Alternatives

Products that do what Local Search Agent – RAG replacement, no embeddings, free tier does

1AE
An experimental, people-powered search engine▲215
2021 · ninfex.com
2PA
Peekier – A new way to search the web▲120
2016 · peekier.com
3HC
Highly cost-efficient search engine in Rust▲61
2021 · github.com
4WA
Wiby – A Minimalist’s Search Engine▲59
2020 · wiby.org
5AS
A search widget for static web sites▲88
2017 · webtigerteam.com
6IM
I'm building an API that allows you to train semantic search for RAGs▲6
When your embedding provider is good, but could be better for your use-case.
2024 · zoplabs.com
7AS
A Simple Search Engine▲30
2020 · kuurio.com
8IW
Improve web search with custom search engines▲23
2020 · searchcommons.org
9TA
Towards agentic Graph RAG: Enhancing graph retrieval with vector search▲6
In this post, we document the results of some experiments comparing vanilla Graph RAG (just a single pass of text2cypher) vs. a router agent Graph RAG approach that can call vector search tools alongside text2cypher. The routing agent uses an LLM to decide which vector search tool to call, depending on the terms identified in the question, and it works quite well. The results show that recent frontier LLMs like `gpt-4.1` and the trusty workhorse `gemini-2.0-flash` produce great quality Cypher reliably and reproducibly, with some prompt engineering to ensure that the graph schema is formatted…
2025 · blog.kuzudb.com
10AS
AgentSearch – Self-hosted search and MCP for AI agents, no API keys▲5
Apr 2026 · github.com
11LA
LLM agents to extract web data▲8
2024 · twitter.com
12AO
An open source web crawler for the Mwmbl non-profit search engine▲6
2022 · github.com
13LP
Linkwok – Picking up where search engines left off▲22
2014 · linkwok.com
14MA
MiniSearch, a client-side full-text search engine▲10
2019 · github.com
15SF
Solve for All – customizable, private, hackable search engine▲7
2016 · solveforall.com
16RF
Rag Framework▲5
A scalable centralized embeddings platform for efficient embedding and retrieval to build RAG applications faster
2024 · github.com
17PD
Presearch: Decentralized Search Engine▲10
2021 · presearch.org
18PR
Prompt-refiner – Lightweight optimization for LLM inputs and RAG▲7
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
Dec 2025 · github.com
19DS
Duo Search – an OpenBazaar search engine▲12
2016 · duosear.ch
20MO
Metarank – open-source hybrid search with LLMs▲7
A small demo for a Metarank open-source project I'm maintaining.
2023 · demo.metarank.ai
21MM
Mu – Minimal HTML5 Song Search▲11
2015 · louisdickinson.com
22WB
We built a better reranker and open sourced it▲6
Hi HN, Our research team just released the best performing and most efficient reranker out there, and it's available now as an open weight model on HuggingFace. Reranker v2 was designed specifically for agentic RAG, supports instruction following (our v1 was the first to introduce this), and is multilingual. Along with this, we're also open source our eval set, which allows you to reproduce our benchmark results. By releasing these datasets, we are also advancing instruction-following reranking evaluation, where high-quality benchmarks are currently limited. Please give it a try and let us…
2025 · huggingface.co
23CA
Coding agent with algebraic memory (VSA) instead of RAG▲5
Jun 2026 · github.com
24PS
Private Search – Decoupled identity and search, no Google/Bing▲5
2020 · private.sh

Ranked by how close each launch is in meaning, then by votes. Refine with a description →