Havuz

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and L

Repo Explainer — turn any GitHub repo into a visual explainer page. Pipeline + 5 live examples.

墨枢是一个面向中文长篇网文作者的 AI 小说写作工作台，支持作品大纲、章纲、人物与世界观设定库、时间线、RAG 检索、一致性守卫、自然化审查、AI 辅助续写、团队协作、用量计费，以及面向漫剧改编的静态分镜管理。前端采用 Vue 3，后端采用 FastAPI，支持 PostgreS

📚🔭 Your personal research radar — an LLM-powered tool that auto-aggregates the latest papers for your keywords across arXiv / Crossref / Sem

🔒 Your private AI assistant, 100% local on Windows: chat, vision, documents (RAG), web search, images, videos with sound, voice, code projec

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills co

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

Fully local AI for Polish legal case files - zero fabricated citations by construction. Free; please support a Wroclaw animal shelter instea

Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embe

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded ingestion, trace replay, HITL a

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

Zero downtime embedding upgrades

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

Official benchmark reproduction code for the SAG paper

The Ultimate AI Compute Gateway ( Router ) | A high-performance, stateless-to-stateful LLM compute gateway in Go. Features multi-model pooli

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harn

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one

Noosphere Desktop：Windows 优先的本地 AI 桌面工作台，集成多模型网关、项目代码检索、长期记忆、运维 Agent 与可审批操作。

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

Claude Code, natively inside Unity Editor. A dockable chat window with full project awareness, 60+ MCP tools, and zero alt-tabbing.

An open-source RAG platform to explore the unsealed Jeffrey Epstein court documents.

FlowState QMD — Anticipatory Memory for AI Agents. Hermes 2026 Hackathon Entry.

A mega collection of 2,070 AI agent data APIs: MCP servers, LLM tools, RAG pipelines, live web data, vision & voice. Give your AI agent live

PostgreSQL-compatible SQL, graph, and vector database built from scratch in Rust.

A self-hosted retrieval-augmented search API: web search, content extraction, embeddings, and answer generation.

Bilingual AI study coach that answers only from your own course material, with citations

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

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

Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON

Synthetic datasets, experiment protocols, and evaluation code for "Governed Memory: A Production Architecture for Multi-Agent Workflows"

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

Operational doctrine for practical AI systems design.

A design-of-experiments platform for evaluating compound AI systems - find which technique drives quality, by how much, and whether the di

Production-oriented multi-agent course advisor with deterministic action governance, offline regression evaluation, SSE contracts and observ

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection,

Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.

An AI native macOS reader. Built for professional reader.

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

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

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

源码级逆向工程（Hermes、OpenClaw、nanobot、NullClaw、OpenFang）记忆系统 —— 架构图、数据模型、检索管线、复刻指南。Source-Level Reverse Engineering of Memory Systems (OpenClaw, n

Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地

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)