Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 semantic-search Open-Source Projects
-
Generative AI for Beginners (Microsoft): 21 lessons on prompt engineering, calling LLMs from code, and building chat and search apps. https://github.com/microsoft/generative-ai-for-beginners
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
MeiliSearch
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
Karakeep (rebranded from Hoarder in early 2025) is the right pick if you want AI-assisted tagging and a more visual interface. It uses Meilisearch as a search engine, which adds memory overhead but delivers relevance ranking that SQLite FTS5 alone cannot match.
-
khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
Khoj is developed as a self-hostable personal AI and "second brain." It combines local or cloud language models with web retrieval, personal documents, semantic search, custom agents, automations, and an experimental /research mode.
-
WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Project mention: 15 Trending GitHub Repos I’d Use Before Building Another AI Project | dev.to | 2026-10-13Repository: Tencent/WeKnora
-
RAG_Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
-
Typesense
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
Project mention: Typesense for Ecommerce Search: Intent, Open Source, Guardrails | dev.to | 2026-10-10Typesense source code and feature list, GitHub (2026)
-
haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Project mention: haystack VS verified-memory-vault - a user suggested alternative | libhunt.com/r/haystack | 2026-08-25 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
DocsGPT
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
-
Weaviate
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Project mention: Financial Research Dashboard Retrieval: Privacy Controls and Freshness Explained | dev.to | 2026-10-14 -
memvid
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Project mention: memvid VS verified-memory-vault - a user suggested alternative | libhunt.com/r/memvid | 2026-08-26 -
Project mention: Dissecting Semantica’s Graph-Native Core: The Missing Layer Between Context and Accountability | dev.to | 2026-09-04
git clone https://github.com/semantica-agi/semantica.git cd semantica python3 -m venv .venv . .venv/bin/activate python -m pip install --upgrade pip python -m pip install -e .
-
Project mention: txtai VS verified-memory-vault - a user suggested alternative | libhunt.com/r/txtai | 2026-08-25
-
claude-context
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Claude Code doesn't do anything with semantic search or embeddings out of the box. They use a simple grep tool instead.
Neither does OpenAI's Codex CLI - you can confirm that by looking at the source code https://github.com/openai/codex
Cursor and Windsurf both use semantic search via embeddings.
You can get semantic search in Claude Code using this unofficial plugin: https://github.com/zilliztech/claude-context
-
-
lancedb
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Project mention: Building KiroGraph: a 100% local semantic code knowledge graph for Kiro | dev.to | 2026-04-08LanceDB stores embeddings in Apache Lance columnar format. Columnar storage is efficient for batch reads and writes, which matters a lot during indexing. Pure JS, no native deps, sub-linear ANN search.
-
paradedb
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
-
GPTCache — an open source library built specifically for caching LLM responses. Pretty flexible and worth looking at if you're rolling your own pipeline.
-
Project mention: First open-source knowledge enterprise world model | news.ycombinator.com | 2026-09-04
-
-
zotero-mcp
Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.
-
USearch
Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
Depending on how 'one-off' the query is, sequential read is the right answer. The alternative is indexing the data for ANN, which will generally require doing the equivalent of many queries across the dataset.
On the bright side, smart folks have already thought pretty hard about this. In my work, I ended up picking usearch for large-scale vector storage and ANN search. It's plenty fast and is happy working with vectors on disk - solutions which are /purely/ concerned with latency often don't include support for vectors on disk, which forces you into using a hell of a lot of RAM.
https://github.com/unum-cloud/USearch
-
Project mention: Z: Local-first search layer for humans and agents | news.ycombinator.com | 2026-09-02
-
GithubStarsManager
AI-powered GitHub stars manager with semantic search, auto-categorization, and release tracking
Project mention: I can't code. My 3,600-star open-source app is written entirely by AI agents — here are the quality gates that keep it honest | dev.to | 2026-10-14The app is GithubStarsManager (MIT, local-first, free): https://github.com/AmintaCCCP/GithubStarsManager — if you have a graveyard of starred repos, it might resurrect them. And if you're a developer reading this with (justified) skepticism about AI-written software: the repo is open. Go read the CI file. I did — well, an agent explained it to me. Then I checked its work, like always.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
semantic-search discussion
semantic-search related posts
-
Fintech News Service Retrieval: Auditable Evidence Without Unlimited Retention
-
Financial Research Dashboard Retrieval: Privacy Controls and Freshness Explained
-
Weaviate at 7,856 body matches: reading a vector store's public surface
-
Travel Itinerary Retrieval Architecture: Versioning for Grounded Citations
-
Retrieval Architecture for Legal Contract Review Workspace Freshness (Release Checklist)
-
Insurance Claims Retrieval Architecture with Node.js: Five Access-Rule Checks
-
How to Tune Retrieval Relevance for a Private Knowledge Manager: Source-Aware Staging
-
A note from our sponsor - AppSignal
www.appsignal.com | 15 Oct 2026
Index
What are some of the best open-source semantic-search projects? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | generative-ai-for-beginners | 121,057 |
| 2 | MeiliSearch | 59,523 |
| 3 | khoj | 37,627 |
| 4 | WeKnora | 32,559 |
| 5 | RAG_Techniques | 29,783 |
| 6 | Typesense | 26,724 |
| 7 | haystack | 26,716 |
| 8 | DocsGPT | 18,321 |
| 9 | Weaviate | 16,875 |
| 10 | memvid | 16,584 |
| 11 | Semantica | 13,893 |
| 12 | txtai | 12,996 |
| 13 | claude-context | 12,597 |
| 14 | cocoindex | 11,670 |
| 15 | lancedb | 11,617 |
| 16 | paradedb | 9,384 |
| 17 | GPTCache | 8,207 |
| 18 | utopia | 8,183 |
| 19 | superduper | 5,317 |
| 20 | zotero-mcp | 5,289 |
| 21 | USearch | 4,330 |
| 22 | zvec-grep | 4,091 |
| 23 | GithubStarsManager | 3,678 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com