Webwright: A terminal is all you need for web agents
Webwright introduces a terminal-native approach for web agents, allowing them to manage multiple browser sessions efficiently. This innovative model enables agents to create reusable programs from web tasks while maintaining a local workspace for logs and outputs. The system demonstrates significant improvements in long-horizon browsing accuracy compared to traditional methods.
- ▪Webwright allows agents to launch, inspect, and discard browser sessions while preserving outputs in a local workspace.
- ▪The model achieves 86.7% accuracy on the Online-Mind2Web benchmark and a 60.8% score on the Odysseys long-horizon browsing test.
- ▪Webwright's implementation consists of a minimal harness with three core modules totaling around 1,000 lines of code.
3 outlets in our directory ran this story, first to last over 24 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ Webwright: A Terminal Is All You Need for Web Agents — Microsoft Research
- ▪ Your LLM Is Not an Agent. Your Framework Is Not Enough. You Need a Harness. — DEV.to (Top)
Hacker News (Newest) files mainly under programming. We currently carry 5,306 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://microsoft.github.io/Webwright/ |
| Publication time | Tue, 26 May 2026 06:18:55 +0000 |
| Retrieval time | 2026-05-26T06:37:45.433Z |
| Last seen | 2026-05-26T06:37:45.433Z |
| 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 | J1-QXfgLYElF · 3 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
Terminal-native web agents A terminal is all you need for web agents. Webwright gives the model a terminal, a local workspace, and the freedom to write code that launches, inspects, and discards browser sessions. The output is not just a completed task, but a reusable program. How it works Watch the trace GitHub Microsoft Research Blog 3 core modules ~1K lines of harness code 86.7% Online-Mind2Web accuracy 60.8% Odysseys score Paradigm shift In Webwright, agent can launch multiple browser sessions in terminal. Traditional web agents keep one browser session alive and predict the next click, type, or scroll. Webwright separates the agent from that session: the browser can be launched, inspected, and discarded, while code, logs, screenshots, and outputs persist in the local workspace.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Github.
Discussion
0 commentsMore from Github
