Drydock.si
Submit a tool

AGENTS · INFRA · SHIPYARD

Where AI agents ship.

Everything you need to build, test and launch AI agents (frameworks, orchestration, vector stores, inference, coding agents and protocols) with live GitHub stats and launch feed.

Tools indexed
82
GitHub stars
3.5M
Categories
6
Open source
50
Free to start
73
Feed items
43
LIVE

// guides

Latest guides

All guides →
Screenshots of Cursor, Claude Code, OpenAI Codex, GitHub CopilotHow toHow to · Nov 20, 2026 · 8 min readCursor Plugins: Install, Build, and Plugin vs MCPCursor plugins bundle rules, skills, agents, commands, hooks and MCP servers into one install. How to add them, build and validate your own, and when MCP is enough.Read the guide →ListenExplainers · Nov 19, 2026 · 9 min readSuperpowers for Claude Code: Setup, Skills, CostSuperpowers for Claude Code is a free skills plugin that makes the agent brainstorm, plan, test first and review. How to install it, what it does and its token cost.Read the guide →ListenScreenshots of Claude Code, CursorComparisonsComparisons · Nov 14, 2026 · 8 min readClaude Code vs Cursor: Which Fits Your Workflow?Claude Code vs Cursor in November 2026: agent loop, editor, models, cloud agents, pricing and privacy compared, plus how to run Claude Code inside Cursor.Read the guide →ListenScreenshots of Claude Code, OpenAI Codex, Cursor, OpenCodeComparisonsComparisons · Nov 14, 2026 · 8 min readBlender MCP: Official Lab Server vs MCP for BlenderBlender MCP now means two servers, the official Blender Lab one and the community MCP for Blender. What each does, how to set it up, and the port clash to avoid.Read the guide →ListenScreenshots of Claude Code, OpenAI Codex, CursorBest ofBest of · Nov 14, 2026 · 8 min readBest AI Coding Agents in 2026: Our PicksThe best AI coding agents in November 2026, from Claude Code and Codex to Cursor, Copilot and open source picks, with prices, limits and who each one suits.Read the guide →ListenFree MCP Server for Web Search: 7 Tested PicksHow toHow to · Nov 13, 2026 · 10 min readFree MCP Server for Web Search: 7 Tested PicksThe best free MCP server for web search in 2026 is Exa's hosted endpoint, with SearXNG MCP for self hosting. We tested 7 options and their real free limits.Read the guide →ListenScreenshots of Chrome DevTools MCPHow toHow to · Nov 13, 2026 · 8 min readChrome DevTools MCP: Setup, Tools and 1.13 MocksHow to set up Chrome DevTools MCP in Claude Code, Codex, Cursor or Gemini CLI, what its 33 default tools do, the new 1.13 logpoints and mocks, and safe flags.Read the guide →ListenBuild an MCP Server to Manage Cisco DevicesTutorialsTutorials · Nov 13, 2026 · 9 min readBuild an MCP Server to Manage Cisco DevicesHow to build an MCP server to manage Cisco devices in Python with Netmiko: read only show tools, a guarded config tool, and when Cisco's own servers fit better.Read the guide →ListenExplainers · Nov 12, 2026 · 8 min readQwen Code 1.0: What Changed and Should You Switch?Qwen Code 1.0 Preview explained: the new native installer, Qoder harness, provider config and permission modes, what it lacks so far, and who should stay on 0.27.Read the guide →Listen

// start here

Guides by topic

// field guide

The agent shipyard: from prototype to production

A drydock is where ships are built, repaired and made seaworthy before they launch. Building AI agents feels much the same. A demo that works once in a notebook is a long way from an agent that runs reliably for thousands of users, and the gap is filled by infrastructure: frameworks that structure the reasoning loop, orchestration that survives failures, memory and retrieval, fast inference, sandboxes for running code, and protocols that connect agents to the tools they need. Drydock is a directory of that infrastructure, written for engineers who ship.

Most projects start with an agent framework. LangChain and LangGraph offer the broadest integrations and fine grained graph control; LlamaIndex excels when your agent works over documents; CrewAI and AutoGen focus on teams of collaborating agents; the OpenAI Agents SDK, Pydantic AI and smolagents keep things lightweight; and Mastra and the Vercel AI SDK serve TypeScript teams. If you prefer visual building, Dify, Flowise, Langflow and n8n let you wire agents together on a canvas. For long running work, durable execution engines like Temporal and Trigger.dev make sure a crash halfway through does not mean starting over.

