MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
View on GitHub →Where this sits in the catalog
Most-wanted open issues
Ranked by 👍 reactions. 30 open issues total, checked 2026-08-29.
| Issue | 👍 | Comments | Opened |
|---|---|---|---|
[Bug] Multi-Agent mode: cross-agent memory injection + recursive chunk duplication (65908 records in 1 week) status:stale, area:plugin, status:ready | 1 | 2 | 5 mo |
Bug: Search returns 0 results for cubes with fewer memories despite valid Qdrant data area:core, status:needs-triage | 0 | 1 | 4 wk |
fix: Tier-2 vector recall applies unordered LIMIT before cosine ranking, causing false negatives area:plugin, status:needs-triage | 0 | 0 | 3 wk |
Bug: PostgresGraphDB returns empty search results (pgvector embedding string breaks TextualMemoryItem) area:core, status:needs-triage | 0 | 0 | 1 mo |
/product REST surface is unauthenticated by default; user_id is client-supplied (cross-user IDOR) and doc_path reads arbitrary server files types:bug, area:core, status:needs-product-review | 0 | 2 | 1 mo |
What Hacker News made of it
Threads that link to or name this project, ranked by points. The comments are where the objections live — the README never argues back.
- MemOS: Treating "memory" as a first-class resource for LLMs
2 points · 0 comments · 1 yr
Alternatives in Memory & context
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, com…
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agen…
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists.…
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory acros…
#1 Persistent memory for AI coding agents based on real-world benchmarks