Web dashboard — real-time task monitoring, cost tracking, agent status
Homepage | Documentation | Getting Started | Known Limitations
If you're running one agent at a time, you're leaving performance on the table. Bernstein takes a goal, breaks it into tasks, assigns them to AI coding agents running in parallel, verifies the output, and commits the results. You come back to working code, passing tests, and a clean git history.
No framework to learn. No vendor lock-in. Works with Claude Code, Codex, Gemini CLI, Cursor, Aider, Amp, Roo Code, Goose, Qwen, and any CLI tool that accepts a prompt flag.
Think of it as what Kubernetes did for containers, but for AI coding agents. You declare a goal. The control plane decomposes it into tasks. Short-lived agents execute them in isolated git worktrees -- like pods. A janitor verifies the output before anything lands.
pip install bernstein # any platform
# or
pipx install bernstein # isolated install
# or
uv tool install bernstein # fastest (Rust-based)
# or
brew tap chernistry/bernstein && brew install bernstein # macOS / Linux
# or
sudo dnf copr enable alexchernysh/bernstein && sudo dnf install bernstein # Fedora / RHEL
# or
npx bernstein-orchestrator # npm wrapper (requires Python 3.12+)
# Run:
bernstein -g "Add JWT auth with refresh tokens, tests, and API docs"1.78× faster than single-agent execution, verified on internal benchmarks. See benchmarks for methodology and reproduction steps.
Bernstein is a deterministic orchestrator for CLI coding agents. It schedules tasks in parallel across any installed agent — Claude Code, Codex, Cursor, Gemini, Aider, and more — with git worktree isolation, janitor-verified output, and file-based state you can inspect, back up, and recover from. No vendor lock-in. No framework to learn. Your agents, your models, your backlog.
# 1. Install (pick one — full list in the install block above)
pipx install bernstein
# 2. Init your project (creates .sdd/ workspace + bernstein.yaml)
cd your-project
bernstein init
# 3. Run — pass a goal inline or let bernstein.yaml guide the run
bernstein -g "Add rate limiting and improve test coverage"
# 4. Stop when done
bernstein stopThat's it. Your agents spawn, work in parallel, verify their output, and exit. Watch progress in the terminal dashboard.
Bernstein ships with adapters for 12 CLI agents. If you have any of these installed, Bernstein uses them — no API key plumbing required:
| Agent | Models | Install |
|---|---|---|
| Aider | Any OpenAI/Anthropic-compatible model | pip install aider-chat |
| Amp | opus 4.6, gpt-5.4 | brew install amp |
| Claude Code | opus 4.6, sonnet 4.6, haiku 4.5 | npm install -g @anthropic-ai/claude-code |
| Codex CLI | gpt-5.4, o3, o4-mini | npm install -g @openai/codex |
| Cursor | sonnet 4.6, opus 4.6, gpt-5.4 | Cursor app (sign in via app) |
| Gemini CLI | gemini-3-pro, 3-flash | npm install -g @google/gemini-cli |
| Goose | Any provider | Install Goose CLI |
| Kilo | Configurable | npm install -g kilo |
| Kiro | Multi-provider | Install Kiro CLI |
| OpenCode | Multi-provider | Install OpenCode CLI |
| Qwen | qwen3-coder, qwen-max | npm install -g qwen-code |
| Roo Code | opus 4.6, sonnet 4.6, gpt-4o | VS Code extension (headless CLI) |
Prefer a different agent? Bring your own -- the generic adapter accepts any CLI tool with a --prompt-flag interface. Mix models in the same run: cheap free-tier agents for boilerplate, heavy models for architecture.
Tip
Run bernstein --headless for CI pipelines -- no TUI, structured JSON output, non-zero exit on failure.
Only capabilities that ship with v1.4.11. Full matrix at FEATURE_MATRIX.md.
- Deterministic scheduling — zero LLM tokens on coordination. The orchestrator is plain Python.
