Your Robot Forgets Everything. Until Now.
The memory system that robots have been missing. Remember skills, learn from failures, build on experience —
Every Modality, One Memory
Robots perceive the world through multiple senses. RobotMem stores them all in a unified, searchable memory.
Memory
Built for Real Robots
Not another chatbot memory. RobotMem is designed for physical agents that interact with the real world.
Multi-Modal Storage
Store visual, tactile, auditory, proprioceptive, and procedural experiences with numeric parameters and trajectories.
Cross-Session Learning
Robot remembers across reboots. Skills learned today are available tomorrow. No retraining needed.
Model Agnostic
Works with any framework — ROS, Isaac Gym, MuJoCo, dm_control. Not locked to any specific model or vendor.
Semantic Search
Find relevant experiences by meaning, not keywords. "How did I grasp the red cup?" returns the right memory.
Auto Deduplication
dHash for visual similarity, Jaccard for text overlap. Keeps memory clean without manual curation.
Trajectory & Parameters
Store force profiles, joint trajectories, and numeric parameters as structured data alongside natural language.
Three Steps to Robot Memory
Simple API. No infrastructure. Just save experiences and recall them when needed.
Experience
Robot performs an action. RobotMem captures the perception — what it saw, felt, and did — with full context.
Remember
Next session starts. RobotMem retrieves relevant past experiences via semantic search. Robot picks up where it left off.
Evolve
Over time, patterns emerge. Skills crystallize. The robot builds genuine expertise from accumulated experience.
Robot Memory in 13 Lines
Python API & MCP Server. Your robot remembers in minutes.
from robotmem import save_perception, recall
# Save a grasping experience
save_perception(
description="Grasped red cup: force=12.5N, 30 steps",
perception_type="procedural",
data='{"actions": [[0.1, -0.3, 0.05]], "force_peak": 12.5}',
)
# Next session: recall similar experiences
memories = recall("how to grasp a cup")
for m in memories["memories"]:
print(m["content"], m["_rrf_score"])
$ python robot_controller.py
[recall] hybrid mode | 3 results | top score: 0.847
Grasped red cup: force=12.5N, 30 steps score=0.847
FetchPush: success, dist 0.012m, 28 steps score=0.723
Push cube: force=11.8N, overshoot 0.03m score=0.651
Built Different
Existing AI memory systems are designed for chatbots. RobotMem is designed for robots.
| Capability | RobotMem | Mem0 | Zep | Letta |
|---|---|---|---|---|
| Target Use Case | Robots | Chatbots | Chatbots | Chatbots |
| Multi-modal perception | ✓ 5 types | ✕ | ✕ | ✕ |
| Trajectory storage | ✓ | ✕ | ✕ | ✕ |
| Numeric parameters | ✓ | ✕ | ✕ | ✕ |
| Model agnostic | ✓ | ✓ | ✕ | ✕ |
| Offline capable | ✓ Local ONNX | ✕ Cloud | ✕ Cloud | ✓ |
| Visual dedup (dHash) | ✓ | ✕ | ✕ | ✕ |
| MCP protocol | ✓ | ✕ | ✕ | ✕ |
| Natural language storage | ✓ | ✓ | ✓ | ✓ |
| Score | 8 / 8 | 2 / 8 | 1 / 8 | 2 / 8 |
Start Building Robots That Remember
Open source. Free forever. One pip install away.