Search

Production-ready Go scaffold template with clean architecture, lifecycle-managed dependency injection (samber/do), HTTP server (net/http + Huma/OpenAPI), CLI scaffolding, 45+ AI agent skills for Claude/Copilot/OpenCode, and built-in DevOps security tooling.

ECC is an agent harness performance optimization system for Claude Code, Codex, Opencode, Cursor, and similar AI coding environments. It packages ideas around skills, instincts, memory, security, and research-first development so builders can make coding agents more repeatable and easier to audit.

Hardened, production-grade configuration & safety framework for Hermes Agent on WSL2/Ubuntu 26.04. Features 9-layer security defense, 47 blocked command patterns, Docker & Bubblewrap sandboxing, modular system personas, zero-trust audit tooling, and seamless integrations for RTK, CodeGraph MCP, and Hermes-LCM.

Automate 80% of your customer queries, AI Agents, Integrations, Analytics, Security, Customer Support, Customer Success, Sales Engineer, Pricing, Resources, Blogs, Support OS, Podcast, AI Agent Assist, AI in Customer Support, Team Threado, AI for Internal Teams, AI Knowledge Base, AI in Customer Experience

CubeSandbox is an open-source secure sandbox service for AI agents from Tencent Cloud. The repository describes a RustVMM and KVM-based runtime that creates hardware-isolated sandboxes in under 60 ms with less than 5 MB of per-instance overhead, supports single-node and multi-node deployments, and offers an E2B-compatible interface for agent code execution.

LoginLlama is a groundbreaking user authentication platform designed to secure logins and prevent unauthorized access. Utilizing advanced AI, LoginLlama analyzes multiple ranking factors like historic behavior, AI analysis, request origin, and user agent to determine the 'suspiciousness' of each login attempt. This high level of scrutiny ensures that your platform is protected from phishing attacks, account takeovers, credential stuffing, brute force attacks, and insider threats. By simply integ

Portia AI is an open-source SDK and cloud platform designed to help developers build predictable, controllable, and authenticated AI agents . Its core purpose is to simplify the creation and deployment of AI agents that can execute complex tasks while maintaining security, reliability, and user control . **Key features and capabilities:** Portia AI facilitates the creation of structured, multi-agent plans using a planning agent that guides the LLM to generate explicit plans . Execution agents a

AI First is a no-code AI agent builder that lets businesses create, deploy, and manage autonomous AI agents in minutes—no developers required. With drag-and-drop workflows, natural language instructions, and 200+ integrations (Slack, Zapier, databases, CRMs), teams can automate support, sales, analytics, and operations at scale. Enterprise features like SOC 2/GDPR compliance, role-based access, custom training data, and real-time analytics make AI First a secure, scalable platform for AI adoptio

AI model: LayerFault/agent-mcp-contradictory-tool-annotation

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.

Guardrails for coding agents, decided by TypeSafe's Jev: blocks destructive commands, catches prompt injection, pushes back on an unverified done and routes effort per turn. For Claude Code, pi and omp.

Automated documentation system for Kali Linux tools using an AI agent. Scans, indexes, and documents your system tools automatically.

pentagi is an open-source AI developer tool from https://github.com/vxcontrol/pentagi. Fully autonomous AI Agents system capable of performing complex penetration testing tasks. It is best evaluated by technical teams that want transparent, inspectable automation rather than a black-box hosted workflow.

Korveo observability + Agent Firewall for OpenClaw — captures prompts, responses, tool I/O, and synchronously enforces firewall policies on every tool call.

Pi extension that masks sensitive data before it reaches the LLM and restores it for users and tools.

Browser automation for AI agents - integrates agent-browser with cognition swarms

Autonomous Penetration Testing Agent Framework with External State Memory & Anti-False-Falsification Guardrails.

Lightweight, extensible, Claude-native governance for AI agents: an independent, deterministic verifier that can refuse to certify a tool call before it runs. Builders cannot grade their own work.

Deterministic pre-execution safety gate for AI agents: verify tool calls against trusted evidence, policies, and WorldState before side effects.

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.