Skip to content

Pull requests: vectorize-io/agent-memory-benchmark

New pull request New
11 Open 13 Closed
11 Open 13 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

beam: scale the async-operation timeout to the corpus instead of a fixed 300s
#38 opened Aug 25, 2026 by nicoloboschi Collaborator Loading…
1
external_results: ValorBrain BEAM-100K (80.8% / 70.9%)
#36 opened Aug 24, 2026 by agentxagi Loading…
2
Add MemoryHub memory provider
#34 opened Aug 22, 2026 by rdwj Loading…
1
1
feat: ValorBrain memory provider + BEAM-100K result (71.4% avg score)
#32 opened Aug 21, 2026 by agentxagi • Draft
4 tasks done
1
Add Letta memory provider
#29 opened Aug 17, 2026 by ThePlenkov • Draft
1
Add Tree Ring Memory provider
#25 opened Jul 8, 2026 by TerminallyLazy Loading…
Add AutoMem memory provider + neutral-run results
#24 opened Jul 4, 2026 by jack-arturo Loading…
1
Add coding-agent memory dataset seed
#22 opened Jun 24, 2026 by koriyoshi2041 Loading…
1
Fix agentic-rag retrieval limit wiring
#21 opened Jun 23, 2026 by koriyoshi2041 Loading…
1
fix: add user_ids kwarg to LoCoMo / MemBench / MemSim / PersonaMem load_documents
#14 opened May 12, 2026 by King-Brownie Loading…
1 of 2 tasks
1
feat: support Anthropic-compatible endpoints for benchmark LLMs
#12 opened May 8, 2026 by Sanderhoff-alt Loading…
5
ProTip! Exclude everything labeled bug with -label:bug.