100/100
bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS
Continuously updated
New developer tools
Browse the latest quality-filtered tools added to YunoDB from verified public project data.
Recently added
13476 tools
100/100
casdoor
An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML
100/100
DeepSeek-Reasonix
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
100/100
opencodex
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
100/100
superset
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
97/100
maxtext
A simple, performant, and scalable Jax LLM!
100/100
sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
91/100
goldenmatch
Zero-config entity resolution feeding a durable identity layer: messy records from any source become stable golden entities, a Customer 360 with provenance, mer
97/100
cindy
Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。
99/100
Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
90/100
agentdescent
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradie
98/100
KiroCrew
A persistent workspace for development work that self-improves and continues beyond one session.
96/100
connectonion
The Best AI Agent Framework for Agent Collaboration.
99/100
giskard-oss
🐢 Open-Source Evaluation & Testing library for LLM Agents
100/100
LightRAG
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
92/100
kairon
Agentic AI platform that harnesses Visual LLM Chaining to build proactive digital assistants
100/100
omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
100/100
ekko-studio
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
97/100
pinvou-agent
Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.
96/100
open-science
Open Science is an open-source, local-first, model-agnostic AI research workbench for scientific discovery.
98/100
Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separatio
100/100
seatunnel
SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.
100/100
jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
90/100
swarmauri-sdk
Modular Python SDK and monorepo for AI agents, LLM integrations, tools, parsers, embeddings, vector stores, and extensible application workflows.