ThinkWatch
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
- 817
- Rust
- 10 h ago
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
Production-grade PostgreSQL extension to execute arbitrary SQL in background worker processes — with async execution, autonomous transactions, cookie-protected handles, cancellation, progress reporting, and observability.
Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flags when the agent's summary says all tests pass but something failed. Open-source AI agent verification, hallucination detection, and audit tool. Local-only, no telemetry.
Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI agents with RAG knowledge bases.
Invariant is an open-source, cryptographic command-validation firewall that sits between AI models and actuators to provide provable, deterministic safety profiles and append-only signed audit logs for physical systems like robotics and biosynthesis lines.
Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.
Structured, compile time schema-enforced audit logging for Go services. Taxonomy-driven validation, type-safe code generation, multi-output fan-out (file, syslog, webhook and more), CEF + JSON formatters, HMAC integrity checks, per-output event routing, sensitivity labels, and async delivery.
A Fastly Compute reference for AI agents controlling physical hardware over Anthropic's Model Hardware Standard
A deterministic runtime security SDK for LLM applications that prevents prompt injection, data leakage, and rogue agent behavior using high-performance, auditable rule-based guards instead of probabilistic AI inference.