llm

MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments.

Llama 3+ inference in pure Java

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

Blades is a Go-based multimodal AI Agent framework.

🔥 This repository contains complete application examples, including websites and other projects, developed using Firecrawl.

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)

A real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate with any open source Avatar components (real-time model, visual, voice, memory, search, etc.).

Train a 1B LLM with 1T tokens from scratch by personal

Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.

Training/Fine-tuning at the speed of light

Flexpilot - Open-Source, Native and a True GitHub Copilot Alternative for VS Code

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案，包含从训练到推理的完整代码和脚本，以及实践中积累一些经验和结论。)

Early WebMCP proposal / implementation - since evolved and worked on by much more capable folks that develop the web: https://github.com/webmachinelearning/webmcp

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

Debug your AI agents

A 股多智能体智能投研系统 — 基于 TradingAgents 架构，15 名 AI Agent 模拟机构协作与实时辩论对抗，全流程可视化，支持 OpenClaw / Claude Code 集成，Docker 一键部署。

Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.

AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知

Hypernetworks that update LLMs to remember factual information

Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tools, 10 warehouses, AI-powered.

One gateway in front of every protocol. Same policy across MCP, LLMs, databases and containers. Wire-level enforcement at under 5ms.

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more

Evidence-constrained commercialization assessment: deterministic retrieval, a six-stage LLM workflow, auditable scores and checkpoint recovery. Qwen / DeepSeek / OpenAI / Claude.

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

AI VTuber with LLM, ASR, TTS, OCR, CV and more technologies to live stream or play Minecraft with you.

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

Connect and chat with your multiple documents (pdf and txt) through GPT 3.5, GPT-4 Turbo, Claude and Local Open-Source LLMs

🤖 Beautifully designed chatbot components based on shadcn/ui