88/100
okto-nexus
Local-first MCP coordination hub for multi-agent teams, with durable messaging, handoffs, governance, and observability.
Continuously updated
New developer tools
Browse the latest quality-filtered tools added to YunoDB from verified public project data.
Recently added
13458 tools
98/100
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
92/100
Undefined
QQ bot platform with cognitive memory architecture and multi-agent Skills, via OneBot V11.
95/100
Multi-Agent-CAD
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
93/100
config
Configuration files and scripts used in guides and for system setup.
91/100
humanbound
Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.
92/100
InvestSkill
US stock analysis skills for LLMs (Claude code, Gemini ...) | #AI
89/100
claude-delegator-deepseek-mcp
MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt
90/100
Aivory
Self-hosted AI chat platform with multi-step tool calls, persistent Python sandbox, RAG, and Deep Research. Supports Claude, GPT, Gemini and any OpenAI-compatib
99/100
tick-stock-panel
TSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源
87/100
pi-freeflow
🌊 23 free curated AI models (up to 1M context) for Oh My Pi & Pi. Thin provider + dumb relay pool to bypass rate limits.
90/100
teleton-agent
Teleton: Autonomous AI Agent for Telegram & TON Blockchain
98/100
atmosphere
Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human
90/100
agentic-fm
An open source project designed to assist AI in guided deterministic FileMaker code output.
90/100
Amharic-Tokenizer
Syllable-aware BPE tokenizer for the Amharic language (አማርኛ) – fast, accurate, trainable.
96/100
uAgents
A fast and lightweight framework for creating decentralized agents with ease.
88/100
contextspy
Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs
98/100
tiny-llm
learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
88/100
awesome-ai-built-games
A curated list of vibe-coded games: playable games built with AI coding agents like Claude Code, Cursor, Codex, Gemini and Grok, with Three.js, Phaser, Godot an
95/100
AgileRL
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimizat
88/100
llm_cost_tracker
Rails-native LLM cost ledger: track spend by provider, model, and feature with self-hosted storage and budget guardrails.
98/100
agent-of-empires
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilo
88/100
linktokenview-docs
LinkTokenView（联视未来）国产大模型 Token API 聚合平台，提供 OpenAI 兼容接口，统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型，支持 Token Plan 与 Coding Plan
98/100
openless
Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的