abtonmoy commited on
Commit
397f8ef
verified
1 Parent(s): 304ae78

Org card: three-layer framing (embedding, perception, memory); add Engram + live site

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -9,11 +9,11 @@ pinned: false
9
 
10
  ![Eximius Labs](assets/banner.png)
11
 
12
- Eximius Labs builds open-weight multimodal models that run on your own hardware: the memory and perception layer for physical AI. The technical report is on arXiv: https://arxiv.org/abs/2607.18666.
13
 
14
  We freeze a strong base model and add new senses from the outside, so existing embeddings stay valid and gaining a modality never forces a re-index. One shared vector space spans text, image, video, audio, thermal, and motion (IMU).
15
 
16
- ## Fusion Embedding, the memory layer
17
 
18
  One vector space for cross-modal retrieval, RAG, clustering, and semantic search.
19
 
@@ -27,8 +27,19 @@ One vector space for cross-modal retrieval, RAG, clustering, and semantic search
27
 
28
  Dense scene understanding and geometric place recognition on a frozen vision backbone, projected into the Fusion Embedding space. Code: https://github.com/Eximius-Labs/fusion-perception.
29
 
 
 
 
 
 
 
 
 
 
 
30
  ## Build with it
31
 
 
32
  - Cookbook: https://github.com/Eximius-Labs/cookbook
33
  - Code: https://github.com/Eximius-Labs
34
  - Paper: https://arxiv.org/abs/2607.18666
 
9
 
10
  ![Eximius Labs](assets/banner.png)
11
 
12
+ Eximius Labs builds open-weight multimodal models that run on your own hardware: the embedding, perception, and memory layers for physical AI. The technical report is on arXiv: https://arxiv.org/abs/2607.18666. Try a real robot's memory in the live playground: https://www.eximiuslabs.com/playground.
13
 
14
  We freeze a strong base model and add new senses from the outside, so existing embeddings stay valid and gaining a modality never forces a re-index. One shared vector space spans text, image, video, audio, thermal, and motion (IMU).
15
 
16
+ ## Fusion Embedding, the embedding layer
17
 
18
  One vector space for cross-modal retrieval, RAG, clustering, and semantic search.
19
 
 
27
 
28
  Dense scene understanding and geometric place recognition on a frozen vision backbone, projected into the Fusion Embedding space. Code: https://github.com/Eximius-Labs/fusion-perception.
29
 
30
+ ## Engram, the memory layer
31
+
32
+ The open cross-modal memory layer for physical AI, built on Fusion Embedding. It indexes a robot's video, audio, and motion into one embedding space on a shared clock and answers questions about it in plain language, including temporal reasoning that retrieval alone cannot do.
33
+
34
+ ```
35
+ pip install engram-robomem
36
+ ```
37
+
38
+ Code: https://github.com/Eximius-Labs/engram 路 PyPI: https://pypi.org/project/engram-robomem 路 Playground: https://www.eximiuslabs.com/playground
39
+
40
  ## Build with it
41
 
42
+ - Site: https://www.eximiuslabs.com
43
  - Cookbook: https://github.com/Eximius-Labs/cookbook
44
  - Code: https://github.com/Eximius-Labs
45
  - Paper: https://arxiv.org/abs/2607.18666