Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

OpenClaw: Your Personal AI Assistant

OpenClaw is a personal AI assistant designed to automate tasks and interact with various applications and your local machine. It aims to streamline daily workflows by performing actions like managing emails, calendars, and flight check-ins directly through chat interfaces like WhatsApp, Telegram, and others. OpenClaw operates locally, offering flexibility with different AI models.

General
Release date2024
AuthorPeter Steinberger
Websitehttps://openclaw.ai/
Repositoryhttps://github.com/openclaw/openclaw
TypePersonal AI Assistant

Key Features of OpenClaw

  • Local Operation: Runs directly on your macOS, Windows, or Linux machine, keeping your data private.
  • Flexible AI Models: Supports various AI models including Anthropic, OpenAI, or local models.
  • Chat App Integration: Interact with OpenClaw through popular chat applications like WhatsApp, Telegram, Discord, Slack, Signal, and iMessage.
  • Persistent Memory: Learns and remembers your preferences and context over time to become a truly personalized assistant.
  • Browser and System Access: Capable of browsing the web, filling forms, extracting data, reading/writing files, and executing shell commands/scripts with optional sandboxed access.
  • Extensible with Skills & Plugins: Expand its capabilities with community-built skills, and it can even create new skills autonomously.
  • Proactive Task Management: Can perform scheduled tasks, set reminders, and manage background operations.

Start Building with OpenClaw

OpenClaw provides a powerful platform for personal automation and AI-driven task management. Its local-first approach combined with extensive integration capabilities makes it a versatile tool for enhancing productivity and privacy. Developers and users interested in leveraging autonomous AI agents can explore OpenClaw to build custom solutions or automate their daily digital lives.

While specific boilerplate or library examples are not yet widely available due to its nascent stage, the core functionality revolves around its API and integration points with chat applications and local system access.

OpenClaw Tutorials

OpenClaw Resources

Here are some valuable resources to help you get started with OpenClaw:

Edit on GitHub

Openclaw AI Technologies Hackathon projects

Discover innovative solutions crafted with Openclaw AI Technologies, developed by our community members during our engaging hackathons.

Agent Testnet: A Parallel Internet for AI Agents

Agent Testnet: A Parallel Internet for AI Agents

Agent Testnet is an open-source sandboxed parallel internet for AI agents: a self-contained world of fake services where agents can browse, interact, and break things - phishing, prompt injections, destructive tool calls - without touching the real web. The problem: AI Agents are non-deterministic, it is hard to trust them. So they have to be tested. But today even in tests they are pointed at the real internet - real Gmail, real GitHub, real money. There is no safe testing space. Every test can leak into production, every mistake is global, and exploits can only be observed once the damage is done. Our solution: Agent Testnet is an open-source sandboxed parallel internet for AI agents. Each agent runs inside a microVM whose only network path is a VPN tunnel to a control plane that owns DNS and routing. Declared domains - google.com, github.com, gmail.com - resolve to testnet nodes: fake clones or staging deployments the Agent Testnet community controls. From inside the VM it looks and feels like the real internet, and the agent does not know it is being tested. Everything outside the testnet is dropped: no leaks, no blast radius. Agents interact with each other through email, issues, and shared documents, so test complexity grows as more agents and services join. Three uses, one substrate. Safety testing - malicious agents, vulnerable agents, chaos through randomness without consequences. Behavioural research - reproducible, fully observed runs that capture failure modes and emergent multi-agent strategies. Service testing - point swarms of real agents at your staging deployment and watch how they actually use it. Open and extensible. The whole stack is AGPL-licensed and Go-based. A small testnet-toolkit wraps any existing open-source app into a testnet node in minutes. Every node or agent a contributor adds makes the testnet exponentially richer for everyone. We are building the testing environment for agents: the place you bring an agent before it ships.

Rex Intel Services

Rex Intel Services

RexIntel Services is a crypto + AI intelligence platform built for founders, builders, researchers, and operators who need high-signal information without digging through dozens of feeds. The project combines a public intelligence directory, weekly newsletter engine, contributor system, on-chain address attribution tools, exploit tracing, recovery bounties, and an operator dashboard into one self-hosted platform. The live product is positioned as “Crypto + AI intelligence for builders,” with one weekly briefing plus live boards that the community can contribute to. At the public layer, RexIntel gives users a clean field guide for accelerators, fellowships, grants, VC capital, perks, residencies, hackathons, events, jobs, and pop-up cities. The landing page frames the brand as a crypto intelligence division that “stays deep in the trenches” so users do not have to, then routes users into Intel Wire, Field Calendar, Hackathons, Capital, Grants, Accelerators, Residencies, Pop-Up Cities, Jobs, and Perks. The core intelligence product is the /intel surface. It supports multiple lanes, including signals, accelerators, fellowships, grants, capital, perks, cities, and residencies. Individual intel records can be tips, originals, or incidents. Tips are lower-bar community sightings, originals are RexIntel-authored reporting or analysis, and incidents are confirmed exploits or failures supported by public or on-chain evidence. This taxonomy matters because the weekly digest has an editorial quality bar: it will not draft unless there is at least one original or incident unless the operator explicitly bypasses that rule. RexIntel also goes beyond a normal newsletter or directory. It includes an address graph, per-address attribution pages, an Etherscan-powered victim trace tool, and a recovery bounty board. The trace feature performs a three-hop outbound search across Ethereum activity and can create shareable trace result pages for white-hat investigators.

