Havuz

A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.

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

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG

Privacy and security guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and tool authorization

A free, privacy-first tool that flags the tells of AI-generated writing, overused vocabulary, rhetorical crutches, robotic sentence rhythm a

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

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

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

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

a LLM inference engine to run on consumer hardware

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without ca

LLM-powered conversation summarisation service for OCTO — turns group chats and threads into structured briefs with key decisions, open ques

工厂本体驱动的数据问答框架（开源，Apache-2.0）：把中小企业台账/MES/ERP 变成可自然语言问答的语义知识图谱。CSV进答案出，确定性规则引擎+本体GraphRAG+向量混合检索，本地化数据不出厂，换行业只换词典。

AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether

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

LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AM

🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline.

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

Let your users ask your database anything, in their own words — safely. The model fills in a validated Query AST, never a query string, and

Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and provenance.

A modern, hands-on, self-paced course that takes you from your first line of Python to shipping a real AI-powered automation.

面向小团队的一站式 NLP 小模型平台:数据集版本管理 · 训练 · 评估 · 在线部署 · Badcase 闭环,内置大模型 Prompt 盲测评测(人工 + AI 双指标)。

RAGless is a semantic retrieval system that answers questions about your documentation, without using an LLM at runtime.

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and

Python RAG-based chatbot for document Q&A using retrieval-augmented generation

Better Estonian from your AI agent. Offline MCP server (no third-party calls) wrapping EstNLTK, EKI Reeglid + Riigi Teataja. 28 read-only to

Free, local-first academic integrity checker and MCP server: citation hallucination detection, AI-text and plagiarism signals, venue guideli

This repository is a comprehensive, hands on roadmap to Python Mastery and AI Engineering. It is designed to take a learner from the very fo

Accepted at ISCSLP 2026 · Target-level benchmark for raw-input Chinese news TTS pronunciation

The fastest lightweight, embeddable tiktoken-compatible Rust core.

Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compre

日本語フリガナ (ルビ) を扱う Rust 製ライブラリ + ローカル HTTP サーバー。ルールはすべてデータ駆動 (TOML)。

A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.

Discover the citing papers that matter most — ranked by impact, relevance, and influence

Salience-aware lexical trie for long-context compression.

Open benchmark for expert collapse and routing efficiency in sparse MoE LLMs

Advanced RAG (Retrieval-Augmented Generation) system for private document intelligence. Uses OpenAI GPT-4o and Vector Databases to provide z

A free, open GenAI curriculum built from scratch. Start from zero, build real projects, and work your way up to production AI systems.

Hybrid RAG over Indonesian legal documents (UU, PP, Perpres, court decisions) with local LLM via Ollama.

Production-grade LLM Evaluation & Benchmarking Framework - GPT-4, Claude, Gemini, Mistral. Accuracy, latency, cost, hallucination, reasonin

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summa

Academic Data Scraper para extração massiva de metadados e abstracts (Scholar/Scielo/arXiv). Otimizado para alta performance e baixo consumo

A lightweight LLM evaluation layer that turns subjective model outputs into deterministic decisions by scoring attribution, specificity, rel