AI大模型与框架

Build agents that monitor and act on your behalf. MIT Ruby

reef是一款专为自优化AI智能体设计的持续学习平台，提供模块化基础设施支持。核心功能包括在线增量学习、实时性能监控与自动化参数调优，适用于需要部署自主进化的AI系统开发者。其特色在于支持多智能体协同训练，具备动态环境适应能力，可显著提升AI系统的长期任务表现与自我优化效率。

User-friendly AI Interface, supports Ollama, OpenAI API. (Source Code) BSD-3-Clause Docker/Python

Message transfer agent (MTA). Sendmail C/deb

AI gateway written in Go with a unified OpenAI-compatible API for multiple LLM providers, USD cost tracking, budgets, usage analytics, guardrails, caching, and an admin dashboard. (Source Code) MIT Go/Docker

Kubernetes operator for self-hosted LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API. (Source Code) Apache-2.0 Go/Docker/K8S

A maintained directory of 49 AI agent platforms: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents, with license and hosting details for each.

All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more. (Source Code) MIT Nodejs/Docker

Message transfer agent (MTA) developed at the University of Cambridge. (Source Code) GPL-3.0 C/deb

Your AI second brain. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI. (Demo, Source Code) AGPL-3.0 Python/Docker

Online lab notebook for research labs. Store experiments, use a database to find reagents or protocols, use trusted timestamping to legally timestamp an experiment, export as pdf or zip archive, share with collaborators…. (Demo, Source Code) AGPL-3.0 PHP

Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more. (Source Code) MIT Docker/K8S

Leading provider of open omnichannel innovation. (Source Code) OSL-3.0 PHP

Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI. Apache-2.0 Docker/Shell

ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness. - XiaoDuoYa/codex-with-chatgpt

Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, then verify. Skill for Claude Code, Codex, and other agents. - Vuk97/forward-implementation-first

LocalAI is the open source AI engine. Run any model, LLMs, vision, voice, image and video, on any hardware. No GPU required.

A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day. - damejan80/tokentab

A Python library for fine-tuning LLMs #opensource.

De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136). - Nanako0129/sepia

useagent是一款面向团队的开源AI协作工具，通过云端计算机集成Claude Code/Codex/OpenCode等模型，自动处理网站开发、PPT制作、报表生成等复杂任务。其核心优势在于可继承团队上下文和工具链，实现任务全流程自动化，显著降低开发运维成本，适合需要高效执行标准化工作的技术团队。

A Claude skill that turns brainstorming into an interactive mind map of inverted assumptions — no answers, no ranking, just provocations. - ara-mkr/Wonder-Pill

Ryza AI companion. Bring your own LLM/TTS. 莱莎 AI 陪伴，自填大模型与语音。 - zeroa234/ryza-ai-revive

Native Rust inference server for open models on NVIDIA GPUs. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio - truespar/paddock

A nightly newspaper written by an agent: the figures come from code, the prose from a small local model, and it never publishes an edition with marks in it.

Apeireth — A Pure Safe Rust AGI Operating System & Cognitive Microkernel. 16 crates: continuous topological memory, causal world model, cognitive scheduler, Ember HUD, triple-onion security & portable USB agent. - Apeireth/Apeireth

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness. - TokenRhythm/NeoHorse