100/100
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Continuously updated
New developer tools
Browse the latest quality-filtered tools added to YunoDB from verified public project data.
Recently added
14264 tools
88/100
robots-in-disguise
Information and materials for the Turing's "robots-in-disguise" reading group on fundamental AI research.
89/100
Mechanist
AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence
99/100
chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
87/100
AgentHub
Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservices, multi-type data
100/100
OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
100/100
camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
92/100
Awesome-LLM-Ensemble
A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"
88/100
TrialMatchAI
TrialMatchAI leverages large language models to streamline clinical trial matching by evaluating patient-specific clinical characteristics against trial eligibi
80/100
awesome-llm
A curated list of awesome LLM frameworks, libraries and software.
98/100
FlashRAG
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
95/100
llm-master
大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。
88/100
MOSAIC
⚛ MOSAIC is a visual-first platform that enables researchers to configure, run, and compare experiments results across RL, LLM, VLM, and human decision-makers t
98/100
lmms-eval
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
88/100
alith
Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents and LazAI Gateway for Everyone
88/100
everruns
Headless durable agentic harness engine. Run durable AI agents reliably and scalably.
88/100
conductai
Runtime governance for AI agents. Allow, warn, or block every model and tool call before it commits. Hash-chained audit for every decision. Compliance packs for
88/100
Orquestrador-Maestro
AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemini and Windsurf.
87/100
dwarf_fortress_mcp
A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B s
87/100
skill-router
Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+
88/100
dcc-mcp-core
Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.
93/100
vigil
Vigil: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.
90/100
clawmax
ClawMax is OpenClaw to the Max! 🚀 A web orchestration layer for OpenClaw agents, teams, workflows, and templates.
99/100
openmed
Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no clou