AI agent tools for hybrid search
Short answer: Our top pick for hybrid search: pipeshub-ai, with the highest AgentPick Score (77/100) among tools tagged "hybrid-search". Runners-up: memsearch (74) and seekdb (71). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | pipeshub-ai | The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) in… | 77/100 | ★ 3.8k | Apache-2.0 | 14 Oct 2026 |
| #2 | memsearch | A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus. | 74/100 | ★ 2.7k | MIT | 9 Oct 2026 |
| #3 | seekdb | The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in… | 71/100 | ★ 3.2k | Apache-2.0 | 14 Oct 2026 |
| #4 | moss | The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud. | 69/100 | ★ 798 | BSD-2-Clause | 14 Oct 2026 |
| #5 | mcp-local-rag | Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup. | 62/100 | ★ 415 | MIT | 14 Oct 2026 |
| #6 | knowledge-rag | Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external server… | 61/100 | ★ 296 | MIT | 14 Oct 2026 |
| #7 | ClawMem | On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search. | 58/100 | ★ 210 | MIT | 11 Oct 2026 |
| #8 | codeseek | Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) acros… | 49/100 | ★ 768 | MIT | 2 Aug 2026 |
| #9 | PharosRAG | Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits. | 24/100 | ★ 243 | MIT | 19 Aug 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.