Search

Chatbase is an AI customer-support platform for building and deploying agents. Its official product page documents business-data training, role and guardrail configuration, an embeddable website chat, listed Slack, WhatsApp, Messenger, email and voice channels, actions on external systems, conversation logs, analytics and smart escalation to human agents. Pricing uses model-dependent message credits; actions can create multiple requests, and subscription credits renew monthly without carryover.

Open standard for verifiable AI agent identity and authority. One signed JSON file at /.well-known/agent-passport.json, keyed in DNS. Verifier, spend caps, signed receipts, CLI and MCP server. MIT.

Protect OpenAI Codex with Radware Agentic AI Protection - AI Guardrails on prompts and Behavioral Protection on tool calls, enforced before they execute

Open-source safety checks for AI agents on Solana: pre-sign simulation, intent matching and token verdicts. MCP and HTTP, free daily allowance, x402 USDC.

The pre-trade safety net your Vercel AI SDK agent didn't know it needed. Live sell simulation across every DEX on Base (Uniswap V2/V3/V4, Aerodrome), catching traps a static scan will never see. Honeypot detection, rug-pull risk, deployer history. x402-po

The zero-trust framework for autonomous AI agents.

🚀 An Model Context Protocol (MCP) server for Fleet. Query OSQuery data, check compliance, and investigate CVEs natively from Claude, Cursor, and any MCP-compatible AI agent.

Nexus-LLM is a ai model which can run locally on your device.

A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

Portfolio técnico de Eugenio Santiago — arquitetura de agentes AI: multi-agent systems, MCP servers, n8n workflows. Berlin.

Agentic Control Plane for fx (vercel-labs/fx) — a governed protocol middleware for fx's Agent Client Protocol mode, checking every tool call against your policies before fx's own permission prompt reaches the client.

Permits and signed receipts for agent tool calls. One dispatch, one charge, verifiable offline.

Deterministic contract enforcement for agent tool calls: gates the destination, not the tool. No LLM in the decision path.

Deception at the Registry Layer: detecting autonomous AI agents in MCP environments (working paper)

It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.

MCP_HACK//26 — Industrial Zero-Trust AI: T-IA Connect + AgentGateway for Siemens TIA Portal

Mercado Pago Subscriptions as drop-in tools for the Vercel AI SDK. Argentine-focused, agent-ready.

A firewall that blocks dangerous AI requests before they execute

No-code AI agent builder — turn one sentence into a single agent or a multi-agent team. The engine inside Agentlas. A no-code CrewAI / LangGraph / AutoGen alternative that runs on Claude Code, Codex, and Cursor.

Ethics-aware OSINT investigation planning, collection, and risk evaluation, delivered as an MCP server. Classification, risk tiers, hard stops, and defensible documentation — driven by local YAML doctrine.