Skip to content

ralph-orchestrator

v2.10.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai ai-agents ai-agents-framework ai-developer-tools claude-code claude-code-cli
+9 more
codex-cli development-tools development-workflow gemini-cli kiro kiro-cli opencode ralph-loop ralph-wiggum

Summary

AI summary

Updates Release Notes, Install ralph-bench 2.10.0, and Install ralph-cli 2.10.0 across a mixed release.

Full changelog

Release Notes

Added

  • Forge CLI backend integration.
  • RObot (human-in-the-loop) RPC domain in the control plane, plus a file-backed web mode that drives human interaction through files instead of a live socket.
  • Worktree loops can publish remote review branches, with rebase support.
  • Local file-based hat imports in preflight, including import resolution and schema validation with imported-file context.
  • On-demand export of TUI iteration buffers to disk: e exports the current iteration, E exports all iterations.
  • Context-window utilization telemetry, surfaced in the TUI.

Changed

  • Updated the Pi backend package reference to @earendil-works/pi-coding-agent.
  • Refreshed agent waves observability documentation and added the hat imports design spec.

Fixed

  • TUI search mode now captures typed query characters instead of leaking them to keybindings (e.g. an e in the query no longer triggers export); the Search: prompt, N/M match counter, and n/N navigation work again.
  • Runtime now requires an explicit completion signal after guidance, preventing premature loop termination.
  • Persist loop continue state across iterations.
  • Honor per-hat scratchpad configuration in generated instructions.
  • Drain ACP terminal output before exit so the final output is no longer truncated.
  • Canonicalize Ralph artifact paths to avoid path-mismatch errors.
  • Deduplicate MCP tool schemas exposed over the API.

ralph-bench 2.10.0

Install ralph-bench 2.10.0

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/mikeyobrien/ralph-orchestrator/releases/download/v2.10.0/ralph-bench-installer.sh | sh

Install prebuilt binaries into your npm project

npm install @ralph-orchestrator/[email protected]

Download ralph-bench 2.10.0

| File | Platform | Checksum |
|--------|----------|----------|
| ralph-bench-aarch64-apple-darwin.tar.xz | Apple Silicon macOS | checksum |
| ralph-bench-x86_64-apple-darwin.tar.xz | Intel macOS | checksum |
| ralph-bench-aarch64-unknown-linux-musl.tar.xz | ARM64 MUSL Linux | checksum |
| ralph-bench-x86_64-unknown-linux-musl.tar.xz | x64 MUSL Linux | checksum |

ralph-cli 2.10.0

Install ralph-cli 2.10.0

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/mikeyobrien/ralph-orchestrator/releases/download/v2.10.0/ralph-cli-installer.sh | sh

Install prebuilt binaries into your npm project

npm install @ralph-orchestrator/[email protected]

Download ralph-cli 2.10.0

| File | Platform | Checksum |
|--------|----------|----------|
| ralph-cli-aarch64-apple-darwin.tar.xz | Apple Silicon macOS | checksum |
| ralph-cli-x86_64-apple-darwin.tar.xz | Intel macOS | checksum |
| ralph-cli-aarch64-unknown-linux-musl.tar.xz | ARM64 MUSL Linux | checksum |
| ralph-cli-x86_64-unknown-linux-musl.tar.xz | x64 MUSL Linux | checksum |

ralph-api 2.10.0

Install ralph-api 2.10.0

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/mikeyobrien/ralph-orchestrator/releases/download/v2.10.0/ralph-api-installer.sh | sh

Install prebuilt binaries into your npm project

npm install @ralph-orchestrator/[email protected]

Download ralph-api 2.10.0

| File | Platform | Checksum |
|--------|----------|----------|
| ralph-api-aarch64-apple-darwin.tar.xz | Apple Silicon macOS | checksum |
| ralph-api-x86_64-apple-darwin.tar.xz | Intel macOS | checksum |
| ralph-api-aarch64-unknown-linux-musl.tar.xz | ARM64 MUSL Linux | checksum |
| ralph-api-x86_64-unknown-linux-musl.tar.xz | x64 MUSL Linux | checksum |

ralph-e2e 2.10.0

Install ralph-e2e 2.10.0

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/mikeyobrien/ralph-orchestrator/releases/download/v2.10.0/ralph-e2e-installer.sh | sh

Install prebuilt binaries into your npm project

npm install @ralph-orchestrator/[email protected]

Download ralph-e2e 2.10.0

| File | Platform | Checksum |
|--------|----------|----------|
| ralph-e2e-aarch64-apple-darwin.tar.xz | Apple Silicon macOS | checksum |
| ralph-e2e-x86_64-apple-darwin.tar.xz | Intel macOS | checksum |
| ralph-e2e-aarch64-unknown-linux-musl.tar.xz | ARM64 MUSL Linux | checksum |
| ralph-e2e-x86_64-unknown-linux-musl.tar.xz | x64 MUSL Linux | checksum |

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track ralph-orchestrator

Get notified when new releases ship.

Sign up free

About ralph-orchestrator

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

All releases →

Related context

Beta — feedback welcome: [email protected]