AI codebase search

Editorial picks for "semantic code search".

18 tools

All Coding →

Cursor

Featured

Coding · Claude / GPT (configurable)

9.5

AI-first VS Code fork — chat, edit, and agentic coding in one IDE.

Freemium· Hobby: Free · Individual: $20 / mo. · Teams: $40 / user / mo. · Enterprise: Customcodingrefactors

Elasticsearch Vector Search

RAG · BYO embeddings (OpenAI, Cohere, Hugging Face, Mistral, Bedrock, Vertex, Azure) plus Elastic's built-in ELSER sparse model and E5 dense model

8.7

Hybrid vector + keyword search in the enterprise-grade Elasticsearch engine

Freemium· Resource based pricing: Pay as you go (monthly) or prepaid · Usage based pricing: Pay as you go (monthly) or prepaid · License based pricing: ?RAG chatbot over enterprise docsHybrid semantic + keyword product search

Vespa

RAG · Hosted search engine (not an LLM)

8.2

Yahoo's open-source search engine with vector + sparse retrieval.

Freemium· Free open-source; Vespa Cloud paidlarge-scale searchranking

Repomix

Coding · ChatGPT, Claude, Gemini, Grok

8.1

Packs an entire codebase into a single AI-friendly file so LLMs can actually read your repo.

Free· Free and open source (MIT)codebase-to-llmcode-review

Windsurf

Coding · SWE-1.6 Fast (plus Claude Agent, OpenCode via ACP)

8.1

AI-native IDE turned agent command center, now folded into Cognition's Devin lineup.

Freemium· Free; Pro $20/mo; Max $200/mo; Teams $80/mo + $40/seat; Enterprise customai-idecoding-agents

Cody

Coding · Claude / GPT / Mixtral (configurable)

8.0

Sourcegraph's AI coding assistant — codebase-aware via their search index.

Freemium· Free; Pro $9/mo; Enterprise customenterprisemonorepos

Pieces

Coding · Multi-model (BYO OpenAI, Anthropic, Gemini, Ollama)

7.2

On-device long-term memory layer that feeds your last nine months of work context into any LLM or IDE assistant.

Freemium· Pro: $18.99 · Enterprise: $22.99developer-memorycode-snippets

Serena

Agents · Bring your own (Claude, GPT, etc.)

7.1

Open-source MCP toolkit that gives coding agents IDE-grade symbol search, refactoring, and editing across 40+ languages.

Freemium· Core server free (MIT); optional JetBrains plugin is paid with free trialagent-codingrefactoring

Graphify

RAG · Multi-model

7.0

Open-source on-device knowledge graph engine that turns code, docs, papers, meetings and images into a queryable graph.

Free· MIT-licensed, free forever; cloud tier hinted but unpriced (waitlist)knowledge-graphcode-search

Phind

Coding · Phind-70B / Phind-405B plus GPT and Claude models on Pro

7.0

AI answer engine for developers that cites sources and writes working code.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salescode-searchdebugging-help

Gitingest

Coding

6.9

Turns any Git repo into a single LLM-ready text digest by swapping 'hub' for 'ingest' in the URL.

Free· Free hosted service; open-source self-hostcodebase-to-promptcode-review

Augment Code

Agents · Claude Opus, Claude Sonnet, Gemini, and open-source models via BYOK; routed by proprietary Prism model router

Enterprise agent-orchestration platform for the software development lifecycle.

Paid· Business: $100/month · Enterprise: CustomAutomated pull-request reviewTest-coverage expansion on legacy code

Chroma MCP

MCP Servers

Official MCP server that gives LLM clients direct access to the Chroma vector database.

Free· Open source (Apache 2.0). Free to run locally or self-hosted; embedding-function API keys (OpenAI, Cohere, Jina, VoyageAI, Roboflow) billed by those providers. Chroma Cloud pricing set separately by Chroma.Long-term memory for Claude DesktopTeam knowledge base shared across agents

Exa MCP Server

MCP Servers · Exa neural search index (in-house)

Web search, code search, and company research for AI assistants over MCP

Freemium· Free: $0 USD · Team: $4 USD per user/month · Enterprise: $21 USD per user/monthLive web search inside Claude DesktopRAG grounding for research agents

Magic.dev

Coding · In-house frontier code models (including a long-term-memory 'LTM' model family with reported 100M-token context)

Frontier code models with ultra-long context aimed at automating software engineering

Enterprise· No public pricing. Access is via research partnerships and enterprise engagements; no self-serve tier or public API published as of writing.Whole-repo refactorsLong-horizon feature implementation

Meilisearch

RAG · Retrieval engine (Rust); pluggable embedders including OpenAI, Cohere, Hugging Face, Ollama and custom REST models

Open-source, lightning-fast search engine with built-in hybrid and vector search for RAG

Freemium· Cloud: $20/month · Usage-based: $30/month · Resource-based: $23/month · Instance: $18/monthE-commerce product searchDocumentation and knowledge base search

Qdrant MCP Server

MCP Servers · FastEmbed (default: sentence-transformers/all-MiniLM-L6-v2); pairs with any MCP-capable LLM such as Claude 3.5/4, GPT-4o, or local models

Official Qdrant MCP server that turns a vector database into a semantic memory layer for Claude, Cursor, Windsurf, and any MCP client.

Free· Free and open source (Apache-2.0). Qdrant itself can be self-hosted for free or used via Qdrant Cloud (free tier available, paid plans from ~$25/mo for managed clusters).Persistent memory for Claude Desktop agentsSemantic code snippet search in Cursor and Windsurf

Turbopuffer

RAG · bring-your-own embeddings (any provider)

Fast search on object storage

Paid· launch: $16/month · scale: $256/month · enterprise: >=$4,096/monthProduction RAG chatbotsMulti-tenant semantic search