Every shipped thing.

This Mac only actually filters to this machine

Projects no longer uses the org’s last-heartbeating executor as “this Mac” (that flipped between machines). Identity comes from this install’s clientId; This Mac only only lists folders registered on that id. Link folder / Clone here still attach the same Bitbucket remote on another disk.

• Local device identity from ~/.grain/config.json (not org executorClientId)
• Strict This Mac only — no unscoped paths from other machines
• Mac 0.7.51 on download.grain.sh

Multi-Mac projects: same Bitbucket remote, unique folder per machine

Studio and laptop can both connect to the same org and git remotes while each keeps its own local checkout path. Link folder / Clone here on the second machine. Mac 0.7.50 notarized on download.grain.sh (MinIO CDN).

• Mac desktop 0.7.50 notarized + auto-update on download.grain.sh
• Per-machine devicePaths
• Import merges by Bitbucket/GitHub remote across Macs

Grok CLI detection, multi-Mac project paths, Workrooms control plane

Desktop finds the official Grok Build install at ~/.grok/bin (Token Max no longer shows NOT DETECTED when Grok is open in Terminal). Projects keep a separate local folder per machine. Workrooms listLanes is live; Mac download is 0.7.48 notarized.

• Mac desktop 0.7.48 notarized — Grok path probe + Refresh detection
• Per-machine project paths (Studio vs laptop unique folders)
• Workrooms control plane: listLanes, agent runs, soft fail UI
• Privacy + Terms (Macrodeep Inc.) on grain.sh

Workrooms, fleet routing, team templates — go-live ready

Missions become Workrooms with chat, Run-on, and artifacts. One-click agent teams with role assignment. Preferred computer on web, Slack, iOS, WhatsApp, automations. Offline pin shows a waiting banner with re-route. Slack: /grain on, devices, preferred. Pricing: Starter $49 / Pro $199.

• Workrooms + artifacts; team templates assign roles / open bidding
• Preferred device on all major create paths; waiting-for-device UX
• Slack: `/grain on Studio Mac …`, `/grain devices`, `/grain preferred`
• iOS TF 36: Devices admin + Workrooms / templates
• Devices fleet checklist; hide legacy grain-desktop when upgraded
• Canonical pricing Starter $49 · Pro $199

Name your computers; cloud executor hidden

Devices list shows only real Macs/PCs. Rename to Jesper’s Workstation / MacBook / Mini. docker-executor no longer appears as a fake second machine.

• Rename + Remove on Devices cards
• docker-executor filtered out of Run-on / Devices
• Desktop 0.7.42 full matrix re-ship

Multi-device Run-on + preferred computer

Create tasks with live computer chips: preferred machine auto-selected when online, free/busy status, per-machine execution defaults in Settings → Computers. Full desktop re-ship.

• New task: Run on computer chips for every live Mac/Win/Linux executor
• Auto-select ★ preferred computer when it is live
• Per-machine Plan/Implement defaults on Settings → Execution → Computers
• Desktop 0.7.41: Mac notarized Swift DMG, Windows NSIS, Linux deb + AppImage + one-click install

Kimi Code + multi-device routing on every desktop

Kimi Code CLI (K3) joins Claude Code / Codex / Grok as a first-class coding backend. Pick which Mac runs each task. Fresh installers for Mac, Windows, and Linux.

• Kimi Code CLI backend + Kimi K3 / K2.7 models in Settings, Agents, and task routing.
• Multi-device: Run on Mac 1 / Mac 2 with Free / Executing status on web + desktop.
• Desktop 0.7.40: Mac notarized Swift DMG, Windows NSIS, Linux one-click install script.

Plan approval, Live stream, Pipeline that actually runs

The three-phase pipeline is trustworthy end-to-end: see the plan, approve it, watch a real CLI stream, and let Grok implement with Codex plan/verify. Desktop 0.7.39 ships the same day on Mac, Windows, and Linux.

• Approve-before-implement: Plan phase posts a review card on the task Details drawer — approve or reject before Implement starts.
• Live agent stream redesigned for readability: wider drawer, larger CLI-style output, phase + model labels (Codex Sol / Grok / Codex Terra).
• Pipeline routing fixes: org defaults merge on claim, model↔backend coerce, Codex via `codex exec`, Grok via `--prompt-file` + always-approve.
• Verify NEEDS_WORK soft-fails into REVIEW instead of looking like a hard ERROR with a “What Looks Correct” dead-end.
• Settings Verify (and Plan / Implement) fields round-trip correctly — no more “unsaved” on reopen.
• Desktop installers: Mac notarized DMG, Windows NSIS, Linux deb + AppImage — all 0.7.39 with the fixed local executor.

