Alternatives
Products that do what Custosa does
Permission and compliance layer for Enterprise AI
- 1
- 2
- 3
- 4
- 5AC
We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware. Claude Code's permission system is allow-or-deny per tool, but that doesn’t really scale. Deleting some files is fine sometimes. And git checkout is sometimes not fine. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool's errand. nah is a PreToolUse hook that classifies every tool call by what it actually does, using a deterministic classifier that runs in milliseconds. It maps commands to action types…
Mar 2026 · github.com
- 6
- 7
- 8
- 9
- 10
- 11
Stop AI agents from doing things they shouldn't.
29d ago · sanjaynandanj.github.io
- 12
- 13
- 14AA
At my last company, we connected Claude Code and Cursor to almost all our internal services via MCP. It made the team incredibly fast, but we hit a wall: permissions. If you give an agent "Read Only" access, it can’t actually fix anything. If you give it "Write" access, it’s only a matter of time before a hallucination or a bad prompt results in a deleted database or a nuked production bucket. We had a few "close calls" that convinced us that simply reducing IAM permissions makes agents useless. I built Armour (https://github.com/fuushyn/armour) to solve this. It’s a…
Jan 2026 · github.com
- 15CL
With the right technique, I was able to break the so-called secure models like Claude and OpenAI. So, I built an open-source tool to automate this and find security holes in any hosted model. I got claude-sonnet-4 to demonstrate the following harmful behavior: - steal data from downstream tool calls using sql injection, code injection and template injection attacks - install spyware or malware using prompt obfuscation to send data to a third-party server Try it yourself with this simple command: pip install compliant-llm && compliant-llm dashboard
2025 · github.com
- 16LE
I started using Claude Code (claude --dangerously-skip-permissions) and Codex (codex --yolo) and realized I had no reliable way to know what they actually did. The agent's own output tells you a story, but it's the agent's story. logira records exec, file, and network events at the OS level via eBPF, scoped per run. Events are saved locally in JSONL and SQLite. It ships with default detection rules for credential access, persistence changes, suspicious exec patterns, and more. Observe-only – it never blocks. https://github.com/melonattacker/logira
Mar 2026 · github.com
- 17CC
We’ve been building visual rule engines (clear spreadsheet interfaces -> API endpoints that map incoming data to a large number of potential outcomes), and had the fun idea lately to see what happens when we use our decision table UI with Claude’s PreToolUse hook. The result is a surprisingly useful policy/gating layer– these tables let your team: - Write conditional, exception-friendly policies beyond globs/prefixes (e.g. allow rm -rf only in */node_modules/*, deny / or $HOME, ask if --force or network call; gate kubectl delete / SQL DROP with a clear reason) -…
Jan 2026 · github.com
- 18CL
We're excited to launch compliant-llm: an open-source toolkit that helps infosec and compliance teams audit AI agents against regulatory frameworks like NIST AI RMF, ISO 42001, and OWASP Top 10. Infosec and compliance teams are now responsible for tracking security and compliance risks of a growing number of AI agents across external and internal apps and third-party vendors. compliant-llm gives you a way to: - Define and run comprehensive red-teaming tests for AI agents - Maps test outcomes to compliance frameworks like NIST AI RMF - Generate detailed audit logs and documentation -…
2025 · github.com
- 19TO
Jun 2026 · github.com
- 20
Give AI agents your company data. Only what they can see.
4d ago · warehousd.com
- 21ZA
Hi HN, I'm Jiasheng, co-creator of ZenStack. Access control usually ends up scattered across app code instead of living with the data model — and that's riskier when the code is written by an agent, since it's easy to ship a query with a missing or incomplete authorization check. ZenStack enforces policy (RBAC/ABAC/relation-based) directly at the ORM layer, on top of Kysely, so every query gets checked the same way regardless of who wrote it and who is calling it. Postgres RLS is an option too, but it's hard to maintain and scale, and it's Postgres-only — ZenStack's approach is…
Jul 2026 · zenstack.framer.website
- 22OS
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
- 23PE
Show HN: Runtime authorization for Claude Code, Cursor, and Codex Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. We built Kastra after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database. We caught it before it ran, but it made us realize that nothing in our stack actually decided what the agent was allowed to do. What mattered for us wasn't…
Jul 2026 · kastra.ai
- 24AP
Hi HN, We’re the founders of Abide — a tool to prevent employees from leaking sensitive data to AI models. Over the past month we’ve spoken to lots of friends at tech companies, law firms, creative agencies, and more. There was a consistent theme: companies aren’t sure how AI tools affect their data privacy and security processes. There are concerns that when employees use LLMs to write code or send emails, there's a security/compliance risk (e.g., accidentally sharing an API key in a prompt) or violation of privacy agreements (e.g., using AI to draft a memo about non-public client…
2023 · tryabide.co
Ranked by how close each launch is in meaning, then by votes. Refine with a description →