Field notes · open source · v3.8.3
Field notes from the orchestra pit.
Engineering deep-dives, community spotlights, and updates from the Bernstein project - written when something is worth writing down.
subscribe via RSS.
bernstein 3.x recap: deterministic replay, evidence bundles, tournament runs, and a run you can walk away from
The arc from 2.0 to 3.5.0, in one page. The 2.x line taught the orchestrator to do more. The 3.x line made each of those things carry its own proof: an always-on signed lineage spine, deterministic replay by default, content-addressed evidence bundles, a durable ledger that resumes on another machine, detached runs, tournament selection with no model in the decision path, cost-aware dispatch under USD caps, a run review board, SPIFFE identity, an MCP Tasks surface, a stateless chain-anchored MCP core, and provider-side context mutations recorded into the replay journal.
Running many agents on 2.16: the output-economy suite, safer summaries, and a lifecycle you can hold still
A walkthrough of what shipped across the 2.4 to 2.16 arc for operators running many agents at once: per-role response-style profiles, per-profile cost attribution, a three-arm cost-and-quality A/B harness, proactive context compaction with signed receipts, a credential-shaped-content gate on summaries, schema-enforced worker completion payloads, sha256-pinned team manifests, hold/release spawner control, per-agent run instrumentation, and the Windows adapter path fix.
bernstein 2.x recap: lineage, ten trackers, A2A capability cards, and a CI that started fixing itself
Thirteen releases since the 1.10 recap consolidated into nine themes: a per-artefact transparency log with Ed25519 signatures, ten tracker adapters from Jira to Plane, A2A capability cards, MCP client and server hardening, a Playwright sandbox for UI agents, a secrets broker, supply-chain coverage with SBOM and OSSF Scorecard, calibrated cost guards, and a web UI plus PWA in the wheel.
bernstein 2.0.0: a web UI ships in the wheel, CLI unchanged
Bernstein 2.0 ships a FastAPI + React web UI inside the wheel. CLI and TUI surfaces are unchanged, configs do not move, agents and adapters keep working.
bernstein 1.10.x recap: agents.md sync, a2a, cost guards
five point releases in five days: agents.md cross-cli sync, runtime cost guards, a2a v1.0 signed agent cards, four new cli adapters.
Shipping the orchestrator onto someone else's box
On-prem deployment notes for Bernstein 1.10: cluster mTLS, signed lineage, air-gapped install, lethal-trifecta capability gate. Not an install guide.
We orchestrate the orchestrators now: Composio + ralphex adapters
Bernstein adapters for Composio's @aoagents/ao and umputun/ralphex. Leaf-node delegation, not deep meta-orchestration: each runs as a single agent in a plan.
A daemon that closes its own pull requests
How the Bernstein autofix daemon turns a red CI run on a Bernstein-opened PR into a fix commit. Capability gating and budget caps keep it from being a footgun.
bernstein 1.9.0: ACP bridge, CI autofix daemon, keychain creds
ACP bridge so Zed can dispatch tasks, a daemon that closes its own pull requests, OS keychain credentials, sandboxed preview server with a public URL.
Four commands that take the glue out of multi-agent runs
Bernstein 1.8.14 ships pr, from-ticket, remote, hooks. The four shell snippets every multi-agent team ends up writing by hand, now built into the CLI.
Four commands that turn the orchestrator into a service
1.8.15 ships a chat bridge, mid-run approval, a tunnel wrapper, and a daemon installer. Less script you sit next to, more thing you install once.
The install we should have shipped at launch
Three months after launch Bernstein got a real curl | sh one-liner. It only happened because a community contributor picked up the issue we kept deferring.
orchestration primitive vs desktop ade: pick the right layer
multi-agent coding split into two shapes: orchestration primitives (bernstein, workz) vs desktop ades (emdash, conductor). when to reach for each.
getting started: first multi-agent claude code run in 5 min
install bernstein, point it at claude code (or codex/gemini cli), run a goal in parallel, read the tui. five minutes if python 3.12 is ready.
community spotlight: april 2026 bernstein contributors
first community spotlight. contributors who shaped bernstein's architecture decomposition, adapter list, windows support, cost-aware router.
agents on cloudflare: workers, durable objects, r2, d1
bernstein 1.8.4 cloudflare backend for ai coding agents: workers run agents, durable workflows handle multi-step tasks, r2 + d1 hold state.
refactor a 4,000-line python file with 11 parallel ai agents
11 parallel ai coding agents split a 4,198-line python file into 22 sub-packages in three hours. how the decomposition pass actually ran.
Picking a cheaper model when the task allows
Bernstein's epsilon-greedy bandit picks a model per task. Internal runs cut roughly in half. Measure your own with bernstein cost.
bernstein 1.0: open-source orchestrator for ai coding agents
Orchestrate Claude Code, Codex, Gemini CLI + 40 other CLI coding agents in parallel git worktrees. Deterministic scheduler, HMAC-signed audit chain.