Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
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)
4,305 projects · ranked by GitHub stars, not a quality score
AI Agnostic (Multi-user and Multi-bot) Chat with Fictional Characters. Designed with scale in mind.
几个 AI 终端开着,谁在等你一眼能看见。Claude Code、Codex 还在原来的终端里,旁边就能改文件、看 Git。macOS 本地工作台。
Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.
Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
Samples showing how to build Java applications powered by Generative AI and LLMs using Spring AI and Spring Boot.
An LLM extension for Ghidra to enable AI assistance in RE.
RDNA-native LLM inference engine in Rust.
Spec-driven development for coding agents — a desktop app, a CLI, and skills for Codex, Claude Code, Cursor, Copilot, Antigravity and Junie
SkyAGI: Emerging human-behavior simulation capability in LLM
Claude Code skills for startup founders — product briefs, competitor analysis, pricing strategy, pitch decks, and GTM plans from your termin...
An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.
Embeds text files into vectors, stores them on Pinecone, and enables semantic search using GPT3 and Langchain in a Next.js UI
Open-source Grok Bot alternative for teams. Always-on bots that run on your Claude Code or Codex subscription, in chats your whole team can...
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
:newspaper: Let LLM Summarize Hacker News for You
Hands-on LangGraph course repo for building production-grade LLM agents with Agentic RAG, ReAct, and reflection workflows.
鲸鲸 · 让 DeepSeek 用你的微信账号陪聊(Windows 桌面端 + WPF 启动器)。WeChat chat bot powered by DeepSeek/Qwen.
One-click, privacy-first exporter for Claude.ai chats — clean Markdown with artifacts and attachments, ready for Obsidian and RAG.
Managed Claude Code instruction deployment with safe CLI recovery and an unsigned macOS/Windows desktop beta.
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Aligning Large Language Models with Human: A Survey
AI Werewolf game. You take one seat, LLM players fill the rest. AI 狼人杀。