An open-source visual programming environment for battle-testing prompts to LLMs.
AI 开源项目
精选 GitHub 上值得关注的 AI 开源项目:大模型、智能体、RAG、本地部署、图像与语音……共收录 1037 个。
想找可以部署在 Cloudflare 免费套餐上的项目?看 Cloudflare 开源
Multi-framework streaming Markdown renderers for AI apps: Vue/Nuxt, React/Next.js, Svelte, and Angular, with Mermaid, KaTeX, stream-diffs code blocks, safe HTML, and low-jitter updates.
Deepnote is a drop-in replacement for Jupyter with an AI-first design, sleek UI, new blocks, and native data integrations. Use Python, R, and SQL locally in your favorite IDE, then scale to Deepnote cloud for real-time c
DeepTeam is a framework to red team LLMs and AI agents.
PyTorch native quantization for training and inference
Inspect: A framework for large language model evaluations
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
Community maintained hardware plugin for vLLM on Huawei Ascend
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Data manipulation and transformation for audio signal processing, powered by PyTorch
Ruler — apply the same rules to all coding agents
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS
OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.
Minimalistic large language model 3D-parallelism training
An open-source data logging library for machine learning models and data pipelines. 📚 Provides visibility into data quality & model performance over time. 🛡️ Supports privacy-preserving data collection, ensuring safety
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
在 stdio 与 SSE / HTTP 传输之间互相转换的 MCP 代理。
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.
Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.