LLMs & Model Tooling
Model-layer infrastructure: training, fine-tuning, prompting and everything that wraps a large language model.
Plug-and-play homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can explore it too.
🤖 Building AI Agent Systems from Scratch — A comprehensive, practical tutorial from fundamentals to production-grade multi-agent applications
The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.
A curated collection of datasets for Large Language Models (LLMs), covering medical AI, NLP, multimodal learning, instruction tuning, reasoning, code generation, and evaluation benchmarks.
面向教育场景的RAG智能问答系统，融合关键词匹配与语义检索双引擎，融合MySQL和RAG技术，先经过MySQL数据库的检索(还融合了Redis辅助储存和搜索)，若无符合条件答案，则进入RAG系统，RAG知识库中的知识储存在Milvus向量数据库中
Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.
Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.
High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.
Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.
Stop re-explaining your data to your AI every session. The individual-analyst context layer, delivered over MCP (Claude Code / Cursor / Codex).
The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.
一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。
Keep one source of truth for your AI coding-agent rules. Convert and sync between AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Windsurf, Cline, Aider & Gemini — or scaffold a fresh AGENTS.md. Zero dependencies.
Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development review using → test AI large language models. Capable of autonomously handling medium to large-scale engineering projects.
Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.
Deploy a complete self-hosted AI stack with Docker Compose: Ollama, LiteLLM, AnythingLLM, Whisper, WhisperLive, Kokoro, Embeddings, Docling and MCP Gateway. Local-first, private by default, with lightweight stacks, optional HTTPS and NVIDIA CUDA acceleration. Multi-arch: amd64, arm64.
A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.
QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.
学习Agent开发的笔记，尝试让Agent从可用到可靠
Local-first AI workspace for macOS. Ten workspaces — Coder, Agent Swarm, Finance, 3D Forge, Sandbox, Virtual OS and more. 12 providers, or fully offline with Ollama. No backend, no telemetry, no account. Your keys and files stay on your machine. 8.9 MB, MIT.
TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。 它不是只封装一次模型调用，而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批、执行中干预，到 SSE 流式输出和全链路观测的完整过程。
An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.
Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.
面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.
200 production-grade DESIGN.md design systems for the world's best apps. Framework-neutral plus SwiftUI, Jetpack Compose, and Expo. Hand one to your AI agent, ship pixel-matched UI.