How much does Bernstein cost?

Free and open source under Apache 2.0 with no paid tier; installs via pip, pipx, uv, brew, and npm. The real cost of a run is the metered spend of the underlying coding agents it orchestrates, which the built in cost aware dispatch can cap in USD.

Does Bernstein support MCP and tool calling?

Full under the Agentic Index verification standard. Bernstein publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: MCP server mode over stdio, HTTP, and SSE plus a stateless chain anchored MCP core and an MCP Tasks surface, a task server REST API with an OpenAPI reference, a documented adapter guide for adding custom agents, and a generic CLI wrapper; A. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Bernstein have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Bernstein publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: Documented product security capability is unusually deep for a dev tool: sandbox isolation via Docker, E2B, or Modal, per agent credential scoping, SPIFFE identity, an air gap install profile with deny all egress and signed verification, PI. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can Bernstein be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Bernstein publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: Runs entirely where the user chooses: installs via pip, pipx, uv, brew, and npm, state local in .sdd with no server to provision, cluster mode, a Cloudflare Workers backend, Kubernetes and Docker extras, and a documented air gap installatio. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Bernstein

Q: Who is Bernstein for?

developers, platform teams, consultancies and forward deployed engineers, compliance sensitive engineering teams

Q: What are the best alternatives to Bernstein?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Bernstein among agent infrastructure platforms are Vapi, LangSmith, Pipecat, Windmill. Each is graded on the same public evidence, and no vendor pays for placement.

Also known as: bernstein.run, Bernstein orchestrator, bernstein-orchestrator

Visit site

Agent infrastructureindependentVerified 2026-08-08

Entry priceFree and open source (Apache 2.0)Full pricing detail

Open source deterministic orchestrator that runs 40 plus CLI coding agents such as Claude Code, Codex, and Gemini CLI in parallel git worktrees with no model in the coordination loop, so runs replay byte identically behind an HMAC signed audit chain.

Bernstein takes a software goal, decomposes it into a task graph with a single upfront model call, and then hands coordination to deterministic Python: scheduling, worktree isolation, verification gates, and merging are auditable code rather than model responses, spending zero LLM tokens on coordination. Each task runs a CLI coding agent in its own isolated git worktree, with more than 40 adapters spanning Claude Code, Codex, Gemini CLI, Cursor, Aider, GitHub Copilot CLI, the OpenAI Agents SDK, AWS Q Developer, and a generic wrapper for any CLI tool, so agents are interchangeable workers and cheap local models can mix with cloud models in the same run. A janitor system checks tests, lint, types, and PII before any output lands, with optional cross model review and tournament selection where no model sits in the decision path, and cost aware dispatch enforces USD caps across a run. The accountability layer is the distinctive part: an always on signed lineage spine, a replay journal, content addressed evidence bundles, and an opt in HMAC chained audit log let a reviewer verify what happened offline without rerunning anything, which the project pitches at client compliance review in forward deployed engineering work. Deployment is wherever Python runs: pipx, brew, or npm installs, a cluster mode, a Cloudflare Workers backend, pluggable sandboxes including Docker, E2B, and Modal, per agent credential scoping, SPIFFE identity, and an air gap install profile with deny all egress and signed verification. Bernstein is Apache 2.0, free, solo maintained by Alex Chernysh, and carries independent visibility through awesome-python, Python Weekly, MCP catalogs, and orchestrator roundups.

Vendor details

Canonical URL

https://bernstein.run

Subcategory

Deterministic multi-agent orchestration

Funding status

No funding disclosed; solo maintained open source project

Company status

independent

Use cases & customers

Primary use cases

Running multiple CLI coding agents in parallel against one goal with automatic decomposition and mergeReproducible, byte identical agent runs for regulated or review heavy codebasesOffline verification of agent work through signed lineage and an HMAC audit chainCost controlled multi agent dispatch mixing local and cloud models under USD capsAir gapped or client site agent orchestration with per agent credential scoping

Target customers

developersplatform teamsconsultancies and forward deployed engineerscompliance sensitive engineering teams

Deployment options

self-hostedair-gappedclusterCloudflare Workers backendGitHub Action

Integrations

More than 40 CLI agent adapters including Claude Code, Codex CLI, Gemini CLI, Cursor, Aider, GitHub Copilot CLI, OpenAI Agents SDK, Goose, OpenHands, and AWS Q Developer, plus a generic CLI wrapper; pluggable sandboxes (Docker, E2B, Modal); artifact storage on S3, GCS, and R2; chat bridges for Slack, Discord, and Telegram; MCP server mode over stdio, HTTP, and SSE; a task server REST API.