Project scan that finishes

Scan & import no longer hangs for a minute on developer machines that keep large git clones under Documents.

• Stop descending once a `.git` folder is found (Swift parity with Rust) — no walking `node_modules` / `target`.
• Prefer `Documents/GitHub` over full Documents/Desktop; skip heavy directories.
• 12s native deadline + 15s UI timeout; lightweight inspect via `.git/config` + HEAD.

Scan local repos + multi-repo tasks

Import the projects you already have on disk, then attach two or three repos to a single task when the work spans more than one checkout.

• Scan & import wizard for local Git installs and folders; manual folder path and clone URL still work.
• Multi-repo tasks (2–3) for cross-repo work.
• Mac Swift + Tauri Win/Linux shell commands for scan / detect tools / find local repo.

Live activity across every CLI

See what the agent is doing in real time — tools, thinking, and status — whether the run uses Claude Code, Codex, Grok, Gemini, or OpenCode. Clearer than a black-box spinner.

• Live activity timeline on the task: Tool / Thinking / Status / Error / Done badges with step count and CLI label.
• Same strip appears in chat while the task is running so progress stays in view.
• Executor streams Codex / Grok / Gemini / OpenCode stdout into classified progress (not Claude-only anymore).
• Tool events also show as short system chips in chat (Reading file…, Running command…, Working…).
• QUESTION: option pickers, plan approve, and interactive mode still handle direction when the agent asks.
• Mac desktop 0.7.32 notarized with the streaming executor; use app.grain.sh or reinstall Mac for the full local path.

Desktop equal on Mac, Windows & Linux

Grain Desktop ships the same product quality on every OS. macOS stays on the native Swift shell; Windows and Linux use Tauri with a full executor supervisor — install once and local agents just work.

• Windows NSIS + Linux deb / AppImage / rpm at the same version as the notarized Mac DMG — download.grain.sh and grain.sh/download.
• Executor supervisor parity with Swift Mac: health adopt on :3212, free unhealthy ports, launch on start, re-check on focus (2s debounce).
• OS-aware PATH so CLIs resolve when the app is opened from Explorer / .desktop / Dock (npm, Scoop, nvm, cargo, ~/.local, Git for Windows, …).
• Tray + Grain menu on Win/Linux: Show, Check for Updates, Restart Local Executor, Open Logs, Quit.
• Settings / onboarding download CTAs point at real multi-platform installers (not “npm run executor only”).

Simple vs Pipeline — how tasks run

Settings → How tasks run is now two clear layers: pick Simple or Pipeline for day-to-day routing, and keep Reliability as an advanced group so power options stay out of the way.

• Simple mode for one-shot local CLI runs; Pipeline for multi-phase Plan → Implement → Verify.
• Fable → Codex is a recipe inside Pipeline (not a separate product surface).
• Reliability (advanced): Parallel multi-engine, Token Max rotation, Adaptive routing — grouped so defaults stay calm.
• Mac Swift DMG and Grain Mobile (build 31) ship the same Settings + llmConfig story.

Verify fix-loop — implement until it passes

The three-phase pipeline no longer stops at the first “needs work.” Implement and Verify loop until PASS or a hard fix-round cap.

• runThreePhasePipeline: on NEEDS_WORK, re-run implement with verifier feedback (max 3 fix rounds).
• iOS/iPad New Task: Plan / Implement / Verify CLI + model cyclers; mobile API stamps org llmConfig + overrides.
• Desktop embeds the new executor so local Mac installs get the loop without a separate CLI upgrade.

Plan & implement routing on desktop

Swift Mac embeds the latest web Settings at build time — including Plan & implement routing and a quieter install CTA when the local executor is already connected.

• Per-phase CLI + model defaults for Plan, Implement, and Verify.
• Hide the big “Download for Mac” banner when executor status is Connected or you are already inside the desktop shell.

Mac auto-update check

Grain Mac checks download.grain.sh/latest.json on launch and from Grain → Check for Updates…. Newer versions open the notarized DMG URL; Later snoozes for 24 hours.

GPT-5.6 Sol / Terra / Luna + Claude Sonnet 5.0

Model catalog refresh across plan pickers, Settings, and mobile. OpenAI GPT-5.6 Sol, Terra, and Luna join Anthropic Claude Sonnet 5.0 (`claude-sonnet-5`) with updated defaults and pricing.