- Parallel execution — spawn multiple agents across roles (backend, qa, docs, security) simultaneously.
- Git worktree isolation — every agent works in its own branch. Your main branch stays clean.
- Janitor verification — concrete signals (tests pass, files exist, no regressions) before anything lands.
- Quality gates — lint, type-check, PII scan, and mutation testing run automatically after completion.
- Plan files — multi-stage YAML with stages and steps, like Ansible playbooks (
bernstein run plan.yaml). - Cost tracking — per-model spend, tokens, and duration (
bernstein cost). - Live dashboards — terminal TUI (
bernstein live) and browser UI (bernstein dashboard). - Self-evolution — analyze metrics, propose improvements, sandbox-test, and auto-apply what passes (
--evolve). - CI autofix — parse failing CI logs, create fix tasks, route to the right agent (
bernstein ci fix <url>). - Circuit breaker — halt agents that repeatedly violate purpose or crash.
- Token growth monitor — detect runaway token consumption and intervene automatically.
- Cross-model verification — route completed task diffs to a different model for review.
- Audit trail — HMAC-chained tamper-evident logs with Merkle seal verification.
- Pluggy plugin system — hook into any lifecycle event.
- Multi-repo workspaces — orchestrate across multiple git repositories as one workspace.
- Cluster mode — central server + remote worker nodes for distributed execution.
- MCP server mode — run Bernstein as an MCP tool server for other agents.
- 12 agent adapters — Claude, Codex, Cursor, Gemini, Aider, Amp, Roo Code, Kiro, Kilo, OpenCode, Qwen, Goose, plus a generic catch-all.
All methods install the same bernstein CLI.
| Method | Command |
|---|---|
| pip | pip install bernstein |
| pipx | pipx install bernstein |
| uv | uv tool install bernstein |
| Homebrew | brew tap chernistry/bernstein && brew install bernstein |
| Fedora / RHEL | sudo dnf copr enable alexchernysh/bernstein && sudo dnf install bernstein |
| npm (thin wrapper) | npx bernstein-orchestrator or npm i -g bernstein-orchestrator |
The npm wrapper requires Python 3.12+ on the system -- it delegates to pipx/uvx/python under the hood.
COPR targets: Fedora 41, 42 (x86_64, aarch64), EPEL 9, 10.
| Editor | Install |
|---|---|
| VS Code | code --install-extension alex-chernysh.bernstein or search "Bernstein" in Extensions |
| Cursor | Search "Bernstein" in Extensions, or install from Open VSX |
| Cursor (skills) | 8 built-in skills in packages/cursor-plugin/ |
bernstein live # interactive TUI dashboard (3 columns)
bernstein dashboard # open web dashboard in browser
bernstein status # task summary and agent health
bernstein ps # running agent processes
bernstein cost # spend breakdown by model and task
bernstein doctor # pre-flight: adapters, API keys, ports
bernstein recap # post-run: tasks, pass/fail, cost
bernstein retro # detailed retrospective report
bernstein trace <ID> # step-by-step agent decision trace
bernstein logs -f # tail live agent outputAgents appear in Activity Monitor / ps as bernstein: <role> [<session>] — no more hunting for mystery Python processes.
Hidden aliases kept for backward compatibility — not shown in --help:
| Alias | Canonical command | Notes |
|---|---|---|
overture |
init |
Init workspace (legacy name) |
downbeat |
start |
Start server and spawn manager (legacy name) |
score |
status |
Task summary and agent health (legacy name) |
For multi-stage projects, define stages and steps in a YAML plan file:
bernstein run plan.yamlThe plan skips manager decomposition and goes straight to execution. See templates/plan.yaml for the format and examples/plans/flask-api.yaml for a working example.
Prometheus metrics at /metrics — wire up Grafana, set alerts, monitor cost. OTLP telemetry initialization supports distributed tracing.
