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
View on GitHub →Most-wanted open issues
Ranked by 👍 reactions. 43 open issues total, checked 2026-07-17.
| Issue | 👍 | Comments | Opened |
|---|---|---|---|
fix: 记忆漂移 area:memory, status:needs-triage | 1 | 1 | 3 mo |
| 1 | 1 | 3 mo | |
fix: `SimpleTextSplitter` fallback 在文件解析链路中报错：缺少 `protect_urls` types:bug, area:core, ai:pr-ready, status:in-progress | 0 | 2 | 2 d |
feat: area:memory, status:needs-info | 0 | 4 | 3 mo |
feat: support OceanBase for relational, vector, and graph storage area:api, status:in-progress, area:database | 0 | 3 | 3 d |
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…
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory acros…
Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans…