds `engine_sem` across the whole retry chain, now including backoff sleeps

#395 Mixed-version OME queue can feed an empty `approach` into skill extraction

#394 radius is documented and validated but has no effect on any search lane

#382 [Feature]: belief layer — probabilistic conflict resolution over atomic facts

#364 写入失败被上报为成功:cascade worker 不可恢复时 flush 仍返回 extracted;且失败无重试上限

#378 [Bug]: English search results when I use Chinese to create a memory

#367 perf(search): build a LanceDB vector index — dense recall is a full scan today (81ms → 2.2ms measured)

#315 [Bug]: LanceDB index grows unbounded and fills the disk when cascade compaction/prune silently fails

#337 cascade worker fails to index episodes: LanceDB `Spill has sent an error` (IO)

#338 [Cloud API] Queued agent-memory writes lack a usable task_id or exact visibility proof

#335 FTS optimize crashes with 'Max offset exceeds length of values' on lancedb >= 0.32

#334 [Bug]: Cascade rebuild-from-md livelocks after a full index wipe — last_processed frozen at 0, memcells never commit (1.1.2)