November 2026 status archive, page 12 of 15
Shutdown notices, recent changes and all monthly archives
These events link to today's eligible findings, not historical before-and-after claims.
Cited events
2 ADEs
v0initial researchresearch correction37 findings · 39 sources
Findings today
- v0 provides a browser chat, tool cards, live previews and browser-use screenshots.
- The v0 sandbox includes a supported Claude Code wrapper invoked with claude.
- v0 credits pay for generation and platform fees.
- A GitHub import creates a chat on a selected base branch; the first generated change creates a working branch and…
- The v0 API creates chats and apps, sends messages, embeds authenticated previews and deploys to Vercel.
- Users can connect preset or custom MCP servers to give v0 additional external tools during generation.
- The beta Slack bot accepts @v0 prompts, reads the thread and creates a code branch and pull request.
- The Plan Mode instruction asks v0 to outline an approach, steps and risks and request approval before implementing.
- Reusable named instructions are saved to the account, available across chats and projects and applied until unchecked.
- v0 searches the web with linked sources and uses a browser to inspect previews or external sites, supplying…
- Users can stop the agent, see tool execution cards and follow automatic continuation through multi-step work.
- Natural-language requests select web search, browser use, integrations or terminal execution; action progress is…
- VM-backed chats run project files, Node.js preview servers and shell commands in Vercel Sandbox virtual machines.
- Each VM-backed chat has separate files, processes and environment variables; sandbox ownership follows the chat…
- The chat filesystem persists between sessions.
- Sandboxes include Node.js and pnpm, npm, yarn and bun; a framework-aware dev server starts on the appropriate port…
- A sandbox has an absolute twenty-four-hour maximum and receives automatic active-use extensions within that cap.
- Chat shows progress indicators, tool execution cards, browser screenshots and source links; deployment Fix with v0…
- The dashboard groups credit consumption by chat or project.
- Team members can receive Can Edit access to a chat and generate changes; shared chat history is included on Plus,…
- Plus members have Builder access.
- Sandbox terminal execution has Ask, Auto and Full permission modes; actual deny and revoke enforcement was not tested.
- Save commits tracked manual file changes and Discard restores the latest commit; generated message versions retain a…
- A message Diff tab displays version changes; users can select diff lines and attach comments to the next prompt.
- Chats can be transferred between personal and team scopes, bringing the full prior history into the team-owned chat.
- Browser-use screenshots and preview context appear in chat along with tool output.
- The GitHub Publish flow respects required checks, reviews, draft state and branch protections; blocked merges remain…
- v0 automatically commits and pushes to a chat working branch, creates PRs, displays CI and offers fixes for CI or…
- Publish creates or reuses a pull request, merges to its base branch and waits for production deployment, subject to…
- Users can view and restore previous generated versions.
- The code viewer can copy or download files, including pending edits.
- Enterprise customers can opt out of content use for model training, and Enterprise data is processed on separate…
- Plus costs USD 30 per user monthly and Business USD 100, with USD 30 monthly credits each.
- The October 19 changelog announces the shipped Slack integration.
- The vendor asserts that v0 is included in Vercel SOC 2 Type 2 attestation covering Security, Confidentiality and…
- New Free signups receive a one-time USD 5 allowance which does not renew; existing Free users retain a USD 5 monthly…
- The public plan table gives monthly prices, included credits and credit expiry.
Sources
Open the v0 page
Wakuinitial researchresearch correctionfreshness recheck23 findings · 5 sources
Findings today
Sources
Open the Waku page
18 ADEs
Orchestrator.incresearch correctionfreshness recheck3 findings · 24 sources
Ampfreshness recheckresearch correction39 findings · 20 sources
Findings today
- Amp offers Mac, experimental Windows and native Linux desktop apps, native phone apps, the web app and CLI.
- Amp supplies its own coding-agent harness across clients and builds prompts/tools around the selected model.
- The pricing guide supports linking ChatGPT and Claude subscriptions.
- The quickstart permits a project without a Git repository.
- Local commands and remote MCP servers are supported.
- GitHub webhooks can continue threads or spawn Orbs from issues and pull requests.
- Thread artifacts can hold plans and checklists, persisted with the thread.
- Amp loads AGENTS.md in the current directory, parents and relevant subtrees, plus personal and system guidance.
- Artifacts can retain a plan or requirements document with a thread; a dedicated executable requirements schema is…
- The Orb guide describes several independent tasks running at once, each with its own environment.
