Search

具备“信”、“达”、“雅”翻译能力的英译中智能体

This project is designed to collect, analyze, and summarize news articles using AI. It integrates multiple news sources for collection and uses AI models such as DeepSeek and Gemini for analyzing the content. The system interacts with the AI to provide insights.

Salesforce AI Assistant — An intelligent, LLM-powered assistant that enables natural language interaction with Salesforce metadata and data. Built with LangGraph for agent workflows, Weaviate for semantic search, MongoDB for short-term memory, and high-quality embedding models. Supports SOQL generation, metadata exploration, and secure multi-org

Comparative Guide Assistant

Open source version of Notebook LLM

Skill-oriented desktop GUI vision automation CLI for LLM agents with machine-readable JSON output.

🗣️ Engage in real-time voice conversations with an AI agent using Next.js and ElevenLabs for an interactive and responsive user experience.

Open LLM CLI - LLM Automation

The Sakhi Project is emotional AI, built entirely through prompts (no APIs, no memory, no fine-tuning)

An agent that leverages Python to collect, analyze, and interpret datasets, providing data-driven answers.

Advanced Research Agent built with Python, MCP, Firecrawl, and LangGraph to autonomously crawl, extract, and structure web research data using LLM-driven workflows.

MassAudit Pro: Next-Gen Agentic Security Auditor. Combines CodeQL's precision with LLM (DeepSeek) reasoning. Features an automated "Context-Retrieval Loop" that fetches missing function definitions to eliminate false positives. The future of SAST.

An agent-based system for context-based document filtering and information aggregation.

AgentHER: Hindsight Experience Replay for LLM Agents

Extensible framework for creating and managing LLM function calling.

No description available

Interactive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player characters (NPCs) in any game!

A shared decision protocol for governed collaboration between agents, automation, and stewards.

LLM quant agent with persistent graph memory (Vector DB + Knowledge Graph). Uses LSTM encoder for pattern similarity and Neo4j for causal attribution.

An autonomous web scraper that fixes its own broken selectors using a fine-tuned multimodal LLM (Qwen 2.5) and DOM-aware RAG.