Dify
The leading open-source LLM app development and agent orchestration platform with visual workflow canvas and RAG pipeline.
Coze 扣子
ByteDance’s next-gen AI bot development platform with an extensive plugin marketplace and visual workflow designer.
Ollama
The leading open-source command-line framework and lightweight runtime for packaging, downloading, and running local LLMs via REST API.
Hugging Face
The world leading open-source AI platform hosting millions of models, datasets, and Spaces web demo applications.
FastGPT
Open-source knowledge base Q&A platform and visual workflow agent orchestration studio powered by LLMs.
OpenRouter
Unified API gateway and model router for all major AI models with competitive pricing and fallbacks.
vLLM
Industrial-grade high-throughput, low-latency open-source LLM inference and serving engine powered by PagedAttention.
LangChain
The industry-standard open-source LLM application framework featuring LangGraph for robust multi-agent orchestration.
阿里百炼 (ModelStudio)
Alibaba Cloud all-in-one foundation model platform integrating Tongyi APIs, fine-tuning pipelines, and agent orchestration.
Mem0
The intelligent memory layer for AI agents that continuously learns user preferences across sessions.
LFM3 Omni 2B WebGPU
Liquid AI on-device multimodal Space executing 2B model weights inside your browser via WebGPU acceleration.
Aiproxy
Redact sensitive PII locally before prompts reach Claude or OpenAI APIs
Pushary
Realtime push notification and action approval infrastructure for autonomous AI agents.
QAnything (网易有道)
NetEase Youdao open-source two-stage retrieval RAG framework capable of slicing and reranking any document format.
Dex Semantics
Open source semantic layer enabling AI agents to query databases with 25% fewer errors.
LlamaIndex
The premier data framework for building context-augmented LLM applications and advanced RAG ingestion pipelines.
CrewAI
Cutting-edge multi-agent framework enabling role-playing autonomous AI agents to collaborate seamlessly and execute complex tasks.
Goethe
A lightweight infrastructure engine for self-hosted AI, orchestrating nodes, models, and resilient routes.
百度智能云千帆大模型平台
Baidu enterprise foundation model platform featuring proprietary ERNIE models, open weights, and end-to-end LLMOps.
Flowise
Open-source drag-and-drop UI tool designed to build customized LLM orchestration flows and LangChain agents.
AutoGen (Microsoft)
Microsoft premier open-source multi-agent conversation framework for orchestrating automated, collaborative LLM workflows.
Promptfoo
Open-source CLI and platform for LLM red teaming, prompt evaluation, and application security
Orderflow Claude Skill
Evidence-graded order-flow and market depth analysis skill for Claude parsing footprint charts without speculative noise.
Expo Simulators
Cloud simulators built for agents to programmatically run, inspect, and test mobile apps
MaxKB (飞致云)
Open-source enterprise LLM knowledge base Q&A system with seamless embedding into third-party business software.
Tanka
Next-generation communication and workflow platform built for AI-native teams.
Hardcount
Self-hosted LLM token metering and multi-tenant billing engine for granular AI cost control.
腾讯云知识引擎 LKE
Tencent Cloud enterprise-grade RAG and smart agent creation engine for knowledge bases and customer interaction.
Helicone
Open-source LLM observability platform and smart proxy for monitoring costs, latency, and intelligent caching with one line of code.
Modelpeers
Decentralized blind benchmarking and peer-review platform ranking language models across authentic workloads.
FounderMail
Email infrastructure for you and your AI agents hosted on your Cloudflare domain.
Groq
Ultra-fast LLM inference platform powered by custom LPU chips, delivering hundreds of tokens per second with minimal latency
UUMit
Expose local PC apps, developer tools, and AI agents as securely shared web endpoints
讯飞星火开放平台
iFlytek AI open platform offering Spark model APIs, custom assistant builders, and domain fine-tuning toolkits.
Modal
Python-native serverless cloud platform for running AI pipelines, batch workloads, and low-latency model APIs.
Fireworks AI
Production-ready platform for deploying and querying generative AI models with ultra-fast latency and compound AI architectures.
Fal.ai
Lightning-fast developer platform and serverless inference API for generative media models.
Replicate
Serverless cloud platform allowing developers to run, fine-tune, and deploy open-source AI models with a single line of code.
