knowledge-retrieval 开源项目推荐（104 个）

arn-c0de /Crawllama

CrawlLama 🦙 is an local AI agent that answers questions via Ollama and integrates web- and RAG-based research.

Md-Emon-Hasan /MediGenius

AI-powered multi-agent medical assistant with a deterministic safety layer — crisis detection, refused-topic hard-stops, dosage grounding, and post-generation diagnosis verification running before and after every LLM call, backed by parallel RAG, Wikipedia, and Tavily retrieval with symptom and drug-question routing.

kallemickelborg /stateful-ai-agent

Stateful AI Agent for Knowledge Extraction

AliceLJY /recallnest

One memory, every terminal — a shared memory layer for any MCP client.

mims-harvard /ark-agent-cli

Terminal based chat implementation of ARK agent

Shuvam-Banerji-Seal /AgriIR

AgriIR: Configurable RAG framework for domain-specific knowledge retrieval in agriculture. Features 6-stage pipeline, deterministic citations, and domain-specific agents. ECIR'26.

vinnybellack /PromptWeaver-RAG-Edition

PromptWeaver: RAG Edition helps design effective prompts for Traditional, Hybrid, and Agentic RAG systems. It offers templates, system prompts, and best practices to improve accuracy, context use, and LLM reasoning.

theSleepyPig /AALawyer

(ACL 2026 Main) Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents

vanyadraven /sonnenfeld

Project context and memory for coding agents.

cnbjjj /td-rag

A local Retrieval-Augmented Generation (RAG) system for answering questions about TouchDesigner using wiki pages, tutorials, and other structured or semi-structured content. Powered by FAISS and local LLMs via Ollama.

Bhavesh716 /Self-healing-RAG-pipeline

Self-healing RAG system that retrieves, verifies, and grades its own answers. Automatically rewrites queries and retries when outputs are weak, ensuring accurate, hallucination-free responses.

jaredhorn511-stack /qepm-1k-retrieval

Sub-linear knowledge retrieval via quantum-inspired hyperdimensional folded space (0.88ms @ 100% accuracy)

Luious-LYH /TiBan

TiBan | Agent-native learning workspace for multi-domain question banks, contextual tutoring, governed RAG, FSRS review scheduling, learning memory, and model evaluation.

Daniel-codi /Concept_Curve_Embeddings_Indexation

Code to make any AI have unlimited context persistent memory. In the example, a software for any AI to read the Uniform Commercial Code of Michigan. A document of 220,000 tokens

deibertmyung-ship-it /wenmai-search

Wenmai Search — self-hosted, traceable hybrid document retrieval with REST, MCP, and Web UI

szilvia-csernus /openai-assistants-with-file-search

Notebook examples for using OpenAI's Assistants API with the file search (knowledge retrieval) functionality.

TEAM-SEAM-contextctl /contextctl

Knowledge retrieval control plane for scoped and governed context delivery.

XimilalaXiang /viking-go

Go reimplementation of OpenViking — hierarchical context database for AI agents with long-term memory, RAG, embedding, and skill management. Single binary ~14MB

Anurag-M1 /Corrective-RAG

Corrective RAG with LangGraph: evaluates retrieval quality, routes to web search when needed, refines context, and generates grounded answers.

sonwanesuresh95 /askdoc-local

⚡️ Local RAG API using FastAPI + LangChain + Ollama | Upload PDFs, DOCX, CSVs, XLSX and ask questions using your own documents — fully offline!