Show HN: Relay – a harness for AI coding agents that recover and verify
The only harness you need for codingSelf-improving AI agents.Agents that learn from every run and re-test every pull request. Relay never bills your tokens.Building the singularity, one merged pull request at a time.We believe AI will surpass people at building software. Relay is the harness it learns in.Your model is your bill.Relay never sells tokens.
- ▪The only harness you need for codingSelf-improving AI agents.Agents that learn from every run and re-test every pull request.
- ▪Relay never bills your tokens.Building the singularity, one merged pull request at a time.We believe AI will surpass people at building software.
- ▪Relay is the harness it learns in.Your model is your bill.Relay never sells tokens.
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,889 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 | Relay |
| Canonical URL | https://relayevals.com |
| Publication time | Tue, 29 Sep 2026 18:46:07 +0000 |
| Retrieval time | 2026-09-29T18:52:31.858Z |
| Last seen | 2026-09-29T18:52:31.858Z |
| 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 | Yl7JuOkvqJrk · 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
The only harness you need for codingSelf-improving AI agents.Agents that learn from every run and re-test every pull request. Free, on your machine, with your models.InstallRead the docsRuns the models you already pay forSign in with Claude, ChatGPT or Copilot, or bring an API key.AnthropicOpenAIGitHub CopilotGooglexAIDeepSeekMistralOpenRouterAmazon BedrockEvery lap starts higher.QueueYour backlog, one worktree per taskRunYour model, inside your limitsCheckTests re-run by RelayLearnKept for the next runControl, not babysitting.Learns from every runWhat a run learns is kept for the next one.Tested before it shipsRelay re-runs your tests, lint and build before a pull request exists.Stays inside your limitsTurns, tokens, time and spend, capped on every run.Any model, your keysOver 1,000…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Relay.
Discussion
0 commentsMore from Relay
