# nilsherzig/LLocalSearch

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

Repository: https://github.com/nilsherzig/LLocalSearch
Canonical: https://ross.abutalabs.com/products/llocalsearch
Language: Go
License: Apache-2.0
License Family: permissive
Topics: llm, search-engine
Archived: true
Last push: 2026-03-24T09:58:01+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 73, release rhythm 8, longevity 63
- inputs: {"age_days": 893, "days_push": 162, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5947, forks 364 (observed 2026-08-28T04:09:32.684623+00:00)

## What it is
LLocalSearch is a self-hosted search aggregator that uses locally running LLM agents to answer questions with web-sourced information, showing live agent progress and cited links. It requires no OpenAI or Google API keys and runs on modest consumer hardware.

## Use cases
- search the web privately without sending queries to Google or OpenAI
- ask a question and get an LLM-synthesized answer with source links
- run a Perplexity-like AI search engine on my own hardware
- watch the agent's reasoning steps and tool calls live while it researches
- ask follow-up questions about a previous search result
- self-host an AI answer engine with no API keys

## When to choose
- you want private, local AI-powered web search without API keys
- you have a consumer GPU and want to run everything yourself
- you value transparent agent logs and cited sources over black-box answers
- you want a mobile-friendly, self-hosted search UI

## When to avoid
- you need a actively maintained project - the public version has not been developed for over a year
- you need production-grade reliability or chat history features
- you have no local GPU or hardware to run LLMs
- you want the best answer quality regardless of privacy, using frontier cloud models

## Facets
- artifact type: application
- maturity: maintenance
- function: search-engine, agent-framework, llm-inference, rag, web-scraping, chat-interface
- domain: artificial-intelligence, large-language-models, privacy, self-hosted, web-development
- platform: self-hosted, cross-platform, go
- tags: local-llm, search-aggregator, llm-agents, privacy-respecting, perplexity-alternative, langchaingo, ollama, search, ai-agents, docker, web-server

## Member repositories
- nilsherzig/LLocalSearch (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:32.684623+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:50:44.198282+00:00, confidence not recorded.
  - readme: https://github.com/nilsherzig/LLocalSearch (fetched 2026-08-28T04:09:32.684623+00:00, sha 2a48124dcc2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.