btw
btw is turning into an agentic R harness that no longer needs you to be in R
Comparison · ai-assistants
ellmer vs ONNX Runtime
A side-by-side editorial comparison of ellmer and ONNX Runtime — release velocity, themes, recent moves, and the top alternatives to consider.
ellmer vs ONNX Runtime: at a glance
What is ellmer?
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.
What is ONNX Runtime?
ONNX Runtime is retiring WebGL for WebGPU and turning on telemetry outside Windows.
v1.29.0 announces the deprecation of WebGL and JSEP in onnxruntime-web, naming the native WebGPU execution provider as the path forward, and adds POSIX telemetry on Linux, macOS, Android and iOS for telemetry-enabled builds, disabled via ORT_DISABLE_TELEMETRY. It also carries a long list of security fixes — a TensorRT path-traversal vulnerability, plus rank, shape and bounds validation across a dozen kernels. Separately, the WebGPU plug-in reached v0.2.1 with fused FlashAttention decode kernels for any sequence length and Qwen3 and Gemma 4 model paths, while v1.28.0 made cuDNN and cuFFT optional at runtime to shrink the CUDA redistributable.
ellmer vs ONNX Runtime: editorial side-by-side
ellmer
2.5AI-ASSISTANTS
ellmer stopped being a chat wrapper and started shipping the parts production LLM code needs
◆ Current state
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.
◆ Where it's heading
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.
◆ Prediction
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.
ONNX Runtime
6.3AI-ASSISTANTS
ONNX Runtime is retiring WebGL for WebGPU and turning on telemetry outside Windows.
◆ Current state
v1.29.0 announces the deprecation of WebGL and JSEP in onnxruntime-web, naming the native WebGPU execution provider as the path forward, and adds POSIX telemetry on Linux, macOS, Android and iOS for telemetry-enabled builds, disabled via ORT_DISABLE_TELEMETRY. It also carries a long list of security fixes — a TensorRT path-traversal vulnerability, plus rank, shape and bounds validation across a dozen kernels. Separately, the WebGPU plug-in reached v0.2.1 with fused FlashAttention decode kernels for any sequence length and Qwen3 and Gemma 4 model paths, while v1.28.0 made cuDNN and cuFFT optional at runtime to shrink the CUDA redistributable.
◆ Where it's heading
The browser story is consolidating onto one backend after years of maintaining three, and the WebGPU plug-in's independent release track is what made that credible — the attention work landed there first. On the core runtime the direction is subtraction: fewer linked CUDA libraries, removed TensorRT fused kernels, a deprecated CUDA 12, and a steady stream of input-validation hardening that suggests sustained security review. Note the feed is non-monotonic, with v1.26.0 and v1.29.0 published minutes apart.
◆ Prediction
CUDA 12 removal in 1.27.0 was already announced, and the CUDA runtime is slated to move into a dedicated execution provider — that separation is the next structural change to watch.
Alternatives to ellmer and ONNX Runtime
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 ONNX Runtime.
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
See all ellmer alternatives → · See all ONNX Runtime alternatives →
Recent activity from ellmer and ONNX Runtime
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 3d agoONNX RuntimeONNX Runtime 1.29 deprecates WebGL and JSEP, adds POSIX telemetry ⚡
- 3d agoONNX RuntimeONNX Runtime 1.26 adds RISC-V vector support and .ort memory mapping
- 16d agoONNX RuntimeWebGPU plug-in: FlashAttention fusions, Qwen3 and Gemma 4 paths
- 21d agoONNX RuntimeONNX 1.22 upgrade, slimmer CUDA footprint, experimental C API
- 29d agoellmerellmer 0.4.2
- 1mo agoONNX RuntimePatch release: QMoE batch-1 decode fast path and fixes
- 1mo agoONNX RuntimeSecurity-hardening minor targeting ONNX 1.21
- 3mo agoellmerellmer emits OpenTelemetry traces for every chat and tool call ⚡
- 9mo agoellmerellmer 0.4.0 adds provider-native web search and stops storing API keys ⚡
- 11mo agoellmerellmer 0.3.2
- 11mo agoellmerellmer 0.3.1
- 1y agoellmerellmer 0.3.0 adds a universal chat() and rewrites tool specification
Frequently asked questions
What is the difference between ellmer and ONNX Runtime?
They serve adjacent needs but don't currently overlap on shipped themes. ONNX Runtime 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 ellmer better than ONNX Runtime?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. ONNX Runtime 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 ellmer?
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.
What are the best alternatives to ONNX Runtime?
Top ONNX Runtime alternatives in ai-assistants are ranked by recent ship velocity. Browse the "ONNX Runtime alternatives" section above for the current picks, or visit /alternatives/onnx-runtime for the full list with editorial commentary on each.