ellmer
ellmer stopped being a chat wrapper and started shipping the parts production LLM code needs
Comparison · ai-assistants
btw vs Writer
A side-by-side editorial comparison of btw and Writer — release velocity, themes, recent moves, and the top alternatives to consider.
btw vs Writer: at a glance
What is btw?
btw is turning into an agentic R harness that no longer needs you to be in R
btw assembles context about an R session — packages, documentation, files, data frames — and hands it to an LLM through ellmer, with btw_app() as a chat interface. Over the last year it has grown well past context assembly: LLMs can document, check, test and measure coverage of a package, read CLAUDE.md and AGENTS.md as project context, fetch skills from packages or GitHub, and inspect the source of any installed namespace. Much of this is now reachable from a terminal CLI rather than only from an R prompt.
What is Writer?
A new Palmyra model arrives wrapped in spend controls — WRITER is selling predictability, not raw capability.
Almost everything WRITER publishes is thought leadership aimed at CMOs: brand differentiation, AI visibility, org design, wealth-management capacity. The product signal arrives once a month as a "New at WRITER" digest, and the August one carries Palmyra X6, a faster WRITER Agent, and governance additions in AI Studio, framed around keeping agentic work from running up unpredictable AI spend. That framing is now four digests deep: agent autonomy and admin control in April, brand systems in May, playbooks built for cost efficiency and control in July.
btw vs Writer: editorial side-by-side
btw
2.5AI-ASSISTANTS
btw is turning into an agentic R harness that no longer needs you to be in R
◆ Current state
btw assembles context about an R session — packages, documentation, files, data frames — and hands it to an LLM through ellmer, with btw_app() as a chat interface. Over the last year it has grown well past context assembly: LLMs can document, check, test and measure coverage of a package, read CLAUDE.md and AGENTS.md as project context, fetch skills from packages or GitHub, and inspect the source of any installed namespace. Much of this is now reachable from a terminal CLI rather than only from an R prompt.
◆ Where it's heading
The direction is from describing a session to operating on it, and from inside R to outside it. Each release adds either a tool group that lets a model do something (document, check, test, cover; read namespace source; fetch skill resources) or a CLI command that removes the need to start R first. The 1.2.0 tool renaming — session becoming sessioninfo, search becoming cran, files_read_text_file becoming files_read — reads as the naming cleanup you do when you expect a lot more tools to follow.
◆ Prediction
The CLI has been absorbing one tool family per release (skills, then pkg desc and pkg src) while the R-side tool groups stay ahead of it, so the next releases likely continue exposing existing tool groups as terminal commands rather than adding new capabilities.
Writer
6.3AI-ASSISTANTS
A new Palmyra model arrives wrapped in spend controls — WRITER is selling predictability, not raw capability.
◆ Current state
Almost everything WRITER publishes is thought leadership aimed at CMOs: brand differentiation, AI visibility, org design, wealth-management capacity. The product signal arrives once a month as a "New at WRITER" digest, and the August one carries Palmyra X6, a faster WRITER Agent, and governance additions in AI Studio, framed around keeping agentic work from running up unpredictable AI spend. That framing is now four digests deep: agent autonomy and admin control in April, brand systems in May, playbooks built for cost efficiency and control in July.
◆ Where it's heading
WRITER is positioning cost and control as the thing it sells, with model capability as the enabler rather than the pitch. The April digest established admin control over agent autonomy, July attached cost efficiency to playbooks, and August pairs a new model with governance and budget language in the same breath — the pattern is that every capability ships alongside the lever that constrains it. The company is aiming at buyers who have already run a pilot and now have to defend scaling it internally, which is exactly what the surrounding editorial argues.
◆ Prediction
The next digest should continue instrumenting spend and administration — usage visibility, per-agent limits, or model routing by cost — rather than leading with a capability jump. The entries are digest stubs without itemized release notes, so which specific control lands next isn't observable here.
Alternatives to btw and Writer
Other ai-assistants products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either btw or Writer.
tfevents
tfevents logs TensorBoard events from R, and this release only changes who maintains it.
safetensors
safetensors for R changes hands with no code change to show for it.
torchdatasets
torchdatasets ships custodial work as mlverse gathers its torch satellites under one maintainer.
mlr3tuningspaces
A curated catalogue of published hyperparameter search spaces, now reaching deep neural networks
mlr3hyperband
Hyperband tuning for mlr3, now built on an asynchronous backend it treats as mandatory
Recent activity from btw and Writer
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 2d agoWriterPalmyra X6, a faster agent, and AI Studio governance ⚡
- 2d agoWriterDear CMOs, here’s how to talk to your CIO about AI
- 2d agoWriterWhy brand distinctiveness is your strongest moat in the AI era: Colin Kelton’s framework from 36 years at Vanguard
- 4d agoWriterHow to show up where AI is listening: Building AI visibility from buyer conversations
- 10d agobtwbtw 1.4.0 adds CLI commands for reading R package source
- 10d agoWriterThe Agentic CMO: How Vanguard’s Colin Kelton Rebuilt Marketing From the Inside Out
- 10d agoWriterHow Beauty Pie’s 2-person IT team scaled customer intelligence across the company with WRITER
- 1mo agobtwbtw 1.3.0 makes skills fetchable from the terminal ⚡
- 4mo agobtwbtw 1.2.1
- 5mo agobtwbtw 1.2.0 renames its tool groups ahead of expansion
- 7mo agobtwbtw 1.1.0 lets an LLM document, check and test an R package ⚡
Frequently asked questions
What is the difference between btw and Writer?
They serve adjacent needs but don't currently overlap on shipped themes. Writer is currently shipping more aggressively (velocity 6.3 vs 2.5), with 1 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is btw better than Writer?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Writer is currently shipping more aggressively (velocity 6.3 vs 2.5), with 1 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
What are the best alternatives to btw?
Top btw alternatives in ai-assistants are ranked by recent ship velocity. Browse the "btw alternatives" section above for the current picks, or visit /alternatives/btw-r for the full list with editorial commentary on each.
What are the best alternatives to Writer?
Top Writer alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Writer alternatives" section above for the current picks, or visit /alternatives/writer-ai for the full list with editorial commentary on each.