Eclipse ships open-source AI search

// 63d agoOPENSOURCE RELEASE

Eclipse ships open-source AI search

Eclipse is a self-hostable AI search app that combines SearXNG with Ollama to produce multilingual, citation-backed results in a modern Next.js interface. It is fully open source under AGPL and includes voice search, history, maps, calculator, and stock widgets.

// ANALYSIS

This looks less like a Perplexity clone and more like a practical reference architecture for local-first AI search.

–SearXNG gives it a real search backend, while Ollama keeps the LLM layer local and swappable.
–The 12-language UI and citation tracking make it feel productized rather than like a weekend demo.
–Voice search, maps, calculator, and stock widgets suggest it wants to own the whole search session, not just answer one query.
–The Eclipse name collision will likely create SEO and discovery headaches, and AGPL may slow some commercial adoption while encouraging forks.

// TAGS

eclipsesearchllmopen-sourceself-hosted

DISCOVERED

63d ago

2026-03-25

PUBLISHED

63d ago

2026-03-25

RELEVANCE

7/ 10

AUTHOR

immortaledge138

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE4h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE4h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE8h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.