RobotMem

18

Persistent memory system for robotic agents with hybrid BM25 and vector search, spatial retrieval, and session-based memory consolidation.

Visit Site GitHub
Category Agents
Added Mar 28, 2026
Views 56

About

Model-agnostic persistent memory system designed for physical robots and AI agents. Provides seven core tools (learn, recall, save_perception, forget, update, start_session, end_session) combining BM25 full-text search with vector embeddings using reciprocal rank fusion. Supports spatial nearest-neighbor sorting for robotics applications, CJK language tokenization, structured JSON filtering, and local SQLite storage with optional ONNX models for offline operation.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/robotmem.svg)](https://hifriendbot.com/ai-list/robotmem/)
Listed on AiList

Compare

RobotMem vs claude-persistent-memory RobotMem vs Clude Bot Memory RobotMem vs Memory3

Similar Projects

claude-persistent-memory

5

Give Claude Code persistent memory across sessions. Hybrid BM25 + vector semantic search, auto-structuring via LLM, and 4-channel retrieval (MCP + hooks). Your AI assistant finally remembers.

MCP Servers

Clude Bot Memory

1

Self-hosted persistent memory server backed by Supabase with hybrid vector-keyword-graph retrieval, importance scoring, memory decay, and dream consolidation cycles.

MCP Servers

Memory3

13

Ultra-light memory system with hybrid BM25 and vector search, HNSW indexing, Late Chunking, and TTL support using SQLite with no external dependencies.

MCP Servers Python

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project