AI Developer Frameworks & Infrastructure
136 tools in this category.
L 
LangGraphAgent orchestration framework by LangChain for building stateful, controllable AI agents using graphs.
LA Lightning AICloud-based AI development platform by the PyTorch Lightning team—train and deploy right in your browser
Statewave為 AI 代理打造企業級記憶體管理與安全合規執行階段
OpenObserve高效經濟的開源可觀測性與 AI 監控平台
Laminar開源的 AI 代理與 LLM 應用可觀測性與評估平台
Powabase專為 AI 應用打造的全方位後端與 RAG 平台
Enkrypt AI全生命週期LLM安全平台與合規防護
TwelveLabsIntelligent Video Search
OxloDeveloper-First AI Inference Platform
OpenCodeOpen-source, model-agnostic AI coding agent for terminals, integrating 75+ model providers, supporting offline and enterprise-level deployment
ReplicateRun open-source AI models with one API call.
N n1n單一金鑰與端點，輕鬆串接多種語言模型
MotherDuck基於 DuckDB 的雲端資料倉庫，支援 AI 自然語言查詢與協作
Chunkr開源且支援自架的文件擷取 API，將 PDF 轉為具語意結構的 Markdown 區塊。
V Vijil企業 AI 代理的安全防護與信任評估平台
KernelCloud browser infrastructure for AI agents, with millisecond-level cold start, built-in anti-detection, and proxy, making it possible for agents to browse and interact with websites like humans.
Pydantic AIPython agent framework from Pydantic team, bringing FastAPI development feel to GenAI
MLflowOpen-source AI engineering platform for end-to-end tracking, evaluation, monitoring, and optimization of ML models, LLMs, and agents
LiteLLMOpen-source AI gateway to unify 100+ LLMs with cost tracking, load balancing, and logging
cubicAI-powered code review platform from Y Combinator, understanding complex logic across files and providing actionable insights
D DifyOpen-source LLM application development platform
PineconePopular vector database service
LangfuseOpen-source LLM application observability platform
DBHub讓AI透過統一介面高效查詢多資料庫的MCP伺服器
Activeloop專為多模態 AI 設計的現代化資料庫與管理平台
DoclingIBM開源的高效文件轉換工具，專為LLM與RAG打造
Aporia即時攔截 AI 幻覺與攻擊的防護欄引擎
CD Context.devExtract web data with ease using Context.dev, a powerful web scraping tool for developers and data scientists
OmnaraTake control of your AI agents on-the-go with Omnara, the mobile and web command center for Claude Code and other AI agents.
PromptfooOpen-source LLM evaluation and red team testing tool for comparing GPT, Claude, and Gemini performance with declarative settings, and vulnerability scanning for AI applications
BifrostA high-performance, open-source LLM gateway written in Go, boasting 50x faster speed than LiteLLM and microsecond-level latency at 5000 RPS
DaytonaA secure sandbox for running AI-generated code, with 90ms cold start and compatibility with Docker and OCI
LangWatchAI Agent Testing and Evaluation Observability Platform
Z ZeroEntropyAccurate RAG search with high-precision re-ranking and embedding models
CuaEmpowering AI with a true cloud computer. Cua offers Linux, Windows, and macOS sandbox desktops with an open-source SDK, enabling agents to interact like humans.
Kilo CodeOpen-source AI coding proxy, untethered from single models and editors, with transparent costs and flexible integration
QdrantHigh-performance open-source vector database.
WeaviateOpen-source vector database
RunPodAffordable cloud GPU platform
CerebrasDelivering ultra-fast AI inference with its own chip.
FalHigh-speed inference platform for generative media.
LangSmithThe observation and evaluation platform for LLM applications.
ModalCloud platform for running AI and compute workloads.
LangChainBuilding the development framework for LLM applications.
Fireworks AIHigh-speed open-source model inference platform
TA Together AICloud Inference and Fine-tuning Platform for Open-source Models
LlamaIndexLlamaIndex is ideal for building and managing large language model data indexes and query systems.
