How to Use Claude Code in Your Browser - Towards Data Science
Earlier context — a how-to on running Claude Code directly in the browser, hands-on browser use of Claude's coding tools.
AI Storyline
7 items · 4 sources · 5 days
Operational story trace
Let's Science
Follow in this browser to see new updates on your Live feed.
Current stateLaunched
Latest change
No Claude Science product news since the June 30 launch and same-day Modal integration — the four most recent additions to this cluster are unrelated LLM-inference-tooling pieces that share only the "...Data Science" publication branding with the product name, not a new development.
Earlier contextThe story so far
The thread starts with hands-on, browser-based use of Claude's coding tools (a Jun 22 how-to on running Claude Code in the browser), then converges on a science-specific product. On Jun 30 Anthropic packaged that direction into Claude Science, a dedicated workbench for researchers.
editor-curated · source-linked
Arc
Jun 22Jul 6 · now
EARLIER CONTEXT · Jun 22Claude Code goes browser-based1 source · show source ▾
LAUNCH · Jun 30Claude Science debuts as an AI workbench for scientists1 source · show source ▾
Claude Science, an AI workbench for scientists
The launch: Claude Science debuts as a customizable AI workbench integrating researchers' tools and packages, producing auditable artifacts with flexible compute access.
ECOSYSTEM · Jun 30Modal integration brings elastic compute to Claude Science1 source · show source ▾
Anthropic integration with Modal brings scalable compute to Claude Science
Same-day ecosystem move — Modal's integration brings elastic, on-demand compute to Claude Science researchers.
UNRELATED ROUNDUP · Jun 30 – Jul 6Cluster also swept in four unrelated inference-tooling reads4 sources · show sources ▾
Article Compares Continuous and Static Batching in LLM Inference - Let's Data Science
Unrelated: compares continuous and static batching strategies for LLM inference — grouped in only by shared 'Data Science' publication branding, not the Claude Science product.
codebase-memory-mcp speeds AI coding agent queries - Let's Data Science
Unrelated: an MCP-based codebase-memory tool for speeding AI coding agent queries — no connection to Claude Science.
WattGPU Predicts LLM Inference Power Without Profiling - Let's Data Science
Unrelated: a tool that predicts LLM inference power draw without profiling — no connection to Claude Science.
Inference Chips Differ for LLM Serving Workloads - Let's Data Science
Unrelated: compares how different inference chips handle LLM serving workloads — no connection to Claude Science.
Day 1 Monday, Jun 22, 2026
How to Use Claude Code in Your Browser - Towards Data Science
Earlier context — a how-to on running Claude Code directly in the browser, hands-on browser use of Claude's coding tools.
Day 2 Tuesday, Jun 30, 2026
Anthropic integration with Modal brings scalable compute to Claude Science
Same-day ecosystem move — Modal's integration brings elastic, on-demand compute to Claude Science researchers.
Claude Science, an AI workbench for scientists
The launch: Claude Science debuts as a customizable AI workbench integrating researchers' tools and packages, producing auditable artifacts with flexible compute access.
Article Compares Continuous and Static Batching in LLM Inference - Let's Data Science
Unrelated: compares continuous and static batching strategies for LLM inference — grouped in only by shared 'Data Science' publication branding, not the Claude Science product.
Day 3 Friday, Jul 3, 2026
codebase-memory-mcp speeds AI coding agent queries - Let's Data Science
Unrelated: an MCP-based codebase-memory tool for speeding AI coding agent queries — no connection to Claude Science.
Day 4 Sunday, Jul 5, 2026
WattGPU Predicts LLM Inference Power Without Profiling - Let's Data Science
Unrelated: a tool that predicts LLM inference power draw without profiling — no connection to Claude Science.
Day 5 Monday, Jul 6, 2026
Inference Chips Differ for LLM Serving Workloads - Let's Data Science
Unrelated: compares how different inference chips handle LLM serving workloads — no connection to Claude Science.
What to watch — open questions
- Is Claude Science generally available, or limited/waitlisted? The launch note doesn't state access terms.
- What format are the 'auditable artifacts', and are they exportable or interoperable with existing research tooling?
- Will compute providers beyond Modal integrate, or is elastic compute effectively single-vendor for now?
- Does the customizable app support self-hosted or arbitrary tools and packages, or a curated set?
How this thread was built
editor wrote the arc · 4 beatswatcher 1 status change
Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.