Havuz

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

Dissenyador visual de workflows i graphs d’IA agentiva · Diseñador visual de workflows y graphs de IA agéntica · Visual designer for agentic

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

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out

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

Machining process planning for motor shafts - input shaft geometry, RAG-grounded operations, machine tools, cutting tools, heat treatment, e

Agentic memory built on Postgres

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

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

景区导览服务 AI 数字人：基于 Spring Boot、Vue 3、UniApp 与本地 RAG 的智能导览系统。

开源紫微斗数 AI Agent：基于确定性命盘事实进行可追溯对话。 Evidence-backed chart conversations.

AI求职操作系统 — 岗位采集→10维评分→定制简历(LaTeX PDF)→面试资料生成→投递指南，一条龙服务

Open-source customer support platform: ticketing, help center, live chat widget and grounded AI — one deploy, many brands. Self-hosted alter

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex

这个项目为两件事而生，重心是学AI代理：把RAG、引用校验、最大工具循环这些机制零框架亲手写一遍，再配一个「学习中心」把每个机制讲成课；其次是学命理——把八字排盘室外可的点击活教材，每个干支、十神问、大运追到底。就算不接api key，也可以体验到大部分。

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

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

privacy-first context graph engine for AI agents and human teams.

A 21-day hands-on journey to mastering AI for DevOps — covering LLMs, GenAI, CI/CD, Kubernetes, cloud, automation, and AI-powered DevOps pro

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

Mental health support companion

Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with p

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

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

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

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

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

BGNexa AI — Evidence intelligence for cybersecurity, privacy and regulatory readiness.

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

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

🚀 多Agent协作智能知识库系统 — 五层可编排Agent架构 + RAG全链路 + 统一ToolRegistry，Spring Boot + FastAPI + React，核心亮点是 五层可编排 Agent 架构——Interface、Orchestrator、Tool、M

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservic

DeepSeek Harness (dsh) 插件:论文伴读工作台 —— PDF 转录 / 检索 / 流式问答 + 内置阅读器页面。

A multimodal RAG dashboard and interactive 3D Knowledge Graph. Process documents locally with Ollama or via Cloud APIs, powered by LightRAG,

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

A local-first studio for roleplay and long-form writing: a roleplay chat with a living Narrative State, a Worldbuild that keeps your canon,

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

Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have

Open-source, AI-native social media management, design & scheduling platform for 45+ channels. BYOK AI across 30+ providers with governance

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

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

A high-accuracy, multilingual rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accur

local RAG extension for pi coding agent

AI-powered incident response platform with intelligent root cause analysis and automated recommendations. An AI-powered Site Reliability Eng

Namaste AI — Free handwritten notes and study material covering AI concepts from the Namaste AI course. Explore the history of AI, neural ne

ONGRID — Ontology-Native Graph · Retrieval · Inference · Decision. 3D knowledge graph + zero-token ZTC answer verification. by VIDRAFT.

AI Business OS: multi-agent platform with RAG, OCR, speech & workflow automation. FastAPI + LangGraph + Celery + Flutter. Production-grade,

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

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