mem0ai/mem0
Universal memory layer for AI Agents
View on GitHub →Most-wanted open issues
Ranked by 👍 reactions. 190 open issues total, checked 2026-07-17.
| Issue | 👍 | Comments | Opened |
|---|---|---|---|
Feature: Azure Cosmos DB NoSQL vector database enhancement, P2-medium, vector-store | 7 | 2 | 11 mo |
🚀 Feature Request: Include OpenAI Token Usage in All Relevant Method Responses enhancement, P2-medium, sdk-python | 7 | 8 | 1 yr |
BM25 keyword search and entity extraction are hardcoded to English Core / Python SDK | 5 | 9 | 3 mo |
Support for LanceDB enhancement, P2-medium, vector-store | 3 | 4 | 1 yr |
Missing Native Batch Operations in Memory and AsyncMemory Classes enhancement, sdk-python, P1-high | 2 | 4 | 8 mo |
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…
#1 Persistent memory for AI coding agents based on real-world benchmarks