Native Swift Mac shell + Tauri Win/Linux split

Desktop shells split by platform: macOS is a native Swift host for the shared React UI; Linux and Windows stay on Tauri. Same product, better native fit on each OS.

• Swift Mac: WKWebView shell, executor sidecar, Developer ID + notarized DMG.
• Grok CLI and Gemini CLI in Settings; Grok 4.5 default where appropriate.
• Notification dropdown reliability fixes on web + desktop.

Per-task control, Fable→Codex recipe, skills & reliability

Finer control when you create a task, a practical Fable-then-Codex path for long coding runs, and a tougher on-device executor.

• Per-task run mode + Full access (never ask) in the create form.
• Plan with Fable → build with Codex as an orchestration recipe (org default or per task).
• Skills library expanded (recursive planning, spec writing, implementation, visual review).
• Executor keeps polling during long browser/2FA waits; guided Setup tab; stuck-task recovery.

Local executor that stays awake + in-app auto-update

The desktop sidecar no longer wedges at startup or freezes mid-run. Auto-update is live for Mac via download.grain.sh/latest.json.

• Poll loop starts immediately; vault scans and stats never block first claim.
• Executor logs to ~/.grain/executor.log (no more full-pipe freezes).
• Growth Agent G4 monitoring + campaign loop self-heal; server browser publishing fixed.
• Multi-agent handovers record Gemini / Grok / Hermes context; Codex can resume sessions.

Live output surface + quieter channel auth

Local runs can stream browser / editor / sheet surfaces in-app, and channel auth no longer spams Slack or Telegram when a CLI login flap recovers.

• Live browser, code/text editor, and spreadsheet viewers for on-device deliverables.
• Auth alert latch + healthy-streak dedupe so expired CLI login does not flood every poll cycle.
• iPad auth full-width login/signup with real mobile API (not mock-only).

Slack integration — full conversational workflow

Mention @Grain in any channel to spawn tasks, get quick answers, plan from threads, or schedule reminders. One-click OAuth install — no bot token paste, no scope picker, no signing-secret hunt.

• One-click OAuth — Settings → Integrations → Slack → Connect → Allow. Bot token, signing secret, notification channel and deep integration all activate in a single round-trip.
• @Grain quick replies — short questions answered inline by gpt-4o-mini in ~2 seconds (~$0.0001 per reply).
• Routing confirmation card — for any "create a task" mention, Grain asks: Quick reply or Send to agent. You pick the right tier per request.
• Plan from thread — @Grain plan a task from this thread reads the full thread, proposes a structured breakdown, posts a Block Kit card with ✅/❌ buttons. Approval creates N tasks atomically.
• Scheduled reminders — @Grain remind me Tuesday morning to follow up with Acme parses natural-language time and schedules via a per-minute cron. One-off, recurring, DM-private all supported.
• 12 Slack-native task tools — agents can post_message, update_message, react_to_message, dm_user, schedule_message, list_channels, get_user_profile, get_permalink, and more.
• Live progress streaming — the original Slack message updates in place via chat.update. No thread spam: one card that morphs Starting → Researching → Drafted ✅.
• Opt-in channel monitoring — tick #bugs or #support; gpt-4o-mini classifies every top-level message and proposes "File this in Linear?" cards. Default OFF per channel.
• Strict @mention policy — Grain stays silent in channels unless explicitly tagged. No autonomous chatter.

Settings & integrations UX overhaul

Native integrations (Slack, GitHub, Linear, Notion, HubSpot, Stripe) now sit at the top of Settings → Integrations, before the long-tail Composio catalog. Every tile shows inline Connect / Manage / Disconnect with a confirmation dialog. Disconnect is a full teardown: OAuth token revoked, deep integration disabled, notifications stopped — one click.

• Native integrations hoisted above the search bar — reads as "6 things Grain built" + an optional second tier of 3,200+ community apps.
• Settings sub-tabs deep-link via URL — share app.grain.sh/settings/integrations and the page lands on the right sub-tab.
• MCP catalog deduped — community @modelcontextprotocol/server-slack tile removed; native Slack OAuth covers the same surface without credential paste.

Clean URLs everywhere

app.grain.sh/overview instead of app.grain.sh/#overview. Every URL is now path-based, copy-pasteable, and looks professional. Old hash URLs in Slack messages, email, bookmarks continue to work — they auto-migrate to clean paths on first load.

