Catalogue
Submit a toolHarnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
256 tools · showing 73–96
ToolShannon
Security
KeygraphHQ
Shannon is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and
penetration-testingred-teamvulnerability-scannerbrowser-automation
ToolStagehand
Interface
browserbase
Browser automation blending code with natural-language act, extract, and agent calls, plus action caching and self-healing
playwrightpuppeteerself-healingbrowser-automation
Frameworktldraw SDK
Interface
tldraw
React infinite-canvas SDK. Its Agent Starter Kit lets an agent read, interpret and edit canvas content.
canvaswhiteboardcollaborationdiagram
ToolVoltAgent
CodingInterfaceMonitoring
VoltAgent
TypeScript framework and console for building, observing, and operating AI agents
ragobservabilityorchestration
ToolArcjet
Security
arcjet
JS/TS security SDK: bot and AI-crawler detection, rate limiting, PII and prompt-injection checks for AI apps.
sdkprompt-injectionbot-detectiongateway
ToolBrigade
CodingMemoryConnectors
spinabot
Persisting chat logs does not make an agent learn. Hindsight is a self-hostable memory backend with explicit retain, rec
productivitymulti-agentshared-memorylocal-firstdelegation
ToolClowder AI
Interface
zts212653
Build AI teams, not just agents. Hard rails, soft power, shared mission.
multi-agenta2across-model-reviewshared-memory
ToolCorsair
Coding
corsairdev
Your Agent's Integration Layer
oauthapimulti-tenantwebhooks
HarnessLifeOS
MemoryCoding
danielmiessler
An AI-powered Life Operating System for Magnifying Human Capabilities.
productivityintent-engineeringgoal-trackingmemory-layerassistant
ToolMission Control
MonitoringCoding
builderz-labs
Self-hosted control plane to dispatch tasks, inspect runs, and track spend across agent runtimes
guilocal-firstmulti-agentsqlite
Tooln8n-MCP
Coding
czlonkowski
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
n8nmcp-serveragent-buildertemplates
ToolPlaywright MCP
Interface
microsoft
MCP server giving LLMs Playwright browser automation through structured accessibility snapshots rather than screenshots
accessibility-treeplaywrightbrowser-automationstructured-snapshots
ToolTambo
Interface
tambo-ai
Open-source generative UI toolkit for React where an agent selects your components and streams their props, with MCP support
generative-uistreamingzodstate-management
ToolWegent
CodingInterface
wecode-ai
An open-source AI-native operating system to define, organize, and run intelligent agent teams
productivitycoding-agentmulti-agenttask-managementremote-execution
ToolAgent Device
QAInterface
callstack
CLI to control iOS and Android devices for AI agents
mobile-automationiosandroidaccessibility-snapshot
ToolAgentConnect
ConnectorsCoding
agentconnect-md
Tag any agent, wherever work happens, your agents work alongside your team and each other, learning as they go.
multi-agentslacksandboxgithub
ToolBetterWright
InterfaceSecurity
BetterWright
A persistent, policy-guarded Playwright browser for AI agents — network policy, encrypted credential vault, proof screenshots, and CAPTCHA s
playwrightbrowser-automationcaptcha-solvingcredential-vault
ToolCc Haha
CodingInterfaceConnectors
NanmiCoder
本地优先的跨平台 Claude Code / Agent 桌面工作台：多 Agent、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、任务感知桌面宠物，并支持微信、飞书、钉钉、Telegram、WhatsApp 与 H5 访问。
desktopgit-worktreecomputer-usemulti-agent
ToolCindy
CodingInterface
makecindy
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。
productivitycomputer-uselocal-firstmulti-providerdesktop
ToolDeepSeek Harness
Coding
deepseek-ai
DeepSeek open-sourced its full agent harness built so every capability is a plugin. You can swap the loop, the sandbox,
plugindeepseekguisandbox
ToolLetta Code
MemoryConnectors
letta-ai
Letta Code versions agent memory with git … every self-edit is a commit, subagents work on isolated worktrees, conflicts
stateful-agentsmemgptgit-versioned-memorycontinual-learning
ToolMCP Inspector
Coding
modelcontextprotocol
Developer tool for testing and debugging MCP servers through a web UI and a transport-bridging proxy
debuggingguiproxycli
ToolOpenChamber
InterfaceCoding
openchamber
Desktop and web interface for OpenCode AI agent
productivitydesktopcoding-agentcode-reviewmobile
ToolOpenCodex
Coding
lidge-jun
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, an
proxygatewaycodexcli