- Task executes delegated work and Read Thread summarizes threads.
- Amp saves one schedule per thread; it can run once or repeat, with pause, resume and delete controls.
- A snoozed thread surfaces and notifies when it needs an approval or answer.
- The Dial provides low, medium, high and ultra modes; plugins can define custom agents.
- The CLI can run Amp on the user's own machine.
- Runner worktree creation also creates a named branch.
- Docker-backed Orb services restart when a portal is reopened after wake; terminal and desktop process state is not…
- Install shared dependencies in .agents/setup.
- Setup stops after 20 minutes; a failed or timed-out setup does not publish a refreshed snapshot.
- A thread's dollar indicator opens detailed usage; this is documented, not reconciled against invoices.
- After a burst of twenty metered Orb starts per user, later starts queue at one every five minutes.
- Workspace members can chat with each other in the thread.
- Member and Admin roles are documented; Admin manages membership, billing, settings and policies and can view private…
- Multiplayer starts with a seven-day duration, can end early and expires automatically.
- Enterprise admins can access authentication event audit logs; comprehensive application audit logs remain internal.
- The Changes pane offers all changes, uncommitted changes or a selected commit.
- Colleagues use the same thread and Orb or shared runner while multiplayer is active; disconnect takeover was not tested.
- The thread's Changes view shows the diff, alongside files, services and conversation.
- Default Ship asks the agent to run the full test suite.
- Push to Branch ships to a feature branch instead of the base branch.
- Default Ship writes directly to the base branch after rebasing; PR approval and merge-policy enforcement are not…
- The thread records linked PRs when the PR description includes its thread URL or ID.
- Amp access is covered by the limited, revocable service license in its custom terms.
- Amp explicitly says it does not offer self-hosted deployments of its control plane.
- Local code snippets and context can be sent to Amp Server and model providers.
- Public tiers are Hobby free, Megawatt $20/month, Gigawatt $200/month, Teams at no additional workspace charge and…
- Amp publicly states SOC 2 Type II certification; the underlying report was not inspected.
- The Hobby tier is recurring free; model usage and hosted compute may still cost money.
- Agent usage is billed in credits and Orb compute by the minute.
Sources
Open the Amp page
Google Antigravityfreshness recheckresearch correction20 findings · 60 sources
Findings today
- Desktop on macOS 12+ with Apple Silicon or Intel, Windows 10 64-bit+, Linux and Googlebook; CLI and IDE extensions.
- One Antigravity harness with plan-dependent Gemini, Claude and GPT-OSS models.
- Free, Google AI Pro/Ultra subscriptions, AI credits and Gemini Enterprise licenses are documented; API keys work in…
- Teamwork breaks a brief into milestones and parallel tracks; user-visible epics, blockers and readiness are not…
- Custom subagents and Teamwork roles support messaging, result return, live progress and follow-up; cross-harness…
- Quick tasks, plan mode, Teamwork for large work and natural-language custom agents are documented; run-time role…
- Local execution, browser Remote Control of user hosts, and gradually rolling out Google-managed Remote Agents on…
- Sessions can be resumed, the Remote Control web UI tries to reconnect after network drops, and the headless Remote…
- Headless print mode defaults to unlimited time with an optional --print-timeout.
- Conversation histories persist across sessions and Teamwork records logs; export and integrity guarantees are not…
- Diffs, plans, walkthroughs, diagrams, screenshots and browser recordings are produced as artifacts.
- Agents run tests, hooks can run linters and block stops, and Teamwork adds reviewer gates; configured CI gates are…
- Free plan $0/month; Business Standard/Plus from $30 USD per seat per month for eligible Gemini Enterprise customers,…
- App v2.29.0 dated November 3 and CLI v1.5.1 dated November 5 are listed.
- Individual plan is $0/month with basic weekly rate limits and unlimited Tab completions; Pro and Ultra add limits…
- Pricing units are per seat per month or consumption; included limits are qualitative; subscription options require…
- Teamwork captures requirements in a request artifact and maintains milestone plans and progress, with prompt…
- Enterprise SSO, Workforce Identity Federation and BYOID are documented; licenses are assigned by the organization's…
- Command, MCP, URL and file approvals with allow/ask/deny rules and presets exist; approver identity and revocation…
- Desktop threads can be imported into the CLI; 2.0 v2.19.1 can export rendered Markdown in artifacts as PDF; SDK…
Sources
Open the Google Antigravity page
Augment Codefreshness recheckresearch correction41 findings · 21 sources
Findings today
- Cosmos explicitly has no separate iOS or Android app.
