grounded-generation 开源项目推荐（69 个）

microsoft /GODEL

用于目标导向对话的大规模预训练模型

Lipurple /Grounded-Diffusion

Open-vocabulary Object Segmentation with Diffusion Models

microsoft /MSR-NLP-Projects

This is a list of open-source projects at Microsoft Research NLP Group

smaramwbc /statewave-grounded-shop-assistant

Statewave use case in TypeScript: a grounded product advisor and support assistant, with an Ops Assistant that tracks and closes content gaps.

stevencallaway1 /FoodLM

An open-source LLM for food product development

StevenTsai /grounded-rag

Lightweight open‑source RAG framework with claim‑level deterministic verifier — reducing hallucinations by refusing claims that lack evidence, not just generating them.

sebastienrousseau /draft

Turn research PDFs into grounded Markdown drafts — driven by any token-free AI coding-agent session (Claude, Codex, Gemini, Copilot, Cursor, Amp, Crush, Goose, Grok) when online, local Ollama when offline.

coffeequickly /orchestrion

Deterministic multi-LLM orchestration with grounded, verified answers, an editable guardrail gate, and a live process dashboard.

azige1 /FinQA

Financial report grounded QA post-training with QLoRA SFT, DPO preference learning, citation/numeric evaluation, and badcase analysis.

MaSunKing /facade-multimodal-rag-agent

本地企业多模态 Agent：精简Planner、LangGraph有限编排、SQL与混合检索、任务上下文与预算感知、轻量审核、可追溯多模态证据；附100题评测设计（迭代中）

ilyautov /hefest

HEFEST: on-prem рабочее место по химической безопасности завода: паспорта ГОСТ 30333, аварийные карточки, зоны АХОВ, совместимость хранения, СИЗ, класс отхода. Поиск тут фундамент, а не продукт. Офлайн, с провенансом, без выдуманной нормативки. | On-prem chemical safety for industrial plants, with provenance.

sanjay-dilip /levis-rag

Levi's RAG is an AI due diligence copilot for equity research on Levi Strauss & Co. It answers natural-language financial questions using only official SEC filings, grounding each answer in the exact source sentence and tagging it with an evidence tier (verified, qualitative, benchmark, or inference).

GIZELLYPY /llm_ka

Beginner-friendly Python RAG project that turns StackOverflow Q&A data into a grounded knowledge assistant using sentence-transformer embeddings, FAISS retrieval, and strict citation-based LLM answering.

cyberkunju /kspci

Conversational + predictive crime intelligence on Zoho Catalyst: ask 1M+ FIRs in English or Kannada and see the query and rows behind every answer. All-India NCRB-calibrated corpus (640 districts), forecasting validated on 6.37M real incidents, and a trilingual WhatsApp channel for field officers.

EricRollei /Visual_Research

ComfyUI Custom Nodes for Gen Searcher and other tools

TheDarkniteFalls /local-model-reliability-example

Dependency-free checks for structured local-model output, grounded answers, citations, and protected writes.

ChelseaKR /cairn

pip install cairn-assistant · Grounded-or-silent reference assistant for public agencies: answers only from a supplied corpus, cites every claim, and refuses cleanly rather than guessing. No model and no network at answer time. English and Spanish plus right-to-left languages. A reference implementation to read, not a product to deploy.

dhirajxai /prompt-engineering-foundations

Developer-first prompt engineering patterns for grounded, testable, and reliable AI outputs.

zenouz-ai /zengrowth

Open-source ZenGrowth mirror: a local-first, verification-first career agent with auditable scoring, evidence-constrained materials, and human-controlled outbound actions

anan5093 /Enterprise-RAG-Intelligence

Secure Enterprise RAG platform with RBAC enforcement, OWASP LLM defenses, hybrid retrieval, grounded generation, explainability, and zero-trust context pipelines.