$ timeahead.in
/ servers/pypi/bernstein
pypi

bernstein

Deterministic orchestrator for 40+ CLI AI agents. Git worktree isolation, HMAC audit trail, MCP server mode. https://bernstein.run

712 stars32k/wkupdated 0d agogithub ↗
55poor
▣ Overview
CIPyPIGHCRPython 3.12+LicenseCodeQLOpen in Codespaces

What it does

Bernstein schedules 40+ CLI coding agents (Claude Code, Codex, Gemini CLI, and others) to work on a single goal in parallel, each in an isolated git worktree. The scheduler is deterministic—pure Python logic, no LLM in the coordination loop—so you can replay yesterday's plan and get yesterday's task graph. Every scheduling decision is HMAC-signed into an audit chain; every artifact write tracks its producer, inputs, prompt hash, model, and cost. The orchestrator serializes merges to prevent race conditions when multiple agents complete simultaneously.

Who it's for

Teams running three or more CLI coding agents and burning $1k+/month on agent calls. Operators in compliance-sensitive workflows who need tamper-evident audit trails and want credentials to stay in their environment, not in a SaaS hop. Platform teams rolling agents into client repos without storing external secrets.

Common use cases

  • Run 3+ agents on parallel worktrees against a single coding goal, merge serially without race conditions
  • Audit agent decisions: grep the plaintext HMAC-signed log to see what the orchestrator decided and why
  • Replay a previous run to verify determinism or reduce redundant model calls
  • Track artifact lineage: which agent produced each file, with what prompt, from what inputs, and at what cost
  • Drop agents into client repositories without storing API keys externally

Setup pitfalls

  • 173 secrets detected in codebase—review the security model in docs/security/ before deploying in compliance contexts
  • Requires Python 3.12+; verify compatibility with your agent CLIs before spawning
  • Filesystem write access required for worktree creation, audit logs, and artifact storage; plan disk space and consider sandboxing constraints
  • High risk classification—bearer-token auth and JWS agent cards have security implications; read the manager auth and audit log documentation before use in untrusted environments
173 credentials detected in repository history via Gitleaks
▣ Score BreakdownMCPScore = Σ(raw × weight)
DimensionRawWeighted
Security
35%
0
0.0
Freshness
25%
100
25.0
Adoption
20%
82
16.4
Quality
10%
90
9.0
Trust
10%
50
5.0
Total
55.4
⚿ Capabilities & Risk Explainer
fs readfs writenetworkexecevalsecrets
◆ Risk level: high· 8 tools · auth: API key
fs read + fs write + network + exec + eval + secrets active — can execute code, access credentials, and make external network calls.
Tool nameDescriptionDestructive?
verify_chain✓ no
bernstein_health✓ no
bernstein_run⚠ yes
bernstein_status✓ no
bernstein_tasks✓ no
+3 more tools
bernstein_cost✓ no
bernstein_approve✓ no
bernstein_create_subtask✓ no
⚙ Install config
Claude Desktop · Cursor · Windsurf · VS Code (Copilot) · Claude Code
add to your MCP client config:
{
  "mcpServers": {
    "bernstein": {
      "command": "uvx",
      "args": [
        "bernstein"
      ]
    }
  }
}
📈 Score historylast 46 snapshots
5/10/20267/21/2026 · 46 snapshots
⚙ Maintenance health
63/ 100 · is this project alive?
contributors (1y)11
top contributor share71%
releases (1y)100
last release1d ago
median issue response2.8d
ci⚠ failing
⛁ Raw data
weekly downloads32k
github stars712
forks68
open issues74
license✓ present
readme length62741 chars
last publish0d ago
last commit0d ago
last updated5d ago
install verified✓ pass · 70d ago
owner of this server? claim your listing to get a verified badgeclaim →
🔔 Score drop alerts
get notified by email when this server's score drops 5+ points