Havuz

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-

Self-hosted, distributed, multi-model LLM inference

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

Self-hosted intent radar — Reverse RAG for any input stream.

Generic markdown vault MCP with hybrid search

Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Clau

Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.

Vault health, connection review and Recall for Obsidian. Studio recipes and editable diagrams in the 2.3.0 release candidate.

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic place

Advanced Memory for LLM characters

Agent-native screenshot gallery CLI: index, caption, search & safely rename local photos.

MCP-first AI foundation for TYPO3. Bring AI agents into TYPO3, on your terms.

Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

Open-source, Python-first RAG platform with FastAPI APIs, LangGraph-native agents, pluggable vector stores (Qdrant/Weaviate/Milvus/pgvector/

A 100% local, privacy-first alternative to Windows Recall — captures your screen, OCRs it, and lets you semantically search and chat with yo

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcr

TiyGate is a lightweight gateway for highly available LLM services. 一款致力于提供高可用 LLM 服务的轻量级网关。

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki wit

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically que

Terminal UI and local CLI for crawling GitHub issues and pull requests, generating embeddings, and clustering related work.

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activa

Local document Q&A in your terminal — powered by on-device LLMs.

FischROBLOX Pro Roblox Testing Automation Tools 2026

Client-side vector search powered by HNSW. 54KB gzipped WASM. Sub-millisecond latency.

Context retrieval engine for AI agents — semantic + lexical search over codebases

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Im

TurboQuant-compatible vector search plus graph memory for constrained RAG.

SQL-like query language and CLI for Qdrant vector search engine

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible fi

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hoste

书内 BOOKNOTE · 多账户教材 RAG 学习助手 —— 回答必引原文:C/W 双引用校验、批注阅读器、长对话自动压缩、可选联网补充(MCP)

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Persistent memory for Claude Code. Your AI never starts from scratch again.

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve

Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

Open-source vector database and sub-microsecond key-value store in one Go engine — embed it as a library, run it standalone, or replicate it

Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. Autovisor, an autonomous Supe

Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.

khive is a system of records and operations for agent-native organizations

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin

Unified multi-layer caching library for AI/agent pipelines — LangChain, LangGraph, AutoGen, CrewAI, Agno, A2A