Skip to content

chernistry/bernstein

v1.8.13 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-framework agent-orchestrator agentic-ai ai-agents ai-coding aider
+14 more
anthropic claude-code cli-tool codex-cli coding-agent deterministic-scheduler hmac-audit llm mcp-server model-context-protocol multi-agent parallel-worktrees python swe-bench

Summary

AI summary

Two new scripts simplify first‑time install, checking Python 3.12+, bootstrapping pipx and handling macOS brew or Windows paths.

Full changelog

v1.8.13 — one-line install

Two new scripts take the friction out of first-time install. They check for Python 3.12+, bootstrap pipx via ensurepip + pip install --user when it's missing, fix PATH for the current session, and install (or upgrade) bernstein. The shell script handles brew-managed macOS environments; the PowerShell script prefers the py -3 launcher and falls back to python / python3.

curl -fsSL https://get.bernstein.dev/install.sh | sh

Thanks to @vedangit for picking up the issue and driving it through — including the brew edge cases and the Windows paths.

Also in this release

  • README gained a CLI-agent orchestrator comparison row next to the existing framework table, with a "last verified" date stamp.
  • glama.json added for the glama.ai MCP directory.
  • lxml bumped in the uv dependency group (Dependabot).

Full changelog: https://github.com/chernistry/bernstein/compare/v1.8.12...v1.8.13

View diff on GitHub

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

Share on X Share on Bluesky

Track chernistry/bernstein

Get notified when new releases ship.

Sign up free

About chernistry/bernstein

Deterministic multi-agent orchestrator for 18 CLI coding agents (Claude Code, Codex, Cursor, Aider, Gemini CLI, OpenAI Agents SDK, and more). MCP server mode (stdio + HTTP/SSE) exposes the orchestrator to any MCP client. Git worktree isolation per agent, HMAC-chained audit trail, cost-aware model routing via contextual bandit. ~11K monthly PyPI downloads, Apache 2.0.

All releases →

Related context

Beta — feedback welcome: [email protected]