AI 开源项目

多场景优化脚本：AI chat全能助手、linux.do摸鱼...

A searchable directory of 2,700+ self-hosted, open-source apps — with setup guides, alternatives & live version tracking.

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.

Hermes-Relay — Your Hermes AI agent, in your pocket — chat, voice, and control.

Hybrid Transformer with Online RNN Memory for Neocortex Memory.

中文UI / A terminal-based coding agent with unlimited concurrency, multi-agent orchestration, and a persistent Python runtime (RLM) for stateful data work and recursive subagent delegation

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

A curated collection of resources, tools, practices, case studies, and opportunities for Forward Deployed Engineers.

Open-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Codex, OpenClaw, Hermes); generate via Atlas Cloud — Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu, Gemini Omni, Grok Imagine.

A curated collection of cutting-edge AI agent frameworks, developer tools, and automation resources — by AI Pulse Georgia

AgentEval is the comprehensive .NET toolkit for AI agent evaluation—tool usage validation, RAG quality metrics, stochastic evaluation, and model comparison—built first for Microsoft Agent Framework (MAF) and Microsoft.Extensions.AI. What RAGAS, PromptFoo and DeepEval do for Python, AgentEval does for .NET

A local workbench for agents doing continuous work across sessions, commands, human input, and external events.

AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs.

Community-maintained agent skills for MapLibre GL JS — helping AI coding assistants write better mapping code

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to runnable code, swap wire protocols (Dify/OpenAI).

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.

Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.

Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.

Intelligent multi-LLM router with task-aware routing strategies, cost optimization, and production safety controls — drop-in OpenAI-compatible API

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

Local-first image prompt library for generating images, saving prompts, tags, and collections.

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

Synthetic Autonomic Mind - An AI assistant for everyone.

Ultimate Claude Fable 5 Guide 2026: Use Cases, Integrations & Benchmarks