Agents need memory and models. Vector databases (Pinecone, Weaviate, Qdrant, Chroma, Milvus, pgvector and LanceDB) store embeddings for retrieval and recall, and memory layers like Mem0 and Letta manage what an agent remembers about users across sessions. On the inference side, vLLM and SGLang serve open models at high throughput, Ollama and LM Studio run them locally, LiteLLM and OpenRouter put many providers behind one API, and platforms like Together, Fireworks, Groq, Modal, Replicate and Baseten handle scaling for you.

Coding agents are where many developers meet agents first. Claude Code, Codex, Gemini CLI, Aider and Cline operate on real repositories; Cursor, Copilot and Zed bring agents into the editor; Replit and Lovable build whole apps from a prompt. Underneath it all, the Model Context Protocol is becoming the standard way to plug tools into agents, while E2B, Browserbase, Firecrawl, Exa and Tavily provide sandboxes, browsers, web data and search. Every listing shows live GitHub stars where the project is open source, and the feed below tracks new agent repos, papers and launches.

// at a glance

The Drydock signal

What is rising, where the stars are, and what just landed.

Pricing mix

  • Open source50
  • Source available2
  • Freemium23
  • Paid7

Fresh from the feed

    Open the live feed →

    Sources

    4 public sources

    Hacker News, arXiv, HF Daily Papers, GitHub. Every star count, link and paper points to its original source.

    Newest listing: Chrome DevTools MCP

    // this week · week 47

    This week in numbers

    All weekly reports →
    Firecrawl adds 2,340 GitHub stars to lead the weekFirecrawl added 2,340 GitHub stars between Nov 9 and Nov 16, the biggest gain among the 66 open source tools tracked on Drydock.Read the week 47 report →
    • +2,340GitHub stars for Firecrawl
    • 1036points on the week's top HN story
    • 10notable new papers

