CDRAG is a new retrieval framework that uses hierarchical document clustering, and LLM-guided document selection from those clusters to curate the context most efficiently. It is benchmarked against standard top-K RAG on 100 legal questions from the Legal RAG Bench dataset.
☆39Apr 13, 2026Updated 6 months ago
Alternatives and similar repositories for Clustered-Dynamic-RAG
Users that are interested in Clustered-Dynamic-RAG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Structure-aware RAG for financial document QA - 82% on FinanceBench. LLM navigates section headings instead of searching embeddings.☆13Apr 15, 2026Updated 6 months ago
- Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL rev…☆30Updated this week
- One library to split them all: Sentence, Code, Docs. Chunk smarter, not harder; built for LLMs, RAG pipelines, and beyond.☆88Updated this week
- Roaring Bitmap positional phrase matching for low-latency LLM context retrieval.☆29May 4, 2026Updated 6 months ago
- Tree-based, vectorless document RAG framework. Connect any LLM via URL/API key.☆43Apr 7, 2026Updated 7 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents ha…☆39Nov 5, 2026Updated last week
- Offline local-first personal knowledge base with document upload, vector search, and Ollama-powered RAG chat.☆12Nov 5, 2026Updated last week
- Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.☆47Jun 22, 2026Updated 4 months ago
- Fully local governed RAG for code, documents, and tables.☆42Sep 26, 2026Updated last month
- This is more like a QA system☆16Jul 20, 2026Updated 3 months ago
- Secure your AI Agents against prompt injection attacks☆19Apr 24, 2025Updated last year
- LexReviewer is an AI legal document review engine that ingests PDFs, uses RAG for hybrid retrieval, and enables grounded chat with citati…☆23Mar 16, 2026Updated 7 months ago
- rudradb-opin-examples is for example implementations of the pip install rudradb-opin☆29Mar 3, 2026Updated 8 months ago
- Spectral graph-augmented retrieval for RAG. Augments dense vector search with a weighted chunk graph and its Laplacian spectrum, graph ex…☆51Nov 4, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Help with documents in Paperless NGX with confidential LLM by Privatemode.ai☆11Aug 2, 2026Updated 3 months ago
- ☆20Oct 24, 2026Updated 2 weeks ago
- ☆56May 29, 2026Updated 5 months ago
- A full-stack document management and AI chat application that enables users to upload, manage, and chat with their documents using AI. Bu…☆16Aug 10, 2025Updated last year
- A hierarchical multi-agent framework for exhaustive cross-document question answering.☆21Mar 14, 2026Updated 7 months ago
- Zero-shot forecasting, tabular classification, and regression via MCP — exposes Google TimesFM 2.5 and TabFM v1.0.0 to AI assistants. Jus…☆32Sep 4, 2026Updated 2 months ago
- ☆24Apr 3, 2026Updated 7 months ago
- ☆10Jul 20, 2023Updated 3 years ago
- ☆18Dec 1, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Socratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domai…☆83Jan 13, 2026Updated 9 months ago
- [H] HyperspaceDB is a high-performance, vector database. It features 1-bit quantization, async replication, and native support for hierar…☆167Updated this week
- Drop-in causal memory for AI agents. Append-only event store with associations and bounded memory injection.☆26Nov 2, 2026Updated last week
- Use any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.☆18Aug 14, 2026Updated 2 months ago
- Word GPT Plus is a word add-in which integrates the chatGPT model into Microsoft Word. Both official and web api is supported.☆15Oct 16, 2026Updated 3 weeks ago
- vLLM on AMD RDNA4 (gfx1201 / RX 9070 XT-9070): clone-and-docker-compose-up, with a W4A8-FP8-WMMA MoE kernel☆14Jul 18, 2026Updated 3 months ago
- An AI-powered security analysis tool for web applications that combines Large Language Model (LLM) analysis with intelligent agent-based …☆46Jul 26, 2025Updated last year
- AI-native legal data layer for the agentic economy. 500M+ US federal court records via x402 micropayments on Base. $0.001 USDC per query,…☆34May 28, 2026Updated 5 months ago
- ☆104Nov 27, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆16Sep 1, 2026Updated 2 months ago
- Infrastructure for AI Coding Agents☆18Mar 16, 2026Updated 7 months ago
- Local whiteboard that blooms.☆32May 10, 2026Updated 6 months ago
- A free Windows build planner for Valheim: 397 pieces, world maps, building levels, and material totals.☆17Sep 11, 2026Updated 2 months ago
- Repository for paper: Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets☆31Apr 27, 2026Updated 6 months ago
- A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.☆139Nov 2, 2026Updated last week
- Self-hosted Docker fleet manager in a single binary: Compose stacks across hosts with agents, backups, reverse proxy, roles and SSO.☆21Updated this week
Are these results useful?