- Augment supplies the Auggie/Cosmos coding agent with a selectable model catalog.
- The CLI setup requires an Augment account login.
- Install the prerelease npm package on Node 20+, open the project and run auggie auth login; setup timing was not tested.
- Auggie --print executes one instruction and exits; --mode stream or json controls programmatic output.
- Expert Capabilities bundle tools or MCP servers.
- Triggers include GitHub PRs, Linear status changes, Slack messages and custom webhooks.
- IDE Tasklist retains sequential steps and can be moved into a new chat.
- Agents generate nested subtasks beneath an initial task.
- Reusable agent-skills packages are stored in Files and provide specialized instructions.
- The project is indexed automatically on starting Auggie in its directory; freshness behavior was not tested.
- Humans create IDE Tasklist tasks using Add Task; the agent can also generate them.
- The agent can generate a task list and nested subtasks.
- Project Builder drafts a design document and ticket breakdown; persistence and revision enforcement of a…
- Auggie subagents run in parallel with independent context.
- Project Builder coordinates PR Author implementation workers.
- Cron is a documented Cosmos trigger source.
- The IDE Tasklist red square interrupts the current task.
- Project Builder handles a large feature through design, architecture, tickets and coordinated implementation.
- Auggie CLI executes beside local code with Node 20+ on macOS, Linux or Windows WSL.
- Each isolated daemon session gets a separate Git worktree for every configured repository.
- Environments pause when inactive and run at most 24 hours at a time.
- A Cosmos Environment runs up to 24 hours at a time.
- Interactive mode shows tool calls/results; print mode emits a final response and Request ID unless JSON output is…
- The Outcome Analytics release says session costs remain visible only to admins; invoice reconciliation was not tested.
- Shared sessions are visible to the organization; private sessions only to the owner unless explicitly shared.
- Administrator and Member have separate membership, billing and plan permissions.
- The vendor says consequential actions pause for human approval; exact authority enforcement was not tested.
- A conversation is saved indefinitely, including when an automation archives it.
- Tasks and Changes views show diffs for each completed task.
- Files are stored in a virtual filesystem, with organization-shared and user-private visibility.
- Cosmos includes an automated PR-review expert; exact-revision approval and enforced delivery gates were not established.
- PR Author creates the implementation branch.
- Cosmos agents do not perform the final merge.
- The main Augment/Auggie/Cosmos platform is governed by vendor-authored professional/enterprise service terms.
- All paid plans exclude AI training on customer data according to the pricing FAQ; retention and telemetry require…
- Public plans are USD monthly.
- Auggie 1.x is prerelease; stable 0.x is separately available.
- The vendor asserts SOC 2 Type II on the pricing page; report period, scope and independent verification were not…
- The complete public plan list has paid Standard, Business and Enterprise plus trial access, without a recurring free…
- Usage is measured in dollars across models, Context Engine and compute.
Sources
Open the Augment Code page
Buzz by Blockfreshness recheckresearch correction31 findings · 9 sources
Capyresearch correctionfreshness recheck9 findings · 25 sources
Findings today
Sources
Open the Capy page
Claude Codefreshness recheckresearch correction51 findings · 125 sources
Findings today
- Claude Code has CLI, Desktop, IDE, browser and mobile clients.
- Claude Code embeds its own harness and runs Claude models only.
- Pro, Max, Ultra, Team and Enterprise include Claude Code.
- Programmable access is strong on the CLI: claude -p with JSON output, Python/TypeScript Agent SDK, claude mcp serve…
- Ordinary TaskUpdate changes task dependencies.
- TaskCreate, TaskGet, TaskList and TaskUpdate manage session checklists.
- Agent teams (experimental) document lead assignment and file-locked task claiming; outside teams, assignment is the…
- Delegation is inspectable through subagents (own model, effort, tools), agent teams, cross-session messaging and…
- Cloud scheduled tasks, formerly routines, support schedule/API/GitHub triggers independently of the laptop.