L LinkupA web search API for AI apps that adds production-grade real-time search in a single call.
P ParallelWeb infrastructure APIs that let AI agents search, extract, monitor and research the live web with citations.
Opik開源的 LLM 可觀測性與評估平台
Guardrails AI為LLM應用打造安全的輸入輸出防護網
Nota AINota AI: Optimizing Deep Learning Models for Edge Devices
CoalesceEmpowering Cloud Data Warehouses with AI-Driven Data Transformation and Modeling
KeployAutomate API testing and mocking with real traffic
TrueFoundryUnified Platform for Governing, Deploying, Scaling, and Tracking Agentic AI Workloads
SteelOpen-source browser API for large-scale cloud management, providing a REST/WebSocket service for AI agents and web crawlers
RAGFlowOpen-source RAG engine, strong in 'deep file understanding', transforming PDFs, tables, images, and more into high-quality semantic fragments for enhanced search and retrieval
KiroAWS's spec-driven development tool that brings AI programming back to disciplined engineering
DyadOpen-source, local-first AI app builder, giving you full code ownership and flexibility
C CoderOpen-source, self-hosted cloud development environment platform that turns infrastructure into code with Terraform templates, deployable on AWS, GCP, Azure, Kubernetes, and bare metal, with governed w
OnaEvolve your cloud development environment into a command center for software engineering agents with Ona, the rebranded Gitpod
VoltAgentOpen-source TypeScript AI agent framework with built-in memory, RAG, fencing, tools, MCP, voice, and workflow engine, supporting supervisor and sub-agent scheduling
S SiliconFlowOne API to access 200+ open-source and commercial models, with serverless inference, model fine-tuning, and dedicated GPU deployment
TrieveOpen-source, self-hostable, all-in-one search API. Trieve integrates search, RAG, recommendation, and analysis into a single API, enabling you to add accurate and fast semantic search and retrieval ca
B BytebotOpen-source, self-hosted AI desktop agent
LightrunAI-powered SRE platform for dynamic debugging and telemetry in production environments without restarts or redeployments
Korbit AIAutomate your PR review process with Korbit AI, your team's new 24/7 review robot that catches bugs, writes summaries, and provides actionable modification suggestions.
ZillizThe Cloud-Native Vector Database Behind Milvus
HaystackBuilding Open-Source Frameworks for LLM Applications
ChromaAn open-source, embedded vector database for AI applications.
PortkeyAI Gateway and Management Platform for LLM Applications
BraintrustAI Application Evaluation and Experimentation Platform
HeliconeOpen-source platform for LLM monitoring and analysis.
H HumanloopLLM Evaluation and Prompt Management Platform
VellumBuild, test, and deploy LLM applications with ease.
OpenHandsOpen-source AI software engineering agent.
BasetenA platform for deploying and serving AI models.
M MixpeekA multimodal retrieval platform to search video, image, audio and document libraries by meaning.
myDBAAI 驅動的 PostgreSQL 智慧監控與效能診斷工具
NeuBird自主式 AI SRE 助理，自動診斷生產環境異常
A Acceldata企業級AI資料可觀測性平台
Ragas開源的 RAG 系統自動化評估與測試工具庫
Giskard開源的 LLM 測試與安全防護庫
HumalikeHumalike is a tool that provides behavioral infrastructure API and models for AI agents to learn social intelligence, enabling better human-AI interaction and communication.
LocofyTransform Designs into Frontend Code with AI
DatatureTrain and deploy computer vision models without coding
MetoroKubernetes-dedicated AI SRE platform with eBPF zero-instrumentation observability
AB Anchor BrowserCloud-based browser automation infrastructure for agentic AI, enabling agents to browse like humans with built-in anti-detection and CAPTCHA solving
HyperbrowserCloud-based browser infrastructure built for AI agents, with simultaneous support for thousands of isolated sessions and a HyperAgent framework that understands natural language commands.
Vibe KanbanOrchestrate multiple AI coding agents with a Kanban board, streamlining task planning, parallel execution, and visual code review.
