Reach 125K+ monthly visitors
Advertise on TrendshiftRAG
Chatbot RAG para consulta de documentación técnica y catálogo de vehículos. Python, LangChain, OpenAI, FastAPI, ChromaDB, Docker.
Self-hosted, privacy-first document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page citations.
A Zotero 7 and above plugin that answers questions about your PDFs with inline, clickable page citations — every claim links straight to the source. Works on one paper or across many, with Claude, GPT, Ollama, DeepSeek, or Grok.
MCP server wrapping semantic-memory — local-first knowledge management with evidence-scored retrieval, contradiction detection, and adaptive routing
Markdown-first semantic search CLI for your documentation, powered by vector embeddings and Qdrant or pgvector.
we built this project for a vitual hackathon called Quackathon
Agent-agnostic autonomous research protocol adapted from Deli AutoResearch, with STORM-style multi-perspective questioning, source-grounded claim ledgers, persistent state, Discovery Tail Pass, and sufficiency checks for long-horizon AI agents.
The open-source MCP server behind ByteAsk Embedded Docs: a source-grounded, page-cited evidence-retrieval server for coding agents (Claude Code, Codex, Cursor) that write firmware / driver / protocol code and need exact facts.
A local-first LM Studio companion for configurable RAG, chat history, and custom AI workflows.
FinSight is a low-latency financial intelligence agent that combines real-time market data ingestion, FAISS-powered RAG retrieval over financial news, and LLM reasoning with embedding inference benchmarked across CPU and CUDA-optimized paths.
LEXIS — on-device legal intelligence
One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code extension.
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
AI agent that drafts replies to Slack/Email in your own voice — RAG-grounded knowledge base, urgency triage, human approval before sending. Day 14 of 27-day AI agent build challenge.
开源 AI 应用评测平台，支持 RAG、AI Agent、多轮对话、LLM-as-Judge、接口评测、评测报告和人工盲测。Open-source AI evaluation platform for RAG, AI Agents, multi-turn conversations, LLM-as-Judge, endpoint evaluation
~967,000 live jobs from 16 ATS, enriched with LLM-extracted fields + embeddings, released CC0. Includes agent tooling to search them (hull -> learn -> rank).
Official DittoBench miner starter kit for Bittensor subnet 118 — baseline harness, offline practice runner, scorer, and submission flow.