- Agent view (research preview) is a terminal fleet screen that groups background sessions under Needs input, Ready…
- Quick tasks are one prompt away; larger efforts use subagents, agent teams, projects (cloud beta) or dynamic…
- Claude Code runs locally by default; cloud sessions run on Anthropic VMs (4 vCPU, 16 GB, 30 GB) with no separate…
- Limits include print-mode --max-turns and --max-budget-usd (client-side estimate), subagent maxTurns, tool timeouts,…
- Cost views: /usage session cost (client-side estimate at list price unless an administrator's managed modelPricing…
- Review is available through /diff, Desktop diff view with inline comments, local /code-review, and managed GitHub PR…
- Pro $20/month or $200/year; Max $100/month; Ultra $200/month.
- Fixed subscription examples: one Pro $20/month or $200/year; two Team Standard seats $50/month or $480/year; five…
- Current changelog lists v2.1.319.
- Free excludes Claude Code; all paid plans include it.
- Public seat prices, plan multiples and separate API rates are stated.
- CLI onboarding is one install command plus browser login, and works in any directory.
- No native issue tracker was found in the documentation, changelog or repository checked; work arrives by prompt,…
- Isolation options: git worktrees per session, an OS-level sandbox for shell commands (macOS/Linux/WSL2, off by…
- Cloud environments offer setup scripts, a filesystem-snapshot cache, network access levels and pre-installed…
- Compute-aware scheduling is limited: Remote Control and self-hosted runners cap concurrency, Bash commands have…
- Verification is policy you configure: hooks run commands and can block actions or task completion (exit code 2),…
- Prompts and outputs go to Anthropic (or the chosen provider) over TLS 1.2+; consumer plans train on data only when…
- Claude Code is an MCP client (http, sse, stdio, websocket) with OAuth and scoped config, supports…
- The mobile app is a client for cloud or Remote Control sessions, and IDE extensions wrap or bundle the CLI engine.
- Plan mode proposes a plan before edits and plans can be saved into the repository; /goal tracks a completion condition.
- Persistent instructions and memory are documented: CLAUDE.md at managed/user/project/local scope, AGENTS.md reading,…
- Code understanding relies on agentic search (grep, glob, file reads) plus optional LSP code-intelligence plugins and…
- Living product specifications were not found as a native feature; instructions files and plans in the repository are…
- Parallel work is supported locally (multiple terminals, worktrees, subagents, agent view background sessions, Remote…
- In the CLI a human can interrupt, stop, queue steering messages and resume sessions; background sessions show Needs…
- Sessions persist as local transcripts and resume; cloud sessions restore history after VM reclamation but lose…
- Operational statistics are available via /usage, /insights, OpenTelemetry metrics, logs and traces (beta), and the…
- Live multi-human collaboration is limited.
- Roles and access are managed at the Claude account level: Owners and admins configure cloud environments and…
- Approvals are per-user permission prompts governed by permission modes plus allow/ask/deny rules, hooks and…
- History comes from local session transcripts, checkpoints, OpenTelemetry events and, on Enterprise, audit logs.
- Takeover is mostly same-user: teleport and Remote Control move a session between one person own devices; colleagues…
- Outputs include diffs (/diff, Desktop diff view), live Artifact pages published to claude.ai, Desktop app preview,…
- The CLI supports git workflows: it can create commits and pull requests on request, run in isolated worktrees, link…
- Merge and deployment authority is delegated to git/CLI permissions: Bash allow, ask or deny rules can gate push and…
- Completion evidence is session links to PRs and OTel commit/PR counts; rollback is via /rewind checkpoints on local…
- High-volume shipping features are limited: agent view summaries, /batch splitting a change into worktree subagents,…
- Claude Code is proprietary: the public repository LICENSE.md states "© Anthropic PBC.
- The installed Claude Code CLI can run its full agent loop, tools and context management on user-controlled…
- Claude Code documentation points to the Anthropic Trust Center for compliance artifacts.
- Claude Code has persistent native task checklists with optional cross-session lists and experimental team…
Sources
Open the Claude Code page
Claude Squadinitial researchresearch correctionfreshness recheck30 findings · 7 sources
Clinefreshness recheckresearch correction43 findings · 18 sources
Findings today
- Cline supplies Desktop, IDE, CLI/SDK, Kanban and Cloud Agents clients.
- The pinned Cline SDK includes native Claude Code and Codex CLI execution adapters and an OpenCode SDK runtime.
- Cline supports Claude Pro/Max subscription access via an installed authenticated Claude CLI provider.
- Kanban requires Node 18+, a Git repository root and npx kanban; it starts a local browser server.
- The CLI is documented for scripting and CI/CD.
