vector-search — independent software & tools

15 independent vector-search listings the big search engines bury.

• LexonGraph

  github · Free · by Alan-Jowett

  LexonGraph is a log-structured semantic index that stores embeddings as immutable blocks in navigable vector graph. It supports local and cloud backends, fast centroid-guided search, and efficient period rebuilds, enabling LLMs to retrieve precise context from large archival corpora.

• trusty-tools

  github · Free · by bobmatnyc

  Unified Rust workspace for the trusty-* AI developer-tooling ecosystem: hybrid code search, memory palace, code analysis, PR review, and the MPM multi-agent platform — MCP servers, daemons & CLIs.

• trusty-tools

  github · Free · by bobmatnyc

  Unified Rust workspace for the trusty-* AI developer-tooling ecosystem: hybrid code search, memory palace, code analysis, PR review, and the MPM multi-agent platform — MCP servers, daemons & CLIs.

• wavemind

  github · Free · by CaspianG

  Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.

• mootx01-ce

  github · Free · by codedaptive

  MOOTx01 Community Edition

• agent-history

  github · Free · by d3layd

  Local semantic search over your AI coding agent session transcripts, using Ollama embeddings and sqlite-vec

• justsearch

  github · Free · by eliasjustus

  Private hybrid search over your files, fully offline, 70+ languages. An MCP retrieval backend for AI agents.

• Neuron

  github · Free · by recla93

  MCP server giving LLMs long-term associative memory: per-context concept graph with 384-dim vector search, Hebbian link reinforcement and spreading activation. Local-first (embedded libSQL) or shared on Turso Cloud with concurrency-safe writes.

• archon-cockroach-memory

  github · Free · by upgradedev

  Archon Memory — an agentic financial-intelligence app using CockroachDB (distributed vector indexing) as the agents' persistent memory layer, on AWS Bedrock. CockroachDB × AWS AI Hackathon.

• agentdb

  npm · Free · by ruvnet

  Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

• mcp-memory-graph

  npm · Free · by GitHub Actions

  Local-first memory MCP server for Claude Code and any MCP client: hybrid vector + knowledge-graph search, bi-temporal recall, Obsidian sync. Runs 100% on your machine, $0/token.

• ruvector

  npm · Free · by ruvnet

  Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms

• @vpxa/aikit

  npm · Free · by anvpx

  Local-first AI developer toolkit — knowledge base, code analysis, context management, and developer tools for LLM agents

• Grimore-MD

  github · Free · by kahz12

  Local-first cognitive daemon for automated vault management Markdown. Semantic indexing, auto-tagging, and connection discovery using LLMs and vector search.

• open-brain

  github · Free · by rodaddy

  Local-first search engine for your docs, knowledge bases, and notes. BM25 + vector + HyDE search over 30K+ markdown documents