btw
btw is turning into an agentic R harness that no longer needs you to be in R
A side-by-side editorial comparison of ellmer and GitHub Copilot — release velocity, themes, recent moves, and the top alternatives to consider.
ellmer stopped being a chat wrapper and started shipping the parts production LLM code needs
ellmer is R's provider-agnostic LLM client, covering Anthropic, OpenAI, Gemini, Bedrock, Databricks, Snowflake, Ollama, Groq and more behind one Chat object with structured output, tool calling and streaming. The last year moved it well past request plumbing: API keys are now fetched through a credentials function rather than stored in the object, provider-native web search and fetch are first-class tools, and every call emits OpenTelemetry spans when a tracer is active. Releases land roughly every six to ten weeks with meaningful content each time.
Copilot ships a model a week, but the plugin format is the move that outlasts them
GitHub Copilot's feed reads as a rolling model catalog — Grok 4.6, Gemini 3.7 Flash, MAI-Code-1.1-Flash added, MAI-Code-1-Flash deprecated on a stated date. Underneath that churn sit two structural items: Agent Plugins 1.0, a build-once plugin format shipped with AWS, Anysphere, Microsoft, OpenAI, and Vercel behind it, and per-model token accounting in the usage report. Client work continues across VS Code, JetBrains, the CLI, the web, and the Copilot app.
ellmer is R's provider-agnostic LLM client, covering Anthropic, OpenAI, Gemini, Bedrock, Databricks, Snowflake, Ollama, Groq and more behind one Chat object with structured output, tool calling and streaming. The last year moved it well past request plumbing: API keys are now fetched through a credentials function rather than stored in the object, provider-native web search and fetch are first-class tools, and every call emits OpenTelemetry spans when a tracer is active. Releases land roughly every six to ten weeks with meaningful content each time.
The arc runs from breadth to depth. Early releases raced to add providers; recent ones assume you already picked one and are trying to run it in production — tracing with the gen_ai semantic conventions, prompt caching on by default, parallel and batch chat graduating out of experimental with configurable error handling, and truncated or filtered responses raising warnings instead of passing silently. The credentials rework and automatic key redaction on save show the same instinct applied to secrets.
Batch processing has been picking up one provider per release — Gemini and Groq most recently — so the next releases likely continue filling in batch and built-in-tool coverage across the provider list rather than adding new provider integrations.
GitHub Copilot's feed reads as a rolling model catalog — Grok 4.6, Gemini 3.7 Flash, MAI-Code-1.1-Flash added, MAI-Code-1-Flash deprecated on a stated date. Underneath that churn sit two structural items: Agent Plugins 1.0, a build-once plugin format shipped with AWS, Anysphere, Microsoft, OpenAI, and Vercel behind it, and per-model token accounting in the usage report. Client work continues across VS Code, JetBrains, the CLI, the web, and the Copilot app.
Model additions arrive faster than they can differentiate, which is exactly why the portability and metering work matters more: a plugin that runs unchanged across clients and a bill that itemizes per model are what make an interchangeable model roster manageable. The client surfaces are converging on the same feature set, with memory, local models via Ollama, and enterprise controls reaching JetBrains after the VS Code line. The weekly release cadence formalizes all of it into a single recurring digest.
Expect the model roster to keep rotating on a roughly weekly beat with deprecations following each replacement, and expect Agent Plugins to accumulate more launch partners since its value depends on breadth of adoption. Feature parity across JetBrains, CLI, and the app looks like the ongoing project rather than any single new capability.
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 ellmer or GitHub Copilot.
btw is turning into an agentic R harness that no longer needs you to be in R
tfevents logs TensorBoard events from R, and this release only changes who maintains it.
safetensors for R changes hands with no code change to show for it.
torchdatasets ships custodial work as mlverse gathers its torch satellites under one maintainer.
A curated catalogue of published hyperparameter search spaces, now reaching deep neural networks
Hyperband tuning for mlr3, now built on an asynchronous backend it treats as mandatory
See all ellmer alternatives → · See all GitHub Copilot alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. GitHub Copilot is currently shipping more aggressively (velocity 10.0 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.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. GitHub Copilot is currently shipping more aggressively (velocity 10.0 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.
Top ellmer alternatives in ai-assistants are ranked by recent ship velocity. Browse the "ellmer alternatives" section above for the current picks, or visit /alternatives/ellmer-r for the full list with editorial commentary on each.
Top GitHub Copilot alternatives in ai-assistants are ranked by recent ship velocity. Browse the "GitHub Copilot alternatives" section above for the current picks, or visit /alternatives/github-copilot for the full list with editorial commentary on each.