- Cline supports connecting MCP servers for external tools and data.
- The pinned technical README describes Cline Desktop as a Tauri shell with Bun sidecar and Next.js UI; no…
- Users add task cards manually or through sidebar chat.
- Linked cards form chains; the next task starts after the prior card completes and is moved to trash.
- Memory Bank uses project Markdown files for requirements, architecture, technical context and progress.
- Cline explicitly says it does not index or embed repository contents; it reads files on demand.
- The Kanban board stores manually created cards before play is pressed.
- The sidebar agent can create and link human-visible cards; API permission/conflict behavior remains unknown.
- Memory Bank projectbrief.md stores requirements and goals in the repository.
- Desktop supports multiple independent agent sessions in parallel.
- One coordinator delegates subtasks to specialist teammates.
- Desktop has one-time and recurring Schedule entries with prompt, provider, model, workspace and optional timeout;…
- Cards show latest agent message or tool call; a twelve-state fleet fixture was not run.
- Users can describe a recurring task in chat to create a schedule.
- Desktop runs sessions on local hardware.
- Each Cloud Agent session receives its own repository copy.
- Cloud sandboxes pause after 15 minutes of inactivity.
- Gitignored dependencies such as node_modules are symlinked from the main repository; writes affect the shared target.
- CLI --timeout sets a task duration in seconds; zero means no timeout.
- --json streams timestamped agent events and a final run_result.
- Session cost includes subagent costs.
- At most ten Cloud Agent sessions run concurrently.
- Enterprise documents Member, Admin and Owner with organization-scoped permissions.
- Approving spawn_agent approves its subsequent child tool calls without individual approval.
- Team task-board, mailbox and mission-log state is stored in teams.db and restored when the session resumes.
- Inline diff comments go back to the agent as feedback.
- Imported conversation context can continue in Cline; this does not establish preservation of the original runtime or…
- Card details expose the TUI and cumulative or message-range diffs.
- Cloud Agents use a cline/ branch per task.
- Commit sends a dynamic prompt to merge worktree changes to the base branch; a prompt is not proof of an enforced…
- The cloud sidebar reports working, done or awaiting-input session states; this alone is not merge evidence.
- The repository LICENSE at a459f1d04dea030833b558be645011ab739c463b is Apache-2.0; hosted components and separate…
- The open-source Cline core and its tools run locally or on user-controlled remote hosts with a chosen inference…
- Cline/ClinePass inference telemetry can contain prompts and responses; other providers do not send prompt contents…
- The overview lists ClinePass at $9.99/month for selected open coding models, checked 7 November 2026; exact caps…
- Cline Kanban is a research preview with experimental capabilities; this does not classify the stable IDE extension…
- The open-source extension and CLI are free for individual developers.
- The open-source version has no subscription or seat fee.
Sources
Open the Cline page
cmuxresearch correctionfreshness recheck30 findings · 8 sources
Findings today
- cmux supports local terminals, user-owned SSH hosts and paid early-access persistent Cloud Linux machines.
- cmux can run locally; session snapshots export/import as JSON, while production server components have separate…
- cmux offers stable and nightly builds, public issue support and early-access Cloud.
- cmux runs terminal coding agents including Claude Code, Codex, OpenCode, Gemini CLI, Cursor Agent, Aider, Grok and…
- cmux supplies reusable skills for workspace, browser and CLI automation.
- cmux documents reusable agent skills.
- cmux restores app snapshots and native agent session IDs, while arbitrary process checkpointing is explicitly excluded.
- cmux restricts automatic execution of imported resume commands.
- cmux exposes browser previews and screenshots and also supplies a typed Git diff viewer for proposed changes, with…
- cmux documents local snapshot and hook-state files and strips sensitive resume environment keys.
- Mac terminal, iOS TestFlight and Linux Browser nightly are distinct clients.
- cmux runs agent CLIs unmodified in its terminal, so each agent's own sign-in, including a subscription login, applies.
- Mac setup uses DMG or Homebrew and the user supplies agent CLIs.
- CLI and socket operations automate workspaces, panes and browser actions.
- The Mac terminal is implemented with Swift/AppKit and libghostty.
- cmux persists per-workspace task checklists.
- cmux documents parallel CLI sessions in split terminal workspaces.
- The documented claude-teams command displays Claude-owned team orchestration.
- cmux automation rules match coding-agent and workspace events and execute configured shell/RPC actions without a…
- Notifications identify panes needing attention.
