🛰️ Daily AI Frontier
‹ back to 2026-08-09

ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment

Research Medical/Healthcare AI

Ranking

Overall 65
Content 75
Popularity 42

Observed public metrics from 1 member.

Merged summary

TL;DR - ECHO is a locally-deployable agentic health assistant for chronic care that combines a LangGraph/ReAct chatbot with persistent temporal memory, a two-stage safety layer, and multimodal speech assessment. It matters because it shows a full privacy-preserving clinical agent stack running on consumer hardware without sending patient data off-device.

  • Core agent uses a ReAct loop over LangGraph with 17 clinical tools and a temporal knowledge graph for cross-session memory; 94.9% tool-execution pass rate on a 59-scenario benchmark with GPT-5 Mini.
  • Hybrid safety layer: sub-1ms rule-based filtering for explicit crisis/jailbreak signals, plus a signed GNN with APPNP-style propagation for boundary cases — 88.8% accuracy and 90.6% unsafe recall on 2,537 annotated Turkish health queries, beating zero-shot LLM baselines including Llama 3.3 70B.
  • Speech module fuses Whisper acoustic and BERT text encodings via cross-attention to estimate emotion, depression, and pain, at 0.652 mean macro F1.
  • Delivered as a web app running entirely on consumer hardware with no external data transmission, targeting GDPR and KVKK compliance.

Sources (1)

ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment

arXiv cs.AI Abdulkadir Külçe, Alihan Esen, Cağla Fikir, Berke Kurt, Kuzey Arar, Gökhan Ercan, Faik Boray Tek 2026-08-06 arXiv:2608.06110
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-03 14:29:19.938670 UTC

TL;DR - ECHO is a locally-deployable agentic health assistant for chronic care that combines a LangGraph/ReAct chatbot with persistent temporal memory, a two-stage safety layer, and multimodal speech assessment. It matters because it shows a full privacy-preserving clinical agent stack running on consumer hardware without sending patient data off-device.

  • Core agent uses a ReAct loop over LangGraph with 17 clinical tools and a temporal knowledge graph for cross-session memory; 94.9% tool-execution pass rate on a 59-scenario benchmark with GPT-5 Mini.
  • Hybrid safety layer: sub-1ms rule-based filtering for explicit crisis/jailbreak signals, plus a signed GNN with APPNP-style propagation for boundary cases — 88.8% accuracy and 90.6% unsafe recall on 2,537 annotated Turkish health queries, beating zero-shot LLM baselines including Llama 3.3 70B.
  • Speech module fuses Whisper acoustic and BERT text encodings via cross-attention to estimate emotion, depression, and pain, at 0.652 mean macro F1.
  • Delivered as a web app running entirely on consumer hardware with no external data transmission, targeting GDPR and KVKK compliance.
item →