UpstageEmpowering enterprises with AI-driven document intelligence and large language models
NorthflankOne-stop deployment platform for applications, databases, AI models, and scheduled tasks with GPU support and multi-cloud capabilities
AgentOpsThe observability platform built for AI agents, supporting over 400 frameworks and models, including OpenAI, CrewAI, and Autogen, with a focus on time-travel debugging
BaseRock AIAgent-based QA platform that tests with real business scenarios, automatically verifying business logic and uncovering hidden errors
DiffblueEnterprise-grade Java unit testing agent from the University of Oxford, using reinforcement learning to write and maintain tests at scale.
SambaNovaAccelerating AI Inference with Proprietary Chips
FastGPTOpen-source knowledge base Q&A and workflow platform
LanceDBAn open-source vector database built for AI.
LunaryOpen-source LLM monitoring and management platform.
LA Literal AIYour go-to platform for monitoring and evaluating LLM applications.
SieveDeveloper Platform for AI-powered Audio-Visual Processing
NomicEmbedded Model and Data Visualization Platform
HyperbolicAffordable AI Inference and GPU Platform
Patronus AIAI Evaluation and Protection Platform
DeepInfraAffordable Open-Source Model Inference API
AnyscaleScalable AI Computing and Deployment Platform
PredibaseThe platform for fine-tuning and serving open-source models.
OpenPipeThe platform for fine-tuning and optimizing models.
AA Athina AILLM Evaluation and Monitoring Platform
PromptLayerStreamline Prompt Management and Monitoring
P pganalyzePostgreSQL 專用智慧監控與 AI 效能最佳化平台
RaindropAI 代理的專屬監控平台，自動揪出無聲錯誤
SherlocksAI SRE 平台自動串聯監控訊號進行根因分析
P Prophecy結合AI與視覺化的低程式碼資料工程平台
Osaurus專為 macOS 打造的開源離線 AI 代理執行環境
DeepEval開源大型語言模型評估框架，實現自動化單元測試
VA VESSL AIStreamline AI Model Deployment Across Clouds
CiroosAI-Driven SRE Platform for Accelerated Incident Resolution Across Domains
KodusOpen-source, model-agnostic AI code review agent that integrates with GitHub, GitLab, and Bitbucket, learning your team's rules and offering transparent, cost-effective solutions
KitOpsOpen-source AI/ML packaging and version control tool, creating signed OCI standard artifacts for seamless container repository management
BlaxelThe perpetual sandbox platform for AI agents, with zero compute costs when idle and 25ms wake-up time
AgentaOpen-source LLM application development platform that streamlines prompt management, evaluation, observability, and collaboration in one interface
Truffle AIThe AWS of AI agents, making it easy to deploy and integrate AI into your applications
Coral ProtocolCross-framework multi-agent infrastructure for secure collaboration
Panto AIUnifying dynamic code review, security scanning, and mobile App QA automation into a single, proactive quality platform.
I InferlessServerless Model Deployment Platform
L LaminiEnterprise-level LLM fine-tuning and deployment platform
TruLens開源的LLM與RAG應用評估追蹤工具
Fiddler AI生產環境中的 AI 可觀測性與監控平台
D Datalab高精準度的 PDF 與圖片轉 Markdown API
Repello AI自動化AI紅隊演練與執行期防禦平台
FriendliAIUnlock Efficient AI Deployment with FriendliAI, a High-Performance Inference Platform
ZMLZML is a software that can run large language models on various hardware platforms, breaking vendor lock-in and increasing autonomy and flexibility.
RuntimeAIThe control plane for autonomous AI agents, emphasizing security, governance, and compliance, with features like runtime logging, human oversight, and risk management to help enterprises meet EU AI Ac
TensorZeroThe open-source LLMOps platform that integrates gateway, observability, evaluation, and automated model and prompt optimization loop, enabling your AI applications to continuously learn from real-worl
BA Blocks.aiThe network layer for AI agents, enabling them to run anywhere and be called globally