- The sidebar exposes per-workspace context; the fleet fixture was not run.
- Cloud machines use microVMs as their security boundary, not containers on a shared kernel.
- SSH browser panes use remote-network routing.
- Workspace metadata shows branch, PR state, ports and latest notification.
- Enterprise documents SSO/SAML.
- Attention navigation and embedded browser context are documented.
- The sidebar shows linked GitHub PR metadata.
- Client code is GPL-3.0-or-later; named server directories use BUSL-1.1.
- Free macOS app (local agents use your own API keys); paid Cloud VM plans are Plus $15/mo, Pro $50/mo ($480/yr), Max…
- The Mac terminal is advertised as free; compute and agent costs are separate.
Sources
Open the cmux page
CodeLayer / HumanLayerproduct changefreshness recheckresearch correction50 findings · 26 sources
Findings today
- The complete current application repository lists macOS Electron/Tauri shells, web clients, a daemon and CLI.
- HumanLayer integrates Claude Code, Codex, OpenCode and Pi.
- The pricing FAQ explicitly permits existing Claude/Codex subscriptions or API keys.
- The tutorial names macOS, an account, signed-in Claude Code and Git, then creates an inline task/session.
- Product CLI/RPC routes create/list tasks and launch/list sessions; automation run uses a checkout and PAT.
- The current repository includes Claude Code, OpenCode and Pi session plugins and built-in HumanLayer/RPI skills.
- The current pinned monorepo identifies a shared web UI inside macOS Electron and Tauri shells.
- Users create inline tasks with a name/slug; CLI examples expose persistent task IDs and optional ticket fields.
- Guided workflows save research/design/outline/plan artifacts and allow comments and in-place iteration before…
- Repository skills/instructions and shared task documents supply context.
- Release notes document image attachments in task intake.
- Inline persistent task containers group multiple independent sessions, so a ticket in an external tracker is optional.
- The bundled orchestration skill calls product CLI task/session routes with the same durable task IDs shown in the…
- Task design/PRD/TDD artifacts support comments and agent iteration and guide implementation.
- The vendor states local daemons run many sessions in parallel; the bundled skill launches separate task worktrees.
- Task listing can filter by owning user; this does not establish human assignment edits or enforced exclusive ownership.
- RPI provides named harness-native research/implementation children; a separate bundled orchestration skill…
- User-run CI/cron can invoke automation run with a PAT; schedules, concurrency groups and no-op guards are external…
- Release notes document shared-session queue/interrupt, Pi stop/reply and attention notifications.
- The UI has attention notifications and a task board; tasks group session history.
- Oneshot handles small changes; Freeform omits fixed phases, while RPI/PRD provide guided checkpoints.
- Daemons run on the workstation or user-selected VM/server near the code and private services.
- Worktree timing allows task-specific branches/worktrees or direct checkout use.
- Remote-host sessions and task files are accessible across clients; exact reload/recovery behavior was not tested.
- Workspace configuration supplies setup commands and copied local files per repo; remote hosts need checkout, tools…
- Release notes document Claude usage-limit warnings, waiting states and resumption after reset.
- The status reference names approval, provider-limit and failed/lost states; daemon service logs can be inspected…
- Release notes mention usage/cost metrics and per-host Claude limit alerts; provider-billed versus estimated charges…
- External automation workflows can configure concurrency/no-op guards.
- Task sharing gives editors session/file access and reviewers document comments.
- Official integration guides reserve connection setup to organization admins; task-level edit and review access are…
- The product launch reference lists default, accept_edits, auto and bypass permission modes.
- Shared task files/comments remain with related sessions and can be read by later agents.
- Documented diff review includes changed-file navigation, comments and viewed markers, with artifact comments…
- Shared task access allows another editor to add sessions and continue task files/history.
- Task files sync into an artifact view, including text, HTML, images and PDFs, with task/session grouping.
- Guided implementation documents checks/manual review between phases; PR follow-up can respond to CI.
- Workspace setup creates task branches/worktrees; implementation skills commit checked phases.
- The opt-in GitHub PR tab documents merge and auto-merge actions.
- Release notes document session/PR links through a commit ledger; task artifacts retain PR descriptions.
- Per-task diff/artifact comments, PR controls and workflow next actions exist.
- The current application monorepo at the cited revision is Apache-2.0, with separately licensed vendored MIT folders.
