Alternatives
Products that do what TenantGuard does
Open source scanner for cross-tenant AI-agent security bugs
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9CA
TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base/L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i/o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems…
Jul 2026 · github.com
- 10OS
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
Oct 2025 · archestra.ai
- 11LO
Latch is an open-source proxy that sits between AI agents and the tools they use. It intercepts all tool calls and applies security policies in real-time: Safe operations pass through instantly. Risky operations require human approval via dashboard or Telegram. Dangerous operations are blocked completely I built Latch to address the growing security risks of AI agents accessing critical systems. There have been 1,800+ exposed agent gateways discovered in the wild and recent security audits showing multiple vulnerabilities in agent frameworks, so this was motivated by the clear urgent need…
Feb 2026 · latchagent.com
- 12IB
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
Jan 2026 · github.com
- 13
- 14BO
We’re open-sourcing a simple way to add “canary tools” to AI agents via MCP honeypots. These are functions your agent should never call during normal operation. If a canary is invoked, you get a high-fidelity signal of prompt-injection, tool hijacking, or lateralization—no heuristics, no extra model calls. What it is: - Go framework exposing decoy tools over MCP that look legitimate (names/params/descriptions), return safe dummy output, and emit telemetry when invoked. - Runs alongside your real tools; ship events to stdout/webhook or your pipeline (Prometheus/Grafana,…
Sep 2025
- 15FO
Hey HN, We built FireClaw because we kept watching AI agents get owned by prompt injection through web content. The agent fetches a page, the page says "ignore previous instructions," and suddenly your agent is leaking data or running commands it shouldn't. The existing solutions detect injection after the fact. We wanted to prevent it. FireClaw is a security proxy that sits between your AI agent and the web. Every fetch passes through a 4-stage pipeline: 1. DNS blocklist check (URLhaus, PhishTank, community feed) 2. Structural sanitization (strip hidden CSS, zero-width Unicode, encoding…
Mar 2026 · github.com
- 16AL
AGENTS.lock keeps AI agent skills, instructions, and MCP servers in sync across Claude, Codex, Gemini, and Copilot CLIs using a single TOML lockfile as the source of truth. Instead of manually copying skills and configs between tools, you declare everything once in AGENTS.lock and run `al sync`. GitHub: https://github.com/luml-ai/AGENTS.lock
Jan 2026 · github.com
- 17GS
Anthropic's Model Context Protocol (MCP) has made it easy to spin up servers that expose tools and data to LLMs. A lot of these MCP servers run locally because they need access to your files, shell, browser, etc. The problem: they typically run with the same privileges as your user. If a server is buggy, misconfigured, or prompt-injected, it can do anything you can do: read SSH keys, exfiltrate dotfiles, poke around in private repos, etc. Our research group is working on this by adding a security manifest (inspired by the Android app manifest) plus a local policy enforcement engine that…
Nov 2025 · guardiagent.com
- 18
- 19SA
Mar 2026 · github.com
- 20CS
We've been building with AI tools and noticed there wasn't a good way to manage MCP servers across a team or see what's actually flowing to LLM providers. Who's running what? Which tools are approved? What data is going where or whats shared on AI websites? So we built CyberCage (). What it does: MCP Management — Auto or manual discovery of MCP servers, with approval workflows. Manage allowed MCP servers org-wide (down to individual tools). Secure MCP catalog (integrates with GitHub's MCP Catalog). Operations — Manage allowed AI applications org-wide. Full audit logs (Splunk integration…
Dec 2025 · cybercage.io
- 21
- 22
- 23AB
Hi everyone! My team and I just open-sourced a bunch of cool agent dev tools: Invariant Explorer to visually inspect and understand AI traces and a testing framework, building on pytest.
2024 · github.com
- 24PA
We built PrivateClaw because the hosted OpenClaw platforms on the market today require you to trust them with plaintext. PrivateClaw removes that requirement at the hardware layer. PrivateClaw runs AI agents inside Trusted Execution Environments (TEEs), backed by AMD’s SEV-SNP standard. This means that your data is encrypted at the hardware level, enforced by the AMD Secure Processor outside the host OS trust boundary. PrivateClaw comes with inference that also runs inside TEEs, which means your prompts and completions are private as well. How it works: Each user gets a dedicated CVM…
Apr 2026 · privateclaw.dev
Ranked by how close each launch is in meaning, then by votes. Refine with a description →