Geograms releases offline Android AI assistant Eva

// 1h agoOPENSOURCE RELEASE

Geograms releases offline Android AI assistant Eva

Geograms has announced the open-source release of Eva, an AI assistant for Android designed to operate entirely offline without cloud dependencies. Eva leverages on-device Large Language Models to index and retrieve information from local PDFs and Wikipedia databases.

// ANALYSIS

On-device mobile AI execution is maturing rapidly, making privacy-first, zero-cost offline intelligence practical for everyday smartphone users.

–Eliminates cloud API dependencies and privacy risks by processing document indexing and query synthesis entirely on-device.
–Offline support for PDFs and Wikipedia provides continuous utility in air-gapped or low-connectivity environments.
–Releasing as open source under Geograms allows developers to adapt and optimize local inference pipelines across various Android chipsets.

// TAGS

evaandroidoffline-ailocal-firstopen-sourcepdf-indexinggeograms

DISCOVERED

1h ago

2026-07-29

PUBLISHED

2h ago

2026-07-29

RELEVANCE

7/ 10

AUTHOR

so_sthbryan

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS20m ago

Developer tests Claude Code overnight /goal mode

Software developer Dani Ávila shared on X that he is leaving Anthropic's Claude Code CLI running overnight for the first time using the `/goal` command paired with a comprehensive prompt. The post captures both anticipation and concern as developers increasingly rely on long-horizon, autonomous AI agent execution to tackle complex coding tasks asynchronously while they sleep.

NEWS24m ago

GenLayer hosts AMA on AI consensus infrastructure

GenLayer held a community AMA session featuring co-founder @kstellana and @stargirl_hills to share insights on the project's trajectory. Over the past two years, GenLayer has focused on developing blockchain infrastructure designed to allow AI models to perform consensus-driven reasoning and execute intelligent smart contracts rather than simple content generation.

MODEL59m ago

SK Telecom releases 688B MoE model A.X K2

SK Telecom released A.X K2, a 688B parameter sparse Mixture-of-Experts (MoE) language model with 33B active parameters on Hugging Face. By routing compute through specialized expert pathways, A.X K2 delivers high model capacity while keeping active compute overhead manageable during inference.