(CVPR 2025 highlight✨) Official repository of paper "LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"
Repository Index
142,273 visible repositories in the index
1,633–1,656 of 1,943 · Most stars
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
- ai-safety
- claude-code
- codex-cli
- gemini-cli
Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.
- bert
- hallucination-detection
- hallucination-evaluation
- information-extraction
A framework to evaluate the generalization capability of safety alignment for LLMs
- alignment
- jailbreak
- large-language-models
- llm
小北在读研开源 Codex Skills 合集:Image to VBA、Academic Paper to PPT 等 AI + 科研工作流。
- academic-figures
- codex-skill
- office-vba
- openai-codex
Code for fine-tuning Platypus fam LLMs using LoRA
A MCP (Model Context Protocol) server for interacting with dbt.
🎬 Short-Drama Factory v4.9.1 · 抖音/红果爆款短剧工业化编剧超级系统 | 一句创意/一部网文 → 标准60-100集·长档30-50集·漫剧带付费墙剧本 | v4.9 强画面支撑+15秒换挡+大白话直给+剥壳仿写 | 40赛道全图+六母型钩子+五大断章+A~I反转轮换 | 情绪契约单元链·单矛盾≤30集闭环 | 动态按需挂载矩阵(8交互模式防Context爆炸)| 机检E1~E26+S1~S8 | 纯剧本层 · Industrial hit short-drama screenplay engine (60-100 eps, paywall built-in)
- ai-writing
- chinese-drama
- douyin
- hongguo
🔥 The first-ever interactive streaming video generation benchmark.
- avatar-performance
- interaction-streaming-video
- real-time-video-editing
- streaming-video-generation
A very quick project that transforms research papers into engaging three-person discussions, offering an intuitive and thought-provoking listening experience. Perfect for podcast enthusiasts seeking a fresh way to explore academic content.
基于SparkTTS、OrpheusTTS等模型,提供高质量中文语音合成与声音克隆服务。
- llamacpp-python
- sglang
- vllm
- sparktts
Anthropics/skills中文学习版本 来自:https://github.com/anthropics/skills
RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.
- ai-agents-framework
- embodied-agent
- embodied-ai
- embodied-artificial-intelligence
HunterCode · Community Edition · 腾讯 WorkBuddy 金融版的开源本地替代方案 · open-source, local alternative to Tencent WorkBuddy Finance Edition · 多智能体投研终端 A股/港股/美股 · 推理在你机器上跑 · 仓位不出你硬盘 · BYOK · Apache 2.0 · docker compose 自托管
- ai-agents
- docker-compose
- financial-ai
- mcp
Recursive Language Models for efficient long-context processing. Analyze 1M+ tokens by storing context in a Python REPL while reducing LLM token usage.
🤖 Agentfy is a modular microservices architecture designed to process user requests and execute workflows across multiple social media platforms. ASK ONCE, LET THE AGENT DO THE REST!
结合chrome-devtools-mcp的能力并加上Skill的规范,实现JSRPC+Flask+autoDecoder方案的前端JS逆向自动化分析,提升JS逆向的效率
- js
- automation
- reverse
- skills
kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)
- framework
- function-calling
- large-language-models
- llama
multilspy is a lsp client library in Python intended to be used to build applications around language servers.
- ai
- ai4code
- artificial-intelligence
- code-analysis
ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24)
MCP to connect your LLM with Spotify.
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
The repository host gives no description.