LLM 模型排行

A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.

A simple "Be My Eyes" web app with a llama.cpp/llava backend

Manifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.

Use MCP and OpenAPI to safely control Proxmox VE VMs, LXCs, backups, and snapshots from LLMs and AI agents.

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

🔥 AI-powered deep research tool that breaks down complex queries, validates answers, and provides cited comprehensive results using Firecrawl and LangGraph

Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack，让 AI 团队各司其职、自主稳定迭代。

Local first semantic code search and chat | Leverage custom copilots with fine-tuning datasets from code in Alpaca, Conversational, Completion and Instruction format

The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.

The first AI Agent Server, Eidolon is a pluggable Agent SDK and enterprise ready, deployment server for Agentic applications

🔥 A Survey on AI Auto-Research

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Advanced Retrieval-Augmented Generation (RAG) through practical notebooks, using the power of the Langchain, OpenAI GPTs ,META LLAMA3 ,Agents.

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

A fast and minimal framework for building agentic systems