Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run
Perfect health and docs; Python loses typed-language point, dep manifest unconfirmed from provided data.
HMAC-chained audit log, Ed25519 signed agent cards, 44 CLI adapters — compliance-grade coding agent orchestration.
Per-artefact lineage traces every file write to producer, prompt SHA, model, and cost.
| Rating | Summary | |
|---|---|---|
| Quality | excellent (22/24) | Perfect health and docs with 44 CLI adapters, HMAC audit chain, and active v2.7.0 release; docked for Python (not typed) and unconfirmed dep count. |
| PAI Relevance | integrate (0.75) | Novel compliance orchestration patterns directly applicable to PAI's Delegation subsystem; subprocess-wrappable as a PAI skill despite Python runtime. |
22/24 — actively-maintained / well-documented / solid
Failed:
Passed:
Failed:
Passed:
bernstein init, bernstein run -g "...", and bernstein lineage verify <run_id>Failed:
Passed:
pip install bernstein is documented; PyPI publication confirms pyproject.toml or equivalent manifest exists| Dimension | Score | Assessment |
|---|---|---|
| Harvest Value | 2 | The HMAC-SHA256 audit chain per RFC 2104, Ed25519-signed agent cards via JWS/JCS canonicalization, and per-artefact lineage model are novel architectural patterns directly applicable to PAI's Delegation and Agents orchestration subsystem, neither of which currently implements tamper-evident audit trails or per-output provenance. |
| Integration Readiness | 1 | Bernstein is Python, not TypeScript/Bun, so it cannot be bun add-ed; however it ships a clean CLI (bernstein run, bernstein lineage verify) installable via pipx, making subprocess invocation from a PAI skill straightforward with moderate adapter code. |
| Overlap Risk | 1 | Partial overlap with PAI's Delegation skill (parallel work routing) and Agents skill (agent composition); Bernstein's coding-agent-specific scope — git worktree isolation, merge queue serialization, and compliance audit chain — extends well beyond what those skills cover. |
| Gap Fill | 2 | PAI has no capability for compliance-grade multi-agent coding orchestration: no HMAC audit chain, no signed agent cards, no per-artefact lineage, no parallel git worktree management — all clear gaps in the current Capability Manifest. |
Composite: 0.75
Conservancy editorial loop: Install pip install bernstein and replace the Conservancy's current sequential editorial loop with a Bernstein crew that runs Claude Code and Gemini CLI as parallel agents in separate git worktrees — the merge queue serializes landing so competing "extinction entry" generators never clobber each other, and the HMAC audit chain produces a signed provenance record (prompt SHA + model + cost) for every published article, making the satirical editorial pipeline auditable end-to-end.
Capture-to-Knowledge Pipeline: Write a crew.yaml defining capture, extraction, Haiku validation, and synthesis as discrete Bernstein agent stages — the per-artefact lineage mechanism links every output knowledge node back to its source document + the exact prompt SHA + model that processed it, replacing the current manual stage handoffs with a deterministic, replayable pipeline that survives any individual stage failure and can be replayed from the last HMAC-verified checkpoint.
PAI multi-agent task dispatch: Register Claude Code alongside a second CLI coding agent (Codex or Gemini CLI) as a Bernstein crew for any PAI task that fans out across ≥2 parallel worktrees — the zero-LLM scheduler keeps coordination costs at $0 and the Ed25519-signed agent cards give every scheduled task a tamper-evident record of which agent executed it, turning ad-hoc parallel agent runs into auditable, reproducible operations.
Category: AI Agent Frameworks
In this category: lobehub--lobehub, VoltAgent--voltagent, bmad-code-org--BMAD-METHOD, tkellogg--open-strix, zeenie-ai--MachinaOS, gastownhall--gastown, gordonbrander--busytown, humanlayer--12-factor-agents, NorthwoodsSentinel--meridian-protocol
Standing: Bernstein is the first compliance-grade coding agent orchestrator appraised in this category — uniquely positioned by its HMAC audit chain and signed agent cards versus the general-purpose agent frameworks already on file; nearest structural peers are gastownhall--gastown (multi-agent workspace) and VoltAgent--voltagent (agent engineering platform), but neither ships tamper-evident audit infrastructure or coding-agent-specific worktree isolation.
Density: 9/10 — Available: full README (8KB, substantive), repo metadata (stars, forks, issues, license, dates, topics), latest release tag, CI badge signals, language, archived status, PyPI publication evidence. Missing: dependency manifest (not retrieved), test file listing, contributor count, downstream dependents.
Bernstein is solo-maintained (chernistry) and explicitly says so — the "no vendor SLA, GitHub issues only" caveat is real risk for production adoption. The repo is 71 days old at appraisal with 541 stars and v2.7.0 already released, indicating unusually fast iteration velocity. The air-gap deploy profile (wheelhouse path documented, no SaaS hop, file-based .sdd/ state) makes it credible for enterprise-sensitive environments where other orchestrators route through a cloud data plane. The deterministic scheduler's hard wall against emergent agent collaboration is an intentional design choice, not a limitation — worth flagging for any PAI use case that requires adaptive coordination rather than reproducible replay.