DakeraAI
/

modernbert-embed-base

Feature Extraction

ai-agent-memory

long-term-memory

Model card Files Files and versions

duckkkk commited on 7 days ago

Commit

ceda8df

·

verified ·

1 Parent(s): b2e872f

Model card

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -52,7 +52,7 @@ Apache-2.0, the same as the original model (see [`LICENSE`](https://huggingface.
 ## About Dakera
-**[Dakera](https://dakera.ai) is a self-hosted memory engine for AI agents.** It gives agents long-term memory that survives sessions: hybrid vector and full-text retrieval, reranking, entity extraction and importance decay, in a single Rust binary that runs on your own servers, with an MCP server for Claude, Cursor and other agents. 88.2% Recall@20 on the LoCoMo long-term memory benchmark.
 ```bash
 docker run -p 3000:3000 -e DAKERA_ROOT_API_KEY=dk-mykey ghcr.io/dakera-ai/dakera:latest

 ## About Dakera
+**[Dakera](https://dakera.ai) is a self-hosted memory engine for AI agents.** It gives agents long-term memory that survives sessions: hybrid vector and full-text retrieval, reranking, entity extraction and importance decay, in a single Rust binary that runs on your own servers, with an MCP server for Claude, Cursor and other agents.
 ```bash
 docker run -p 3000:3000 -e DAKERA_ROOT_API_KEY=dk-mykey ghcr.io/dakera-ai/dakera:latest