Havuz

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

Concurrent Go CLI that detects hidden prompt-injection content in documents — invisible Unicode, homoglyphs, hidden HTML, and known trigger

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

Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge gra

Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase

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

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

Install once, talk to your agent. ThinkWiki turns documents and notes into a local Markdown wiki with inbox review, content knowledge graph,

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

Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page cit

Evano Studio is an open-source local AI desktop app for agents, automation, knowledge, and productivity.

Enter a US stock ticker, get an analyst grade memo with DCF valuation, peer comparables, news sentiment, and earnings call tone analysis. Mu

Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.

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

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

根据 Crash/ANR/OOM 等日志构建证据链，实现自动修复代码的Agent框架，并支持衔接自动测试验证、Bug管理平台 Agent framework that builds evidence chains from Crash/ANR/OOM logs, auto-fix

Deterministic agentic-style multi-hop RAG at research-SOTA parity on commodity LLM APIs — no GPU, proof tree per answer.

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

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions i

面向中文食谱问答的端到端 RAG 工程实践，覆盖数据清洗与索引构建、混合检索、多轮状态管理、结构化生成，以及基于真实大模型服务的 Live E2E 测评闭环。

End-to-end educational RAG system: dual-engine retrieval (BM25 + BGE-M3 hybrid vector search), adaptive query strategies (HyDE/sub-query/bac

An AI native macOS reader. Built for professional reader.

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native

RAG-powered document intelligence assistant built for the Midnight Hackathon AI Track. Users upload confidential documents (medical records,

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

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

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

Bring Galileo powered eval workflows into Claude Code and Codex.

基于多模态 Embedding + Zilliz + Qwen 视觉理解的多模态 RAG 系统。支持 **Cohere / DashScope Embedding** 和 **DashScope / OpenRouter LLM** 双引擎切换。上传 PDF，用自然语言提问，系统

Local-first markdown notes with a first-class MCP server. 16 tools + 2 resources for Claude Code, Claude Desktop, Cursor and any MCP agent.

A multi-tenant vector database focused on extreme RAM efficiency. Lightweight, scalable, and optimized for high-density deployments.

Transforme Claude Code en générateur autonome de knowledge vault Obsidian. Pattern Karpathy. Par LE LABO IA.

LingXi: multi-agent CTF and pentest framework originated from Tencent Security Hackathon

A very fast, feature-packed, AI-first Markdown (CommonMark/GFM) gem for Ruby, based on pulldown-cmark (Rust).

RoR engine that enables natural language queries over your database using RAG and LLMs.

Markdown-first work-memory protocol for existing agents, with maintained knowledge, candidate notes, evals, and an example KB.

A terminal-based, multi-domain support-ticket triage agent grounded in a local support corpus.

A schema standard for LLM-compiled personal knowledge bases. AGENTS.md spec, templates, worked example, spaced repetition learning layer.

Framework for building continuous-loop autonomous AI agents.

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

Smart India Hackathon 2025 repository featuring AI-based solutions including a multimodal offline RAG system and a blockchain-enabled touris

A high-performance, local, offline-first AI memory system built in Rust

[ACL'26 Main Conference] Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pi

WikiMind is a personal LLM-powered knowledge OS. Feed it articles, PDFs, YouTube videos, podcasts, or papers — it compiles them into a struc

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

简悦 Andrej Karpathy LLM Wiki 方案

AI-powered SaaS translation platform for web novels — batch translate with RAG memory, multi-agent collaboration, Stripe billing, Chrome ext

Turn your Bilibili favorites and cloud documents into a chat-ready personal knowledge base. Agentic RAG with ASR transcription, Milvus vec