Skip to content

LuizEduPP/rememb

v0.4.0 Feature

This release adds 4 notable features for engineering teams evaluating rollout.

Published 1mo AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-memory ai-agents ai-memories ai-memory cherry-studio claude
+14 more
clawdbot context-persistence copilot cursor fastapi llm llm-memory mcp mcp-server memory model-context-protocol moltbot persistent-memory windsurf

Summary

AI summary

Semantic Bodyguard prevents redundant memory saves and fetch-model CLI command downloads the embedding model.

Full changelog

What's Changed

✨ New Features & Organic Memory

  • Semantic Bodyguard: MCP server now intercepts and prevents the AI from saving redundant memories (blocks saves with >88% semantic overlap).
  • Muscular Memory Boost: Frequently retrieved memories automatically gain access points and priority, shielding them from decay.
  • Hybrid Search: Added exact phrase matching (Lexical Boost) on top of the vector search.
  • Time Decay: Old, unused memories gradually lose relevance score (dropping to 70% after 90 days), pruning stale context organically.

🆕 New Commands
| CLI | Description |
|-----|-------------|
| rememb fetch-model | Downloads the embedding model (~80MB) with a progress bar for safe offline prep. |

🧹 Maintenance

  • Handled error responses in pure English.
  • Stripped inline comments to enforce self-documenting code.

🚀 Installation
pip install rememb==0.4.0

Full Changelog: https://github.com/LuizEduPP/rememb/compare/v0.3.9...v0.4.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track LuizEduPP/rememb

Get notified when new releases ship.

Sign up free

About LuizEduPP/rememb

Persistent memory for AI agents with sectioned entries (project/user/context/etc), semantic search, CLI, and per-project scope. Local JSON, zero config, no server required.

All releases →

Related context

Beta — feedback welcome: [email protected]