Multi-LLM model picker — gpt-4o-mini default for Slack

OpenAI gpt-4o-mini is the new default for Slack quick-answer, plan-from-thread, reminder parsing, and the monitored-channel classifier. ~10× cheaper than Anthropic Haiku for these bounded patterns with no quality difference. Per-org BYO keys in Settings → AI still take precedence.

Desktop app v0.7.2 — UI redesign, code-signed, notarized

Full Grain UI redesign — cream + ink + coral palette, Inter Tight + JetBrains Mono fonts, sticker-style chips, offset-shadow buttons. Every page restyled for visual consistency.

• macOS DMG code-signed with Macrodeep Developer ID and notarized + stapled by Apple. No more "Apple could not verify…" warnings.
• Sign-out menu in the sidebar — click your user card → Settings · Billing · Sign out.
• Cream / ink backgrounds consistent across every page (Overview, Tasks, Agents, Fleet, Briefs, Settings, Integrations).

Agent Fleet — shop-floor schematic

A new visual page at app.grain.sh/fleet showing every agent in your workspace as a live node on a schematic. Status dots, busy/idle indicators, click-to-open agent details, real-time updates as state changes. Replaces the old static agent grid.

Briefs panel — every artifact in one library

Artifact-style outputs from agents (dashboards, reports, battlecards, memos) collected in one library at app.grain.sh/briefs. Click any artifact in the Overview dispatch table to open it.

Composio long-tail — 3,200+ apps available

Toggle on toolkits like Mailchimp, Trello, Calendly, Zoho in Settings → Integrations and agents can use them. Authorization happens at app.composio.dev/apps.

Slack channel monitoring → Linear

Drop the bot in #bugs or #support. Every message gets classified; looks-like-a-bug messages get a "File this in Linear?" proposal card. Approve → Linear issue created with title, body, priority, type, link back to the Slack thread.

Scheduled automations

Create a recurring job: "Every weekday 9am, ask Pulse to summarize yesterday's revenue + post to #leadership." Cron-driven via Convex, supports natural-language schedules, fires reliably.

Slack thread polish

Three quality-of-life upgrades to thread behavior.

• Live progress card — chat.update morphs one message instead of spamming the thread.
• Scoped agent mentions — @Grain ATLAS draft Q3 review routes directly to a specific named agent.
• Thread replies as task chat — reply in the Grain-started thread, your text appends to the agent's running task.

Continuous + self-improving agents

Five phases of the persistent-agent runtime shipped together.

• Auto-curated memory — agents remember decisions across runs, semantically recall relevant context at task start.
• Autonomous skill creation — when an agent repeats a procedure 3+ times successfully, it proposes a new skill manifest for human review.
• SOUL.md personas — global personality file per agent, editable from Settings → Agents → Persona.
• Natural-language scheduling — "Have Pulse send a weekly metrics summary every Friday 5pm to #leadership" → creates a recurring automation.
• Outcome → persona refinement — weekly, each agent's persona gets a refinement diff proposed based on the last 7 days of feedback.

Grain Frames — the canonical artifact format

Block-based artifact system. Agents produce branded shareable outputs: dashboards, reports, memos, battlecards. PDF export, share tokens, embeddable widgets. Every other surface (Slack file deliverable, email attachment, web embed) renders from the same Frame source.

Hyperagent-inspired UX (phases 0–4)

A ground-up rework of the workspace IA and primary surfaces.

• Sidebar IA — + New thread, Search, pinned Agents, Threads with live status descriptors, Projects, footer for Asset library / Integrations / Help.
• Thread + Frame split view — left pane streams typed reasoning / tool-call / file-write cards, right pane renders the live Frame artifact.
• Skill cards in thread — when an agent loads a skill, an inline card shows name + description + tag chips.
• Command Center — replaces the Agents tab. Dense ops-style roster (status dot, name, runs, avg score, trend sparkline, cost, last active) plus a stats strip.
• Empty states do work — a new thread shows the composer + 3 suggested prompts instead of dashboards.

SwarmOS → Grain rebrand

Product renamed from SwarmOS to Grain. Domain moved from app.grain.sh to app.grain.sh. Visual identity refresh (logo, colors, typography). Every old swarmos.tech URL 301-redirects to grain.sh.

Production launch — the foundations

Convex backend, Tauri desktop app, multi-agent task pipeline, 10 named agents (Scout, Closer, Shield, Spark, Atlas, Pulse, Beacon, Forge, Sentinel, Scribe), execution backends (Claude Code, Codex, Gemini, Superagent), per-agent personas, skill library, deep integrations.