Stars
Codegex, a regular-expression-based static analysis approach for automated code review.
🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍
We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
《AI 研发提效:构建 AI 辅助编码助手》 —— 介绍如何 DIY 一个端到端(从 IDE 插件、模型选型、数据集构建到模型微调)的 AI 辅助编程工具,类似于 GitHub Copilot、JetBrains AI Assistant、AutoDev 等。
UnitEval is a benchmarking and evaluation tools for AutoDev Coder.
An easy-to-learn/use static analysis framework for Java
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…
DSPy: The framework for programming—not prompting—foundation models
A high-throughput and memory-efficient inference and serving engine for LLMs
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
🐫 CAMEL: Finding the Scaling Law of Agents. A multi-agent framework. https://www.camel-ai.org
CodeAssist is an advanced code completion tool that provides high-quality code completions for Python, Java, C and so on. CodeAssist 是一个高级代码补全工具,高质量为 Python、Java 和 C 补全代码。
Repository for the Paper "Multi-LoRA Composition for Image Generation"
You can play any API server that compatible with OpenAI API
OpenAI 接口管理 & 分发系统,支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元,可用于二次分发管理 key,仅单可执行文件,已打包好 Docker 镜像,一键部署,开箱即用. OpenAI key management & redistributi…
Drag & drop UI to build your customized LLM flow
LLM powered development for VSCode
LSP server leveraging LLMs for code completion (and more?)