In practice

A platform team points Bernstein at a refactor goal; it splits the work across Claude Code, Codex, and Aider in parallel worktrees, gates every merge on tests and lint, and leaves a clean git history.

A consultancy stands up an AI engineering crew on a client repo in minutes, keeps its own keys scoped per agent, and hands the client an HMAC signed audit record replayable for compliance review.

A reviewer checks what a multi agent run actually did by replaying its journal and verifying the signed lineage offline, without rerunning any agent or trusting a model narrative.

Sources & related URLs

Related / legacy domains

https://bernstein.readthedocs.io https://github.com/sipyourdrink-ltd/bernstein https://pypi.org/project/bernstein/

Research sources

https://bernstein.run/ https://bernstein.readthedocs.io/en/latest/ https://github.com/sipyourdrink-ltd/bernstein https://pypi.org/project/bernstein/ https://github.com/marketplace/actions/bernstein-multi-agent-orchestration

Agentic Index coverage score

10.5 / 14 capabilities · 75%

Integrations & Tool CallingMore than 40 CLI agent adapters (Claude Code, Codex, Gemini CLI, Cursor, Aider, GitHub Copilot CLI, OpenAI Agents SDK, AWS Q Developer and more) plus a generic wrapper for any CLI tool, pluggable sandboxes (Docker, E2B, Modal), artifact storage on S3, GCS, and R2, and chat bridges for Slack, Discord, and Telegram. Bernstein docs and PyPI Aug 2026	Full
Workflow OrchestrationOrchestration is the product: a goal decomposes into a task graph, deterministic Python schedules agents in parallel git worktrees, a documented lifecycle FSM governs task and agent states, multi stage plans run from plan.yaml, and verified results merge automatically. Bernstein docs Aug 2026	Full
Knowledge Grounding & RAGNo knowledge base, retrieval, or grounding layer is documented; agents ground in the repository itself and the .sdd workspace holds run state rather than knowledge. Bernstein docs Aug 2026	Unable to verify
Human Oversight & GuardrailsEvery merge is gated by janitor checks and quality gates, a run review board surfaces completed work for human judgment, and the PR flow keeps humans on the merge; there is no first class inline approval primitive that pauses an agent mid run for sign off. Bernstein docs and site Aug 2026	Partial
Security, Identity & GovernanceDocumented product security capability is unusually deep for a dev tool: sandbox isolation via Docker, E2B, or Modal, per agent credential scoping, SPIFFE identity, an air gap install profile with deny all egress and signed verification, PII checks in the janitor, and an HMAC signed audit chain. As a self hosted open source tool with no hosted service there are no organizational attestations to hold; graded on documented capability. Bernstein docs Aug 2026	Full
Observability & AuditabilityAuditability is the thesis: an always on signed lineage spine, a deterministic replay journal, content addressed evidence bundles, an opt in HMAC chained audit log a reviewer can verify offline without rerunning, a live TUI dashboard, and an observability extra with OpenTelemetry support. Bernstein site and docs Aug 2026	Full
Memory & State PersistenceState persistence is strong: a durable ledger resumes runs on another machine, a replay journal and content addressed evidence bundles preserve every step, and workspace state lives in .sdd with no server to provision. Learned memory across runs in the agent sense is not documented. Bernstein site release notes Aug 2026	Partial
Deployment & Data ResidencyRuns entirely where the user chooses: installs via pip, pipx, uv, brew, and npm, state local in .sdd with no server to provision, cluster mode, a Cloudflare Workers backend, Kubernetes and Docker extras, and a documented air gap installation profile with a wheelhouse build and deny all egress. Bernstein docs Aug 2026	Full
Prebuilt Agents, Templates & PacksProgressive skills and reusable plan.yaml multi stage plans ship with the tool, and the adapter guide documents adding agents, but there is no gallery of prebuilt agents or packaged templates; the adapters are workers rather than prebuilt roles. Bernstein docs Aug 2026	Partial
Triggers & Channel CoverageRuns start from the CLI, from schedules, from PR automation and an autofix daemon, from chat bridges, from a GitHub Action, and from MCP clients via server mode; detached runs continue without a foreground session. Bernstein operator docs and GitHub Marketplace listing Aug 2026	Full
Model Flexibility & RoutingAny agent, any model, any provider by design: adapters are interchangeable, cheap local models mix with cloud models in one run, cost aware dispatch enforces USD caps, and tournament selection plus optional cross model review pick outputs with no model in the decision path. Bernstein docs and site Aug 2026	Full
APIs, SDKs & MCP ExtensibilityMCP server mode over stdio, HTTP, and SSE plus a stateless chain anchored MCP core and an MCP Tasks surface, a task server REST API with an OpenAPI reference, a documented adapter guide for adding custom agents, and a generic CLI wrapper; Apache 2.0 source is itself extensible. Bernstein docs Aug 2026	Full
Testing, Debugging & OptimizationJanitor verification gates every merge on tests, lint, types, and PII, cross model review and tournament selection compare candidate outputs, deterministic replay makes any run debuggable after the fact, an eval extra ships on PyPI, and the project publishes its own benchmarks page. Bernstein docs Aug 2026	Full
Browser & Computer UseNo browser or computer use capability documented; the domain is CLI coding agents operating on repositories in worktrees and sandboxes. Bernstein docs Aug 2026	Unable to verify

