I've built a locally running Perplexity clone
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. The video demo runs a 7b Model on a normal gaming GPU.
Open source
Reactions (1)
Similar products
by description similarity
CodeRLM
github.comTree-sitter-backed code indexing for LLM agents
I built a LLM-powered Ask HN
hackersearch.netlike Perplexity, but for HN comments
Open-source observability for LLM apps
github.comLLMonitor helps you record, trace & search your LLM queries and chatbot conversations.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Mutahunter
github.comLLMs to support mutating testing for all major languages