Pluggy-based plugin system. Hook into any lifecycle event:
from bernstein.plugins import hookimpl
class SlackNotifier:
@hookimpl
def on_task_completed(self, task_id, role, result_summary):
slack.post(f"#{role} finished {task_id}: {result_summary}")Install a GitHub App on your repository to automatically convert GitHub events into Bernstein tasks. Issues become backlog items, PR review comments become fix tasks, and pushes trigger QA verification.
bernstein github setup # print setup instructions
bernstein github test-webhook # verify configurationHire specialist agents from Agency (100+ agents) or define your own:
# bernstein.yaml
catalogs:
- name: agency
type: agency
enabled: trueThe spawner matches the best agent for each role using keyword-based role inference and affinity scoring.
Watch: terminal demo (GIF)
| Bernstein | Paperclip | CrewAI | AutoGen | LangGraph | |
|---|---|---|---|---|---|
| Orchestrator type | Deterministic code | LLM-driven | LLM-driven | LLM-driven | Graph + LLM |
| Agent model | Any CLI agent | OpenClaw, Claude, Codex | Python classes | Python agents | Nodes + edges |
| Parallel execution | Native | Task-based | Sequential | Async | Graph-based |
| Git isolation | Worktrees | None | None | None | None |
| Verification | Janitor + quality gates | None built-in | None built-in | None built-in | Conditional edges |
| Cost tracking | Built-in | Built-in | Manual | Manual | Manual |
| State persistence | File-based (.sdd/) | Database | In-memory | In-memory | Checkpointer |
| Self-evolution | Built-in | No | No | No | No |
| Plan files | YAML stages + steps | No | Python code | Python code | Python code |
| Org/business modeling | No | Yes (org charts, goals) | No | No | No |
Full comparison pages — detailed feature matrices, benchmark data, and "when to use X instead" guides for Paperclip, GitHub Agent HQ, Conductor, Crystal, Stoneforge, and single-agent workflows.
Built during a 47-hour sprint: 12 AI agents on a single laptop, 737 tickets closed (15.7/hour), 826 commits. Full write-up. Every design decision here is a direct response to those findings.
Bernstein's roadmap is public. Near-term work focuses on adoption and the governance moat; longer-term work on enterprise standards and distribution.
| Area | What | Status |
|---|---|---|
| Governance | Lifecycle governance kernel — guarded state transitions, typed events | Done |
| Governance | Governed workflow mode — deterministic phases, hashable definitions | Done |
| Governance | Model routing policy — provider allow/deny lists | Done |
| Governance | Immutable HMAC-chained audit log — tamper-evident, daily rotation | Done |
| Governance | Execution WAL — hash-chained write-ahead log, crash recovery, determinism fingerprinting | Done |
| Adoption | CI autofix pipeline — bernstein ci fix <url> and bernstein ci watch |
Done |
| Adoption | Comparative benchmark suite — orchestrated vs. single-agent proof | Done |
| Adoption | Agent run manifest — hashable workflow spec for SOC2 evidence | Done |
| Adoption | bernstein demo — zero-config first-run experience |
Done |
| Adoption | bernstein doctor — pre-flight health check |
Done |
| Area | What | Target |
|---|---|---|
| Enterprise | SSO/SAML/OIDC auth for multi-tenant deployments | H2 2026 |
| Governance | Time-based model policy constraints ("deny expensive providers during peak hours") | H2 2026 |
| Adoption | Verified SWE-Bench eval publication | In progress |
| Area | What | Target |
|---|---|---|
| Enterprise | Dynamic policy hot-reload without restart | 2026 |
| Adoption | JetBrains IDE extension | 2026 |
| Governance | Task-specific model constraints ("role=security must use opus-only") | 2026 |
Bernstein is free and open-source. If it saves you time, consider sponsoring:
All sponsorship proceeds fund development, infrastructure, and open-source sustainability.
PRs welcome. See CONTRIBUTING.md for setup, testing, and code style. Open an issue for bugs and feature requests.
Don't babysit agents. Set a goal, walk away, come back to working code.
What will your agents build first?