SuperLocalMemory V3.6 Save up to 90% on every LLM API call. Cache. Compress. Remember.The only local-first memory system that SKIPS repeat calls (100% saved), SHRINKS prompts 60-95%, and REMEMBERS everything — locally, for free. For Claude Code, Cursor, Windsurf, and any AI client. v3.6.0 "Optimize" — Cache & Compress & Align. Save up to 90% on every LLM API call — locally. One command: slm wrap claudeAlso includes v3.5 Scale-Ready: 6-channel recall <1s, CozoDB + LanceDB, Core Memory Block. Your database auto-migrates.
| Stars | 183 |
| Forks | 24 |
| Language | Python |
| Category | MCP 服务器 |
| License | AGPL-3.0 |
| Quality Score | 53.366/100 |
| Open Issues | 3 |
| Last Updated | 2026-06-14 |
| Created | 2026-02-05 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~25k |
These tools work well together with superlocalmemory for enhanced workflows:
Explore other popular mcp 服务器 tools:
superlocalmemory is World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. . It is categorized as a MCP 服务器 with 183 GitHub stars.
superlocalmemory is primarily written in Python. It covers topics such as agent-memory, agent-reliability, ai-agents.
You can find installation instructions and usage details in the superlocalmemory GitHub repository at github.com/qualixar/superlocalmemory. The project has 183 stars and 24 forks, indicating an active community.
superlocalmemory is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.