Show HN: How to build and self-host a code review agent

Tilde· Jul 31, 2026 · 8:27 PM UTC ·3 min read · 0 reactions · 0 comments · 3 views

#ai #software-development #cloud #devops

Show HN: How to build and self-host a code review agent

TL;DR · WeSearch summary

Tilde is a cloud‑first SDK that lets developers assemble AI agents from modular components such as tools, chat integrations, and memory stores. The author demonstrates its use by creating a self‑hosted code‑review bot that can be triggered from GitHub, run in a sandbox, and post review comments. The example is available on GitHub and can be deployed to Vercel with a simple configuration file.

Key facts

▪Tilde provides composable components like MCP tool servers, ChatKit integrations for Slack and GitHub, and centralized memory management.
▪The code‑review agent is designed to be invoked via a GitHub PR tag, securely checkout code in a sandbox, analyze diffs, and comment inline and with a summary.
▪Deployment is streamlined through a tilde‑state.yaml file, allowing users to import settings, configure GitHub and Modal sandbox integrations, and launch the agent on Vercel.
▪All Tilde services are cloud‑based, centrally managed, and permissioned, with future support planned for additional frameworks and languages.

About this source

Hacker News (Front Page) files mainly under programming. We currently carry 904 of its stories. Top-voted stories on Hacker News.

All Hacker News (Front Page) coverage →

Original article

Tilde · Tilde

Read full at Tilde →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

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	Tilde
Canonical URL	https://www.trytilde.ai/blog/how-to-build-code-review-agent
Publication time	Fri, 31 Jul 2026 20:27:28 +0000
Retrieval time	2026-07-31T22:18:28.829Z
Last seen	2026-07-31T22:18:28.829Z
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	OGWHe5oJwqpT · 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)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

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.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

Blog30 July 2026 / 3 min readHow to build a code review agentHow to build your own code review agent in under 5 minutesIn briefTilde is a harness SDK for building cloud deployed AI agents, extremely fast.Making a harness cloud-first & composable.Example: How to build a code review agent.Tilde is a harness SDK for building cloud deployed AI agents, extremely fast.I built Tilde for 2 reasons:that creating a single agent harness for all tasks both simple and highly complex would lead to sub-optimal outcomes.That harness's & AI agent libraries at the time didn't give me the developer experience, portability or composability that I wantedOver a year later into building this side project, point 1 is still true.

…

Excerpt limited to ~120 words for fair-use compliance. The full article is at Tilde.

Anonymous · no account needed

Discussion

0 comments