Show HN: Gnt, a company brain AI agents check before acting
Gnt introduces a system where AI agents consult a git‑native rulebook via an MCP endpoint before performing risky actions. Rules are authored as markdown files with YAML metadata, stored in a repository and approved through standard pull‑request workflows. The platform offers a hosted service and a CLI that requires Node ≥ 22.13, with privacy‑focused design and optional on‑device extraction.
- ▪Agents invoke the check_action endpoint to receive an allow, block, or needs_human verdict based on approved rule files.
- ▪Rule files live in the repo’s rules directory and are versioned and approved via pull requests, providing an audit trail.
- ▪The CLI provides commands for login, connecting to GitHub, scanning sources, reviewing rules, and managing skill packs.
- ▪Gnt’s hosted version operates without requiring users to run a Postgres instance, and raw source text can be processed in the cloud or locally for privacy.
- ▪The system includes no analytics or telemetry, and extraction can be performed on‑device using a local Ollama daemon if desired.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,381 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/gnt-ai/gnt |
| Publication time | Mon, 03 Aug 2026 01:35:11 +0000 |
| Retrieval time | 2026-08-03T01:45:44.804Z |
| Last seen | 2026-08-03T01:45:44.804Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | K03vtAPdKQRX · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Run the setup below once and every agent your team runs has a git-native rulebook it has to check over MCP before it acts, approved the same way your code already is: a merged pull request. Rules live in your repo as files and ship through normal PRs, not a dashboard click. Agents call check_action over MCP before anything risky (a refund, a delete, a message to a customer) and get back an allow/block/escalate verdict. Every rule traces back to the git file and the PR that approved it, so "why did the agent do that" always has a paper trail. Prefer not to run any of this yourself? The hosted version at gntai.dev does the same thing without you standing up a Postgres instance. gnt prebrain scanning a repo, opening a PR, and getting it merged. A real terminal session, not a mockup.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.