    // fresh

    New this week on GitHub

    // index

    The directory

    82 of 82 tools

    Ollamaollama.comThe simplest way to download and run open models locally, with a CLI, desktop app and local API.Inference & HostingOpen source★ 187.8kLiteLLMlitellm.aiPython SDK and proxy gateway that calls many LLM providers through one OpenAI style interface with budgets and logging.Inference & HostingOpen source★ 63.7kFirecrawlfirecrawl.devTurns websites into clean, LLM ready markdown or structured data via API, with crawling and search.Dev Tools & ProtocolsOpen source★ 205.9kAgnoagno.comPython framework and runtime for multiagent systems with memory, knowledge and tools.Agent FrameworksOpen source★ 43.3kLlamaIndexllamaindex.aiFramework for building agents over your data, strong on ingestion, indexing, retrieval and document workflows.Agent FrameworksOpen source★ 53kTemporaltemporal.ioDurable execution platform that keeps long running workflows and agent loops reliable through crashes and retries.Orchestration & WorkflowsOpen source★ 24.5kZedzed.devHigh performance code editor written in Rust with built in collaboration and an agent panel.Coding AgentsOpen source★ 95.5kOpenCodeopencode.aiMIT licensed, model agnostic coding agent with a terminal UI, desktop app and web client that share one local background service; supports MCP, skills and plugins.Coding AgentsOpen source★ 228.4kChromatrychroma.comDeveloper friendly open source embedding database that runs embedded, as a server or in Chroma Cloud.Vector DatabasesOpen source★ 29.7kn8nn8n.ioFair code workflow automation platform with a visual editor, AI agent nodes and hundreds of integrations.Orchestration & WorkflowsSource available★ 211.6kTrigger.devtrigger.devOpen source platform for long running background tasks and AI agents in TypeScript.Orchestration & WorkflowsOpen source★ 16.8kBrowserbasebrowserbase.comHeadless browser infrastructure for AI agents, plus the open source Stagehand automation framework.Dev Tools & ProtocolsFreemium★ 26.1kWeaviateweaviate.ioWeaviate is an open source vector database in Go with hybrid BM25 plus vector search, per user tenants, vectorizer modules and a built in MCP server.Vector DatabasesOpen source★ 17kBasetenbaseten.coProduction inference platform for deploying open and custom models with dedicated, autoscaling GPUs.Inference & HostingPaid★ 1.2kQdrantqdrant.techQdrant is an open source vector database in Rust (Apache 2.0) with payload filtering, BM25 plus dense hybrid search and an official MCP server.Vector DatabasesOpen source★ 35.7kBrowser Usebrowser-use.comOpen source Python library and cloud platform that lets an LLM plan and drive a real browser for open ended web tasks, with CLI and MCP options.Dev Tools & ProtocolsFreemium★ 121.7kLanceDBlancedb.comEmbedded, multimodal vector database built on the Lance columnar format.Vector DatabasesOpen source★ 12kOpenRouteropenrouter.aiUnified API to hundreds of models from many providers with automatic fallbacks and price routing.Inference & HostingFreemiumHN 31agent browseragent-browser.devVercel Labs' Rust command line browser for AI agents: compact accessibility snapshots with element refs, a background Chrome daemon, an MCP mode and opt in guardrails.Dev Tools & ProtocolsOpen source★ 53.2kDSPydspy.aiFramework for programming rather than prompting LLMs, with optimisers that tune prompts and weights automatically.Agent FrameworksOpen source★ 39.2kComposiocomposio.devIntegration platform that gives agents authenticated access to hundreds of apps and tools.Dev Tools & ProtocolsFreemium★ 31.2kMastramastra.aiTypeScript framework for agents, workflows, RAG and evals, built by the team behind Gatsby.Agent FrameworksOpen source★ 29.7kE2Be2b.devSecure cloud sandboxes for running AI generated code, powered by lightweight virtual machines.Dev Tools & ProtocolsOpen source★ 15kModalmodal.comServerless platform for running Python and GPU workloads, from inference endpoints to sandboxes, defined in code.Inference & HostingFreemiumHN 20Model Context Protocolmodelcontextprotocol.ioOpen protocol that standardises how applications provide tools and context to LLMs and agents.Dev Tools & ProtocolsOpen source★ 9.7kCursorcursor.comAI code editor with fast autocomplete, codebase aware chat and background agents.Coding AgentsFreemiumHN 19Difydify.aiSource available platform for building LLM apps and agentic workflows visually, with RAG and model management.Orchestration & WorkflowsSource available★ 161.6kLangflowlangflow.orgVisual, Python based builder for agents and RAG flows that can be exported as APIs or MCP servers.Orchestration & WorkflowsOpen source★ 156.8kClaude Codeclaude.comAnthropic's agentic coding tool that works in your terminal and IDE to edit files, run commands and ship changes.Coding AgentsPaid★ 156.5kLangChainlangchain.comWidely used framework for building LLM applications and agents, with hundreds of model, tool and data integrations.Agent FrameworksOpen source★ 