Agent Testnet: A Parallel Internet for AI Agents

Agent Testnet: A Parallel Internet for AI Agents

The problem. Today's AI agents are pointed at the real internet - real Gmail, real GitHub, real money. There is no testing space. Every test runs in production, every mistake is permanent, and exploits like prompt injection can only be observed once the data is already gone. Our solution. Agent Testnet is an open-source sandboxed parallel internet for AI agents. Each agent runs inside a microVM whose only network path is a VPN tunnel to a control plane that owns DNS and routing. Declared domains - google.com, github.com, gmail.com - resolve to testnet nodes: fake clones or staging deployments we control. From inside the VM it looks and feels like the real internet, and the agent does not know it is being tested. Everything outside the testnet is dropped: no leaks, no blast radius. Agents share one environment and interact with each other through email, issues, and shared documents, so test complexity grows organically as more agents and services join. Three uses, one substrate. Safety testing - phishing pages, prompt-injection payloads, and destructive tool calls without consequences. Behavioral research - reproducible, fully observed runs that capture failure modes and emergent multi-agent strategies. Service testing - point swarms of real agents at your staging deployment and watch how they actually use it. Open and extensible. The whole stack is MIT-licensed and Go-based. A small testnet-toolkit wraps any existing open-source app - Gitea-as-GitHub, DokuWiki-as-Wikipedia, a mail server, a search engine - into a testnet node in minutes. Every node a contributor adds makes the testnet richer for everyone. We are building the testing layer for agents: the place you bring an agent before it ships.

GuardForge

GuardForge

Here's a clear, detailed explanation of GuardForge (1987 characters): GuardForge is an enterprise-grade AI Agent Security and Governance Platform. It helps companies safely deploy and manage multiple AI agents for real business tasks. The Problem Companies want to use AI agents to automate work like contract review, document analysis, compliance checking, and report generation. However, AI agents can hallucinate, leak sensitive data, break company policies, or make risky decisions. This creates fear and slows down AI adoption in enterprises. What GuardForge Does GuardForge acts as a smart control layer between users and AI agents. It adds safety, visibility, and control so agents can be used confidently in serious environments. Core Features Multi-Agent System: Multiple specialized agents (Researcher, Analyzer, Compliance Checker, Reporter) work together using LangGraph. Guardrails: Input & output checks to block PII, harmful content, prompt injections, and policy violations. Human-in-the-Loop: High-risk actions pause for human approval. Real-time Monitoring: Live dashboard showing agent activity, status, and performance. Trace Explorer: Step-by-step visual view of every agent’s thinking and actions. Immutable Audit Trail: Complete, tamper-proof logging of all activities. AI Policy Generator: Upload a document and AI auto-creates policies. Digital Twin Simulation: Test workflows safely before running them live. Billing System: Usage-based plans with Razorpay/Stripe integration. Real Use Cases Banks: Safely review loan documents and contracts. Legal Teams: Analyze agreements with full compliance. Healthcare: Process reports while protecting patient data. Enterprises: Automate internal operations with proper governance. Technology Stack Frontend: React 18, Vite, TypeScript, Tailwind CSS, ReactFlow (for visual workflows), Recharts, WebSockets. Backend: FastAPI (Python), SQLAlchemy, PostgreSQL, Redis.

ACMI: The Universal Memory Layer for AI Agents

ACMI: The Universal Memory Layer for AI Agents

ACMI + Lobster Trap is the enterprise security stack for multi-agent systems. Lobster Trap inspects prompts at the LLM boundary — declared vs detected intent, risk scoring, policy enforcement across ALLOW/DENY/LOG/HUMAN_REVIEW/QUARANTINE/RATE_LIMIT. ACMI records what agents did after — three keys per entity (Profile, Signals, Timeline), append-only, ZSET-backed on Redis. Together: prompt-level safety + execution-level audit + cross-framework coordination. For TechEx, LangChain, CrewAI, and a Gemini-powered synthesizer (gemini-2.5-flash-latest via Google AI Studio) coordinate through one timeline. None import each other. Every prompt passes through Lobster Trap first. Every response lands on the timeline. The governance dashboard at acmi-product.vercel.app/governance-dashboard.html renders the full chain — prompt → LT inspection → policy decision → LLM call → audit event — in real time. Receipts: - npm @madezmedia/acmi v1.2.0 LIVE (43+ day-one downloads) - npm @madezmedia/acmi-mcp v1.3.0 — 16 MCP tools, Smithery 83/100 - OAuth 2.1 + PKCE MCP shipped 2026-05-08, sub-100ms cold start - 9 production agents, 30+ days continuous, 1,603 events / 24h - 14+ merged PRs in last week including Lobster Trap (PR #27) + Gemini (PR #28) + governance dashboard (PR #29) - Veea Lobster Trap (MIT, github.com/veeainc/lobstertrap) wired as DPI layer with 220-line YAML policy MIT licensed. Drops into existing stacks via OpenAI-compatible proxy + MCP. Enterprise legal can adopt.