Skip to main content

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.

Featured · read first
15 min read

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.

multi-agent orchestrationreleasedeterministic replayaudit log
13 min read

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.

multi-agent orchestrationreleasecost controloutput economy
18 min read

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.

multi-agent orchestrationreleaselineageaudit log
4 min read

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.

multi-agent orchestrationreleaseweb UIFastAPI
7 min read

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.

multi-agent orchestrationreleaseAGENTS.mdA2A
9 min read

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.

multi-agent orchestrationclusterenterpriseaudit-trail
4 min read

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.

multi-agent orchestrationadapterscomposioralphex
5 min read

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.

multi-agent orchestrationCIGitHub Actionsdeveloper experience
3 min read

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.

multi-agent orchestrationreleaseACPCI
5 min read

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.

multi-agent orchestrationdeveloper experienceCLI toolsAI coding agents
3 min read

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.

multi-agent orchestrationdeveloper experienceAI coding agentsTelegram
3 min read

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.

open sourcedeveloper experienceonboardingCLI installers
5 min read

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.

multi-agent codingagent orchestrationAI coding agentsdeveloper tools
3 min read

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.

multi-agent orchestration tutorialAI coding agents setupClaude Code tutorialgetting started
2 min read

community spotlight: april 2026 bernstein contributors

first community spotlight. contributors who shaped bernstein's architecture decomposition, adapter list, windows support, cost-aware router.

communityopen-sourcecontributorsmulti-agent orchestration
3 min read

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.

Cloudflare Workerscloud AI agentsserverless orchestrationmulti-agent orchestration
4 min read

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.

Python refactoringcode decompositionmulti-agent orchestrationarchitecture
3 min read

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.

AI cost optimizationmodel routingcontextual banditmulti-agent orchestration
2 min read

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.

multi-agent orchestrationAI coding agentsClaude Codeopen-source