Cerebras Inference
Wafer-scale AI inference platform delivering unmatched generation speeds over 2,000 tokens per second
Claude Guardian
An all-in-one Claude account safety and risk prevention toolkit, evaluating device, network, and payment risks.
Omni2api
Convert any Python script, CLI tool, or agent into OpenAI-compatible API endpoints.
智谱 AI 开放平台
Zhipu AI developer platform providing GLM model APIs, fine-tuning, agent tools, and ultra-long context capabilities.
ApiClay
Discover, build, and sell APIs while connecting Claude, ChatGPT, and AI agents over MCP
TruLens
Open-source evaluation and tracking library for RAG applications, measuring context relevance, groundedness, and answer relevance.
ChainPoints
Visual canvas for constructing, debugging, and tracing production-grade LLM chains and prompt graphs.
Langflow
Dynamic visual framework for building multi-agent architectures and RAG pipelines with native Python execution.
MLflow
Open-source platform to manage the ML and LLM lifecycle, including tracking experiments, packaging code, and deploying models.
LangSmith
All-in-one developer platform for debugging, evaluating, testing, and monitoring LLM applications
Replicate
Premier serverless platform for open-source AI models, running and deploying machine learning with one line of code
Cohere
Enterprise AI platform offering Command R models and industry standard Rerank and Embed APIs
Repairer
Autonomous Linux security remediation agent closing zero-day vulnerability windows immediately upon disclosure.
RunPod
Developer-favorite cloud GPU rental and serverless AI deployment platform with global datacenter availability.
Together AI
The leading cloud platform for building and querying open-source AI, offering world-class inference speeds and fine-tuning.
Langfuse
Open-source LLM engineering platform for production tracing, evaluations, prompt management, and metrics to debug AI applications.
Weights & Biases (W&B)
The industry-standard AI developer platform for experiment tracking, hyperparameter optimization, and collaborative model management.
Arize AI
AI observability and LLM evaluation platform delivering tracing, automated evals, and troubleshooting for production agents and RAG.
Glif
Modular visual AI workflow platform where creators connect blocks to build shareable generative micro-apps and tools.
ForAgent
Private phone number infrastructure enabling autonomous AI agents to call each other natively.
Backlane
Dedicated eCommerce MCP server connecting Claude, ChatGPT, and Cursor to online marketplaces.
LanceDB
Open-source developer-friendly vector database built on the columnar Lance format for multimodal AI
Axiocairn MCP
Model Context Protocol server empowering AI agents with institutional portfolio risk analytics.
Ragas
Supercharged evaluation framework for RAG pipelines, providing automated test-case generation and multi-dimensional metrics.
Rainbrand
The brand layer for agents, maintaining visual identity and guidance via MCP.
Airgap Check
Security CLI probing whether local AI apps and coding agents silently make network calls when offline
Agent Buddies
Swappable animated character library bringing responsive avatar reactions to AI agent interfaces.
Lettercamp
Modern minimalist open-source static blog framework engineered for clean writing and fast builds.
Wipecraft
macOS system storage cleaner featuring on-device local AI intelligence to identify safe-to-delete files.
Ragie
The fully managed RAG platform built for software engineers to connect data to LLMs in minutes.
Dev Circuit Ultra
Design-first five-step loop for AI coding agents minimizing context bloat and ceremony
LiteLLM
Call 100+ LLMs in the standard OpenAI format with open-source load balancing and budget guardrails.
three.dev
Detect and fix AI agent failure modes automatically before your users hit them
Vast.ai
Decentralized peer-to-peer cloud compute platform offering extremely low-cost GPU instances for AI model training.
AwaitIO
Long-running asynchronous workflow orchestrator tailored for AI agents with state durability and retry self-healing.
BAML
Type-safe domain-specific language for AI prompt engineering and structured extraction with live previews
Portal2Bench
Rigorous 3D spatial reasoning benchmark testing autonomous multi-modal AI agents inside Portal physics puzzles.
AnythingLLM
All-in-one local AI workspace and multi-format document chat application with zero data leakage.
DeepInfra
Ultra-affordable serverless inference platform for popular open-source LLMs, embeddings, and generative image models.
Switchy
macOS menu bar utility unifying cloud deployments, 2FA tokens, and AI spending thresholds in one click.
OpenAI Platform API
Official OpenAI developer platform providing flagship GPT-4o, o1 reasoning models, Embeddings, and Assistants APIs.
