#vector-search

Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/

Semantic code search for coding agents — search by meaning like grep, trace call graphs, find tests & blast radius. 100% local embeddings (ONNX/MLX), MCP server, plugins for Claude Code, OpenCode, Codex & Droid.

Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).

The embedded graph database that builds itself. Declarative linking rules, explainable derived edges, microsecond traversal. Rust core, Cypher subset, Python bindings.

Persistent memory for Claude Code, Cursor, Copilot & Windsurf — your AI stops re-reading your codebase every morning. 120+ MCP tools, semantic search, shared Team Brain. Free tier, EU-hosted.

A fast, single-binary C database that gives AI agents durable, searchable long-term memory — with a Claude Code integration.

A fast embedded+server columnar database with SQL, vector search, full-text search, and AI-native retrieval. Dozens of languages supported. Written in Rust.

No repository description published.

Native Local AI & Vector RAG Engine for Laravel. Seamlessly integrate Ollama and LM Studio with zero infra and 100% data privacy.

😈 The zero-bs JavaScript-based search engine. Fulltext & vector search wherever JavaScript runs.

Identity-scoped schema selection for text-to-SQL: give the model only the tables this caller may read, and 75% fewer prompt tokens.

Mnemoteca — local memory for every agent

Object-store-native vector database — releases and product home. One static binary, durability from your own bucket.

Offline semantic search engine that runs anywhere.

File-first memory runtime for AI agents — versioned, portable, and always there when the next session starts.

The complete backend for AI agents in one SQLite file : Documents, vectors, cache, queue, and cron.

Hardware-accelerated whole-slice SIMD vector primitives for Go (AVX-512, AVX2, NEON, SVE2, RVV) — zero cgo, zero dependencies, 100% portable Go fallback.

Jurisdiction-aware judicial reasoning platform — a model-agnostic AI engine that produces citation-backed, adversarially-tested draft case analyses for human sign-off. Non-binding by design.

Auditable RAG from the command line: grounded, cited answers over your own documents, with faithfulness verification and retrieval eval you can gate CI on.

No repository description published.

Pinakes — a portable, agent-first knowledge base. One directory = one KB.

No repository description published.

Pure Go client for MongrelDB - embedded and server database with SQL, vector search, full-text search, and AI-native retrieval

Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping

Python SDK for Aetherfy Vectors — a drop-in replacement for qdrant-client with global sub-50ms latency, built-in analytics, workspace scoping, and client-side payload schema validation.

No repository description published.

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

Persistent graph memory MCP server for AI agents. LadybugDB-powered with semantic search, auto-dedup, and Cypher graph queries.

A fractal memory plugin and mcp server for opencode.

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search, sleep-time memory consolidation. One .meh file, zero infrastructure, pure Go.