Benchmark-as-a-service for dotnet/runtime. Triggered from GitHub comments, runs BDN microbenchmarks on dedicated hardware, and posts results back. Mostly intended for triaging performance regressions/improvements from PRs (before/after).

Mention @EgorBot in a PR or issue comment with a C# benchmark snippet:

@EgorBot -arm -amd --envvars DOTNET_JitDisasm:Bench
```cs
using BenchmarkDotNet.Attributes;
public class MyBenchmarks
{
 [Benchmark]
 public void Bench() { /* ... */ }
}
```

EgorBot will build dotnet/runtime for the PR and main (or each commit passed via -commits), run the benchmark, and post BDN results back as a comment. --envvars and other BDN arguments can be passed through to customize the run.

@EgorBot [targets...] [options...] [BDN arguments...]

Everything after @EgorBot on the same line is parsed as space-separated tokens. A fenced code block (```cs) in the same comment provides the benchmark source. Once EgorBot-specific options are no longer recognized, the remaining tokens are passed verbatim as arguments to BDN (e.g. --filter "*MyBench*").

NOTE: 32-bit arm and windows targets are currently not available (let me know if you need them).
NOTE: mono runtime is not currently supported
NOTE: NativeAOT (NAOT) runtime is not currently supported

Targets specify where to run. Format: {os}_{cloud}_{cpu}. If os is omitted, defaults to ubuntu24. If cloud is omitted, defaults to azure (or helix for macOS). If no target is specified at all it defaults to macos26_helix_arm64 (baremetal Apple Silicon via Helix).

You don't have to spell out the full name — EgorBot resolves shorthands:

NOTE: 32-bit arm and windows targets are currently not available (let me know if you need them).

Full target list:

Multiple targets can be specified in a single command.
NOTE: Use AWS targets only when absolutely necessary since these targets are not free for me.

• No target → macos26_helix_arm64
• In a PR comment with no -commits → automatically compares PR_<number> vs main
• No code block → runs benchmarks from dotnet/performance
• Unconsumed tokens after options/targets are passed as BDN arguments (e.g. --filter "*MyBench*")

Compare a PR against main on ARM:

@EgorBot -arm

Compare two specific commits on AMD Genoa:

@EgorBot -genoa -commits abc1234,def5678

Compare a specific commit against its previous commit on Cobalt 100:

@EgorBot -azure_arm -commits abc1234,abc1234~1

Compare a range of commits on Apple Silicon via Helix for a specific dotnet/performance benchmark:

@EgorBot -arm -commits abc1234...def5678 --filter "*MyBench*"

┌─────────────────────┐ ┌─────────────────────┐
│ EgorBot.Github │───────│ EgorBot.Server │
│ (Polls GH comments) │ │ (Orchestrates jobs) │
└─────────────────────┘ └──────┬──────────────┘
 │
 ┌────────────────┼───────────────┐
 ┌──────────┐ ┌──────────┐ ┌───────────┐
 │ Azure │ │ AWS │ │ Helix │
 │ VMs │ │ Instances│ │ Work Items│
 └────┬─────┘ └────┬─────┘ └─────┬─────┘
 └──────────────┼───────────────┘
 bdn-benchmarking-*.py

See docs/api.md for the public REST API documentation.