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

Free and open source (Apache 2.0)

none

Free tier

Included quota

No quotas or tiers; full feature set ships in the Apache 2.0 build including cluster mode, air gap profile, and the MCP and REST surfaces

What is public

Everything: the tool is Apache 2.0 with public source, public docs, public benchmarks, and no paid tier anywhere

Billing mechanics

No billing; costs accrue only in the orchestrated agents (Claude Code, Codex, Gemini CLI and others) and any paid sandbox or storage backends the user configures; built in cost aware dispatch can enforce a USD cap per run

Cost watchouts

Parallel orchestration multiplies underlying agent subscription and API costs; sandbox backends E2B and Modal are paid third party services if used; solo maintainer with no commercial support offering

Variable cost rationale

The orchestrator is free but total run cost is the metered spend of the underlying coding agents it fans out in parallel, which scales with concurrency and model choice; the project exists because parallel agent bills reached hundreds of dollars a month, and it ships cost aware dispatch with USD caps as the control

Overage / add-ons

Not applicable; no paid product exists

Sales call required

No, self serve available

Free / trial

Entirely free; installs via pip, pipx, uv, brew, or npm

Lowest paid plan

None; free and open source

Commercial notes

Solo maintained by Alex Chernysh under sipyourdrink-ltd; sponsorship link published; roughly 11k PyPI downloads a month with independent listings in awesome-python, Python Weekly, and MCP catalogs

Key ambiguities

None on price; the open question for buyers is support and continuity, since no commercial entity stands behind the project

Missing data

No commercial support, SLA, or paid escalation path exists to price

Agentic Index verified 2026-08-08

Official pricing page

Related vendors

Alternatives to Bernstein

The closest documented capability profiles to Bernstein among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Vapi10.5 / 14Adds documented Knowledge Grounding & RAG
LangSmith9.0 / 14A lighter documented profile than Bernstein
Pipecat10.0 / 14Adds documented Knowledge Grounding & RAG
Windmill10.0 / 14Fuller documented coverage on Human Oversight & Guardrails
Inngest10.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Memory & State Persistence
Paragon11.5 / 14Adds documented Knowledge Grounding & RAG

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Bernstein with other vendors →Compare all agent infrastructure platforms →See where Bernstein ranks →

Data confidence: medium