开源紫微斗数 AI Agent:基于确定性命盘事实进行可追溯对话。 Evidence-backed chart conversations.
Best LLM Chat Tools
LLM chat tools are the front door to modern AI — from general assistants to specialist chat UIs. Scan popular GitHub projects here (ranked by stars), then open the compare page for a compact decision table.
Popular on GitHub (by stars)
4,301 projects · ranked by GitHub stars, not a quality score
Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev
[MM' 2026] Light-MER for efficient multimodal emotion recognition with sub-1B MLLMs.
RoleMule — One mule for every role. Self-hosted AI job companion. Paste a posting (or Chrome extension): five agents analyze the role, score...
Local security proxy that keeps secrets and sensitive data out of AI requests. Supports Codex, Claude Code and more.
Autonomous AI agent orchestrator — run multi-model dev teams (Claude, Gemini, GPT) with YAML workflows, daemon scheduling, and MCP integrati...
MCP server for the tastytrade open API: quotes, positions, balances, and dry-run-gated order flow for LLM agents.
Plugins for git and project workflows, code audits and release checks. All 13 run in Claude Code, and 8 also run in Codex and Cursor.
JSON API of 40+ DeFi, portfolio and trading agent definitions in 18 languages, with a Claude Code plugin.
Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Clau...
💻 Keeps your Mac awake while your AI agents work. Built-in detection for Claude Code, Codex, Cline, Copilot plus presets for Gemini CLI, Op...
Community-driven Claude Code marketplace with specialized AI agents for the full SDLC. Features multi-agent coordination, workflow orchestra...
LLaMA-BitNet is a repository dedicated to empowering users to train their own BitNet models built upon LLaMA 2 model, inspired by the ground...
Pocket-sized Ruby AI agent framework / LLM assistant with multi-LLM support
Local-first Windows desktop AI chat. Runs models through Ollama or its own managed llama.cpp runtime (GGUF files). Nothing leaves your machi...
A collection of Italian benchmarks for LLM evaluation
LinkTokenView(联视未来)国产大模型 Token API 聚合平台,提供 OpenAI 兼容接口,统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型,支持 Token...
Open-source AI co-author for novelists & world-builders. ✍️ Canon-safe writing · RAG lore glossary · polyglot translation · BYOK multi-LLM....
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
A native, performance-first ADE built with Flutter, Rust, and Ghostty. Run Claude Code, Codex, Amp, and other CLI coding agents in parallel....
Drive ChatGPT and Gemini from Python — no API keys, no billing, just the free web UI.
Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu...
Fully local: chat, a coding agent, and a design studio in one private desktop app.