150kOpenAI Codexopenai.comOpenAI's coding agent available as an open source CLI, IDE extension and cloud agent that runs tasks in parallel.Coding AgentsPaid★ 136kZepgetzep.comManaged memory and context platform for agents that turns chats and business data into a temporal knowledge graph, built on the open source Graphiti engine.Vector DatabasesFreemium★ 5kGemini CLIgithub.comGoogle's open source terminal agent that brings Gemini models to the command line with MCP support.Coding AgentsOpen source★ 109kvLLMdocs.vllm.aiHigh throughput LLM serving engine built around PagedAttention, with an OpenAI compatible server.Inference & HostingOpen source★ 97.3kClinecline.botOpen source autonomous coding agent for VS Code that plans, edits files and runs commands with your approval.Coding AgentsOpen source★ 71.8kMem0mem0.aiMemory layer for AI agents that extracts and recalls user facts across sessions.Vector DatabasesOpen source★ 69.3kAutoGenmicrosoft.github.ioMicrosoft Research framework for multiagent systems where agents converse to solve tasks. Archived since October 2026; Microsoft points new projects to Microsoft Agent Framework.Agent FrameworksOpen source★ 62kCrewAIcrewai.comPython framework for orchestrating role playing teams of agents that collaborate on tasks, plus an enterprise platform.Agent FrameworksOpen source★ 61.1kChrome DevTools MCPgithub.comGoogle's Apache 2.0 MCP server and CLI that let a coding agent drive and inspect a live Chrome tab: console, network, performance traces, snapshots and network mocks.Dev Tools & ProtocolsOpen source★ 58.6kMilvusmilvus.ioCloud native vector database designed for billion scale similarity search, with a managed Zilliz service.Vector DatabasesOpen source★ 46.7kLangGraphlangchain.comLow level orchestration library for stateful, long running agents modelled as graphs, with persistence and human in the loop.Agent FrameworksOpen source★ 45.2kLovablelovable.devBuilds full stack web apps from a chat conversation, with GitHub sync and backend integrations.Coding AgentsFreemiumHN 13Playwright MCPplaywright.devMicrosoft's Model Context Protocol server that exposes Playwright browser tools to MCP clients using structured accessibility snapshots, not screenshots.Dev Tools & ProtocolsOpen source★ 40kGraphitihelp.getzep.comOpen source Python library from Zep for building temporal knowledge graphs that track when facts change, backed by Neo4j, FalkorDB or Amazon Neptune.Vector DatabasesOpen source★ 33kQwen Codegithub.comApache 2.0 terminal coding agent from Alibaba's Qwen team that works with Qwen, Qoder and other providers; the 1.0 Preview adds a native installer and permission modes.Coding AgentsOpen source★ 30.8kOpenAI Agents SDKopenai.github.ioLightweight framework for multiagent workflows with handoffs, guardrails and built in tracing.Agent FrameworksOpen source★ 30.8ksmolagentshuggingface.coHugging Face's minimal library for agents that think in code, working with any model.Agent FrameworksOpen source★ 30.5kSemantic Kernellearn.microsoft.comMicrosoft's model agnostic SDK for integrating LLMs and agents into C#, Python and Java applications.Agent FrameworksOpen source★ 28.8kVercel AI SDKai-sdk.devVercel AI SDK: a free, open source TypeScript toolkit with one API for many model providers, streaming chat hooks and the ToolLoopAgent class.Agent FrameworksOpen source★ 28.1kHaystackhaystack.deepset.aiOpen source orchestration framework from deepset for production grade RAG pipelines and agents.Agent FrameworksOpen source★ 27.1kStagehanddocs.stagehand.devAI browser SDK from Browserbase with act, extract and observe primitives plus Playwright style page APIs, across TypeScript, Python and Go.Dev Tools & ProtocolsOpen source★ 26.1kpgvectorgithub.comPostgres extension for vector similarity search, letting you keep embeddings next to relational data.Vector DatabasesOpen source★ 23.8kAgent Development Kitadk.devGoogle's open source framework for developing, evaluating and deploying multiagent systems.Agent FrameworksOpen source★ 22.3kNVIDIA OpenShelldocs.nvidia.comSelf hosted runtime from NVIDIA that runs AI agents in sandboxes with YAML policies for files, per binary network access and credentials, plus a policy prover.Dev Tools & ProtocolsOpen source★ 21.9kPydantic AIpydantic.devAgent framework from the Pydantic team that brings type safety and structured outputs to LLM apps.Agent FrameworksOpen source★ 21.3kPlaywright CLIplaywright.devMicrosoft's Playwright command line tool for coding agents: shell commands with skills, named browser sessions, a live dashboard and Playwright code echoed for each action.Dev Tools & ProtocolsOpen source★ 15.4kFlowiseflowiseai.comDrag and drop builder for LLM flows and agents that can be self hosted or used in the cloud.Orchestration & WorkflowsOpen source★ 55.6kAideraider.chatTerminal pair programmer that edits code in your local git repo and commits changes with sensible messages.Coding AgentsOpen source★ 50.2kReplicatereplicate.comRun and deploy