Search

Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.

AI model: SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507

Portable OpenCode workflow plugins, explicit memory, and CLI tooling.

The Trust Layer for the Agentic Economy — Quantum-Safe AI Agent Gateway SDK

Let Claude Code and other MCP agents work on your own computers and servers with your approval: the agent asks your Host, you approve with a passkey, and a bastion on each machine checks every request. Free and self-hosted; runs on Windows, macOS and Linux.

Node SDK for checking AI agent tool calls with Relay.

Universal TIBET provenance for ANY Python code. @tibet_guard decorator, ASGI middleware, agent safety. OWASP LLM06 compliant.

Sandboxed HTTP client with SSRF protection for AI agents

Agentic SOC analyst for Splunk — Claude investigates via the Splunk MCP Server; a deterministic 3-layer validator verifies every finding against real data. An anti-hallucination trust layer for agentic SOC.

Drop Tulip's control runtime (admit() gate + tamper-evident audit) into the agent framework you already use — LangChain, LangGraph, CrewAI, the OpenAI Agents SDK, LlamaIndex.

TypeScript/JavaScript SDK for the Agentum Agentic IAM platform

Gate LangChain tool calls behind a Fidacy verdict. Wraps the tool itself, so a denied payment never executes: callbacks can only observe, this can stop.

Generate adversarial test inputs with a coding agent; your pytest assertions judge them

Local-first LLM agent CLI — model routing + sandboxed tool execution on your own server (Ollama by default)

Deterministic policy engine for LLM-generated SQL: SELECT-only, PII column denylist, table allowlist, cost cap. Multi-dialect via sqlglot (BigQuery, Snowflake, Postgres, Trino, …).

Agentic Firewall sits between an AI agent or MCP client and an MCP server. It can enforce runtime policies and automatically test the server's tool-use attack surface with 17 OWASP ASI scenarios. It runs locally and sends no telemetry.

Community Edition — AgentMesh Runtime: Execution supervisor for multi-agent sessions with privilege rings, saga orchestration, and audit trails

AI model: mradermacher/AgentDoG-FG-Qwen3-4B-i1-GGUF

A police department for your Claude Code agents — a logging hook + CLI that audits what the main agent and its subagents actually did.

Odyssey: Empowering Minecraft Agents with Open-World Skills