Baseten
High-performance serverless AI infrastructure designed for low-latency LLM serving and custom model deployment.
Seldon Wren
Behavioral software QA agent running plain-English tests in parallel and uncovering missing cases
BentoML
The unified framework for building, shipping, and scaling production AI applications and fast model inference APIs.
TestSprite
Autonomous AI software testing agent that automatically creates end-to-end tests and pinpoints regressions.
Hyperbolic
Open-access decentralized AI compute network and cost-efficient open model inference platform
Priv Kit
Privileged process orchestration framework empowering Android apps via Root, ADB, or custom daemons.
Maritime
On-demand cloud computers and secure browser environments built for any AI agent.
Harness Tuner
Evaluation-driven autonomous tuning loop for agent tools, prompt templates, and routing
Portkey
Enterprise AI gateway and control plane offering smart fallback routing, load balancing, prompt guardrails, and unified telemetry.
SunsetLint
Automated scanner detecting deprecated and sunsetting AI model IDs across codebases.
Google AI Studio
Google official web-based prototyping studio for Gemini models, system instruction tuning, and API key management.
Outages.live
Free live outage feed merging official AI, cloud, and developer status pages with RSS, JSON API, and MCP
Omnigraph
Open-source graph database engineered for AI agent memory and multi-hop retrieval
Leetsys
Interactive system design mock interviews with an AI interviewer offering architect-level feedback.
Scale AI
The data foundry for AI, delivering high-quality data labeling, RLHF training, and robust model evaluation.
百度文心智能体平台 (灵境矩阵)
Baidu official developer agent platform offering low-code toolkits with seamless integration into Baidu Search and the Wenxin ecosystem.
Chroma
AI-native open-source embedding database designed for rapid prototyping and production RAG
Neon & Mubit
An intelligent agent gateway that prunes its own prompt tokens by 73% on frontier models
Apgar
Deterministic agent regression testing suite catching tool-calling defects without expensive LLM judges.
Pinecone
The industry-standard fully managed serverless vector database built for high-scale enterprise AI
Semantic Kernel (Microsoft)
Enterprise SDK by Microsoft integrating conventional programming languages like C#, Python, and Java with advanced AI capabilities.
Cloptima
AI Gateway, dynamic safety guardrails, and LLM FinOps cost governance platform.
Anyscale
Production platform for Ray, delivering scalable distributed computing for AI training, tuning, and serving.
Groq
Breakthrough AI inference engine powered by custom LPU chips delivering unmatched real-time token throughput.
Unstructured
The foundational open-source data preprocessing platform preparing enterprise files for LLMs and RAG.
E2B
Secure cloud sandboxes for AI agents and code interpreters with sub-second cold starts.
NoMac
Dedicated cloud macOS sandbox instances for AI agents, billed per minute without subscriptions
Tensward
High-performance local AI inference engine optimizing VRAM footprints and throughput.
Airlock
Policy-as-code guardrails, boundary enforcement, and cost visibility for fleets of AI coding agents
AgentOps
AI agent observability and benchmarking platform providing visual session replay, multi-agent tracking, and compliance evaluation.
Firecrawl
Turn any website into clean LLM-ready markdown or structured data with crawl, scrape, and extract APIs.
Weaviate
AI-native open-source vector database with built-in multimodal search and hybrid keyword-vector indexing
Attest Framework
End-to-end behavioral testing framework verifying what AI agents actually do
Anthropic Claude Console
Official Anthropic developer console providing Claude 3.5 Sonnet and Haiku APIs alongside interactive Workbench tools.
Qdrant
Production-ready vector database and semantic search engine written in Rust for high-scale AI RAG
PinPage
Open-source Windows utility transforming any web page or local HTML file into a desktop widget.
魔搭社区 (ModelScope)
The leading Chinese open-source Model-as-a-Service platform incubated by Alibaba DAMO Academy hosting thousands of models.
TFF dbt Fitness Functions
Automated architectural fitness function framework for dbt analytics engineering and data model governance.
Harness Leaderboard
Interactive leaderboard comparing coding-agent harnesses across models, stages, and reasoning effort
RagFlow
Open-source RAG engine and developer studio powered by deep document understanding for complex enterprise formats.
Voyage AI
State-of-the-art domain-specific embedding and reranker API engineered by Stanford researchers