LLM 模型排行

A stateful multi-agent travel service system built on LangChain & LangGraph. Features intelligent task delegation, permission control, and human-in-the-loop verification for flight booking, hotel reservations, car rentals, and tour planning.

Faster runtime for coding agents. Make coding agents 25% faster and 30% cheaper on average while keeping the quality same or more. Same Task, Same Quality, Faster and Cheaper.

Local-first AI chat client combining SillyTavern-style character cards, LM Studio-style GGUF model management, Ollama/OpenAI-compatible APIs, and an agentic workspace.

MCP server that gives AI assistants control over your Home Assistant. Including 50+ tools over 3 transports. Batteries included 🔋

A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed tools. MCP · ACP · A2A. One Rust binary.

OpenAI-compatible gateway aggregating 8 free LLM providers with automatic failover, circuit breakers, and smart routing. 32+ models, zero cost.

3DCF / doc2dataset: token-efficient document layer with NumGuard numeric integrity and multi-framework exports for RAG & fine-tuning.

Cookbooks and tutorials on Literal AI

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

LLM security and privacy

Prompt Hardener analyzes prompt-injection-originated risk in LLM-based agents and applications.

The Mastercard Developers Agent Toolkit allows popular agent frameworks to integrate with Mastercard Developers Platform for service discovery and integration guides.

A developer-friendly template for building AI assistants that combines the best of LangServe, LangGraph, and assistant-ui into one seamless package.

Build a simple RAG chatbot with LangChain and Streamlit

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

Self-contained offline environment providing local AI chat, offline Wikipedia/content archives, IRC communication, audio streaming, file server, and development tools. Designed for zero internet dependency - download once, run anywhere. Perfect for remote areas, emergency scenarios, or escaping surveillance capitalism.

🚀 Phantom-AI-Interview – A fun experiment exploring how AI can silently assist in virtual interviews, coding challenges, and exams. Uses OCR, LLMs, and automation to extract text, generate responses, and operate without a visible UI. 🔥

Benchmark your local LLMs.

Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.