LLM 模型排行

A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI like Codex CLI and Claude Code through a gated LaTeX workflow with verified BibTeX citations.

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

visionOS examples ⸺ Spatial Computing Accelerators for Apple Vision Pro

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

Odyssey: Empowering Minecraft Agents with Open-World Skills

Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, OpenHands, Aider, Goose, OpenClaw, NVIDIA NemoClaw & more. Live token costs, sessions, tool calls, crons.

Context-Engine MCP - Agentic Context Compression Suite

Neovim plugin for interacting with LLM's and building editor integrated prompts.

🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Low latency JSON generation using LLMs ⚡️

The Official Repo for "Quick Start Guide to Large Language Models"

🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer. Features 60+ coding prompts and generates structured overviews with metrics. Ideal for feeding projects to LLMs like GPT-4, Claude, PaLM, and Gemini for code analysis and understanding.

Quickly create functional plugins from simple descriptions, addressing specific needs without unnecessary bloat.

ATLAS: a senior-engineer layer for Claude Code. Explore with wireframes & prototypes, clarify the essentials, capture it in HTML spec doc then let Claude Code's native plan/goal/workflow loop build. Fewer tokens, less ceremony, faster to what people pictured. KISS/YAGNI/DRY, context decides. No overengineering. Clean architecture that works.

The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

Documentation of AnythingLLM by Mintplex Labs Inc.

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness.