Havuz

Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents e

Preserve knowledge, sustain wisdom forever.

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

Evidence-grounded scientific agent system for research automation, citation verification and paper production.

Vectorless, Reasoning-Based Retrieval-Augmented Generation (RAG)

Open-source AI-era employment platform connecting skills, jobs, enterprises, governance, and AI agents.

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama

Open, structured corpus of US primary law: 2M+ sections of state statutory codes, the US Code, and state constitutions, plus the ingestion p

Chat with the videos you've saved: evidence-backed answers with timestamps that jump back to the source. Browser extension + MCP, self-hosta

All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully

终端优先的 Linux AI 运维工作台：SSH/SFTP、真实命令回显、分级审批与一步一卡教学。Windows 桌面预稳定版。A terminal-first AI workbench for Linux operations.

A framework for building intelligent agents

Self-hosted, traceable document-to-knowledge workspace with deterministic workflows, optional AI, search, RAG, and an editable knowledge gra

AI 驱动的电商全流程自动化系统。选品、上架、客服、运营分析、货源筛选，基于 DeepSeek V4 + Ollama 混合模型路由，自驱型 ReAct Agent 框架

MCP server for AI agent for cybersecurity: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge b

RepoMind is an AI-powered documentation generator for modern codebases that helps developers understand any GitHub repository faster. It ana

Countersign RFP/RFI/RFQ Studio for organizing documentation, hosting internally, including js + PHP proxy for hosting on panel.

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

EduAgent: Open-Source RAG AI Tutor for K-9 Education. 国内首个专为1-9年级量身定制的开源 RAG AI 教辅智能体

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

Sub-millisecond query routing & cost-aware execution for GraphRAG architectures. Adaptive-AtomRAG is a highly optimized conditional routing

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledg

MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than lettin

Fast-AtomRAG-Core

Shared memory + orchestration for your coding agents — one MCP server, persistent vector memory, agent registry

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB,

A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zero upkeep.

Open-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-

AI/ML Engineer in progress — LLM, RAG, Computer Vision. Open to full-time AI Engineer roles.

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

Mako — AI Career Intelligence System

a desktop application for real-time Bible verse detection during live sermons. 🙂

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario

Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable syst

Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n su

The memory and context-management layer for production AI agents. 95.6% on LongMemEval, 93.2% on LoCoMo, with an open harness. Python + JS S

Canonical, LLM-maintainable knowledge base of every Inner Circle Trader (ICT) concept 2016–2026. 226 concept files, machine-readable JSON bl

Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsM

Knowledge-enhanced multimodal Fire Safety Agent with two-hop reasoning, evidence-tree RAG, open-set guardrails, and four-layer memory.

Feature-rich all-in-one self-hosted server & server fleet management (Web UI): patching, monitoring (agent + agentless/SNMP), CVE scanning,

Get your documents ready for gen AI, in pure Go. A Go alternative to anydoc & Docling — 纯 Go 实现的文档解析库:PDF/Word/PPT/Excel/HTML/Markdown/EML/图

A modern Go framework for building multi-agent AI systems.

Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.

Agentic event-venue operator demo built on MongoDB Atlas. Showcases three-layer memory (long-term, short-term, shared), hybrid retrieval wit

开源 AI 运营工作台：将会议、文档与项目动态转化为知识、决策、任务、风险、自动化工作流和组织记忆。

Persistent, inspectable memory that grows and refines over time. Built on files. Owned by you.

Cognee Rust - fast and performant AI memory engine