Show HN: Conduct, open-source guardrails for LLM and MCP tool calls
sudhendra1
20 points
3 comments
August 28, 2026
Related Discussions
Found 5 related stories in 74.5ms across 4,827 title embeddings via pgvector HNSW
- Show HN: An MCP server that turns async-work practices into tools benbalter · 17 pts · July 21, 2026 · 58% similar
- Show HN: Policy enforcement for Claude Code, Cursor, and Codex carlosjimenez1 · 12 pts · July 09, 2026 · 57% similar
- Show HN: Noisegate – a differential-privacy gateway for untrusted AI agents yashmahajan10 · 17 pts · July 30, 2026 · 56% similar
- Show HN: Sqlsure – deterministic semantic checks for AI-generated SQL tejusarora · 26 pts · July 11, 2026 · 55% similar
- Show HN: Sentinel – open-source QA agent that reads your code before it clicks asenna · 15 pts · July 16, 2026 · 55% similar
Discussion Highlights (3 comments)
sigy
If you want something much lighter, and focused around harness tool calls, check this out: https://crates.io/crates/coding-tools
LuD1161
I've been working on something similar , policy guardrails for coding agents, with OPA backed policies and os-native sandbox - https://github.com/LuD1161/agentjail
rob_b
Another example of why vibe coding is the worst advancement ever.