open models through a simple API, packaging custom models with Cog.Inference & HostingPaid★ 9.5kHA MCPhomeassistant-ai.github.ioCommunity MCP server for Home Assistant that lets AI clients control devices and also create and debug automations, scripts, dashboards and helpers, with a read only mode.Dev Tools & ProtocolsOpen source★ 8kLettaletta.comPlatform for stateful agents with long term memory, evolved from the MemGPT research project.Agent FrameworksOpen source★ 25.5kTogether AItogether.aiCloud for running, fine tuning and training open models, plus on demand GPU clusters.Inference & HostingPaidHN 8Docker Agentdocs.docker.comDocker's open source runtime, formerly cagent, that runs AI agents and multiagent teams defined in YAML or HCL, with MCP tools, sandboxing and registry sharing.Agent FrameworksOpen source★ 4.7kVoltAgentvoltagent.devOpen source TypeScript agent framework with memory, workflows, tools and MCP support, paired with the optional VoltOps console for tracing and deployment.Agent FrameworksOpen source★ 11kFireworks AIfireworks.aiFireworks AI serves open models through OpenAI and Anthropic compatible APIs, billed per token on serverless or per GPU second on dedicated deployments.Inference & HostingPaidHN 6Replitreplit.comCloud development platform whose agent builds and deploys full apps from natural language prompts.Coding AgentsFreemiumHN 6Daytonadaytona.ioCloud sandboxes for AI generated code: fast Linux containers by default, plus Linux VM, Windows, GPU and macOS options, with SDKs in five languages.Dev Tools & ProtocolsFreemiumHN 3Exaexa.aiSearch engine and API built for AI, returning web results and page contents via embeddings based search.Dev Tools & ProtocolsFreemiumHN 3turbopufferturbopuffer.comServerless vector and full text search built on object storage for low cost search at large scale.Vector DatabasesPaidHN 3Caprockcaprock.devFree open source desktop app that runs Claude Code, Codex, OpenCode, Gemini CLI and related agents side by side on your machine, shows plan limits and API list price cost per pull request, and lets you answer approvals from your phone.Coding AgentsFreemium★ 50Context Nestpromptowl.aiGoverned Markdown vault for AI agents: typed nodes, selector queries, hash chained versions and an optional review gate, reached over MCP or a CLI. Open core under AGPL 3.0.Dev Tools & ProtocolsFreemium★ 22Kaesokaeso.appMIT licensed AI gateway you host yourself, written in Rust, that gives apps one OpenAI and Anthropic compatible API across providers with single sign on, roles, budgets and request logs.Dev Tools & ProtocolsOpen source★ 19Tokenriptokenrip.comShared workspace where agents from Claude, ChatGPT, Codex, Cursor and any MCP app post files, tasks and decisions, and actions that need a yes wait for your approval.Dev Tools & ProtocolsFreemium★ 6Cloudbrowsercloudbrowser.tvPersistent cloud Chrome for AI agents: isolated browsers with saved profiles, a CDP URL for Playwright and similar tools, live view, and pause, resume and fork.Dev Tools & ProtocolsFreemiumHN 1Pineconepinecone.ioFully managed serverless vector database for similarity search at scale.Vector DatabasesFreemiumHN 1Lizardlizard.buildHosted Firecracker microVMs for AI agents: TypeScript and Python SDKs, pause with memory, snapshots, preview URLs and Persistent Volumes.Dev Tools & ProtocolsFreemium★ 3Sandbox0sandbox0.aiManaged agent sandboxes that keep the whole writable RootFS across pause and resume, with compute billed by the second and no compute charge while paused.Dev Tools & ProtocolsFreemium★ 2Kitekite.newDesign canvas where people and AI agents such as Claude, Cursor and Codex edit the same screens through a hosted MCP server, using your design system's variables and components.Dev Tools & ProtocolsFreemium★ 0GitHub Copilotgithub.comGitHub's AI pair programmer with completions, chat and a coding agent that works on issues and opens PRs.Coding AgentsFreemiumGroqgroq.comInference API running on custom LPU chips, known for very fast token generation.Inference & HostingFreemiumTavilytavily.comWeb search and extraction API tuned for agents and RAG workflows.Dev Tools & ProtocolsFreemiumVolaneavolanea.comEmail API for transactional mail, campaigns and agent inboxes, sent over Amazon SES, with an MCP server so a coding agent can set up the integration.Dev Tools & ProtocolsFreemium

    // taxonomy

    Categories

    // live feed

    Research & news feed

    Sources: Hacker News, arXiv, HF Daily Papers, GitHub

      // submit

      Submit a tool

      Know a tool that belongs in Drydock? Send it in. Every submission is reviewed by a human; listings are never sold.

      // newsletter

      Get The .si AI Tools Weekly

      A short weekly digest, every Monday: the best new tools and research in Agents, curated from the live feed above, plus top picks from our sister .si directories.

      Free, weekly, every Monday. Delivered by Beehiiv; you confirm by email. Unsubscribe any time. Privacy