Lists (5)
Starred repositories
94 models. 30 providers. One command to find what runs on your hardware.
Build resilient language agents as graphs.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
A modern static site generator by the Material for MkDocs team
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Open-source AI hackers to find and fix your app’s vulnerabilities.
🐍 Community-driven Python implementation of TOON
AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A secure low code honeypot framework, leveraging AI for System Virtualization.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A single interface to use and evaluate different agent frameworks
The open-source CapCut alternative
MCP Toolbox for Databases is an open source MCP server for databases.
Make beautiful isometric infrastructure diagrams
Infrahub is a graph-based data management platform with built-in version control, CI workflows, peer review, and API access. It’s purpose-built to power reliable infrastructure automation at scale.
A high-throughput and memory-efficient inference and serving engine for LLMs
supporting materials for vault series on problemofnetwork.com
Achieve state of the art inference performance with modern accelerators on Kubernetes
Auto documentation for Ansible roles and collections
Visual testing tool for MCP servers
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
very good whiteboard infinite canvas SDK
An ansible-native testing framework for collections, playbooks, and roles with configurable workflows for testing any system or service