- Current core can be built/run locally, but setup requires third-party configuration and self-hosting guides are…
- Agents execute on user hosts while events/task artifacts sync through HumanLayer APIs/storage; model traffic can use…
- Public pricing lists Pro at USD 100/user/month with unlimited tasks/sessions and BYO agent subscriptions/API keys;…
- One or two users can fit the advertised free Starter seat allowance if they remain within 200 sessions/month.
- Official notes reach 0.201.0 on November 2, 2026.
- The vendor homepage asserts SOC 2 Type II and Vanta monitoring.
- Starter is an ongoing free plan for up to three members and 200 sessions/month, currently offered during the…
- Pricing is partially specified: per-user monthly Pro price and Starter caps are public; Enterprise is custom, while…
Sources
Open the CodeLayer / HumanLayer page
OpenAI Codexfreshness recheckresearch correction33 findings · 23 sources
Findings today
- Codex is available inside the ChatGPT desktop app on macOS and Windows; Linux is a preview on the distributions…
- Codex supplies its own coding harness.
- Supported local Codex clients can sign in with ChatGPT.
- Install the CLI, open a project directory, run codex and authenticate; elapsed setup time was not tested.
- codex exec runs non-interactive tasks in scripts and CI.
- The CLI supports packaged skills and plugins.
- Codex reads AGENTS.md before beginning work.
- codex --search enables live web search with visible search activity.
- The public CLI supplies a per-turn update_plan checklist inside a conversation event stream.
- Each cloud task has its own workspace; the page gives no concurrency quota.
- Local custom agents can set model and reasoning effort; unspecified children inherit their parent.
- Desktop Codex supports recurring tasks with an RRULE custom cadence.
- The interactive CLI accepts steering during the active turn.
- A scheduled task can choose default or explicit model and reasoning effort.
- The CLI inspects, edits and runs tools in the local project.
- Codex supports local OS sandboxing, user-managed devcontainers and Git worktrees.
- Phone worktree control still requires the execution computer awake; this is distinct from cloud tasks that run while…
- Cloud setup identifies and installs repository runtimes, dependencies and tools.
- Provider SSE idle timeout defaults to 300,000 ms and is configurable.
- Opt-in OTel exports structured API, tool, approval and stream events.
- Business includes SAML SSO; Enterprise adds SCIM and RBAC.
- Local approval policies control escalation beyond the sandbox; /permissions exposes read-only and other configurations.
- Opt-in OTel tool-decision events retain approved or denied decisions and decision source.
- Cloud review shows changed files and check results.
- A dedicated local review can inspect uncommitted changes, a commit or a base branch and return prioritized findings.
- Cloud results can be committed or opened as pull requests after review.
- The repository LICENSE at fc01c073b9ea09c06347a234a1ca231a9ef65bf5 is Apache-2.0; hosted components and separate…
- The Codex CLI and App Server core can run on user-controlled infrastructure under the public source distribution.
- The Business plan states no training on business data by default; consumer routes are not covered by this statement.
- Codex offers Free and recurring paid ChatGPT plans, with separate API-key billing.
- The Linux desktop client is in preview, with named x64/ARM64 distribution packages.
- A $0 monthly plan includes limited desktop Codex usage, subject to rollout.
- Prices distinguish individual subscriptions, Business seats and separate API usage.
Sources
Open the OpenAI Codex page
Conductorfreshness recheckresearch correction23 findings · 41 sources
Findings today
- Conductor documents a macOS app and an iPhone app requiring iOS 26.0+.
- Beta HTTP API (/v0, OpenAPI), hosted Streamable HTTP MCP server and routine webhooks; Conductor CLI exists in cloud…
- API/MCP (beta, cloud workspaces) can create sessions, send prompts, cancel the current turn and read transcripts; an…
- Cloud scope.
- Managed Cloud (Vercel sandbox, us-east-1) keeps agents running after the Mac app closes until sandbox sleep or…
- Cloud preserves files and chat history across sleep but not running processes; interrupted turns must be resent.
- Cloud sandboxes enforce sleep and lifetime limits; Codex chats retry on OpenAI rate limits (0.84.0, no surface named).
- API session status distinguishes idle, working and errored; failed Cloud startup exposes setup logs.
- Experimental cloud cost estimates (Codex, 0.77.0) exist; per-task cost reporting is otherwise not documented;…
- Each Cloud workspace is documented with 8 vCPUs and 16 GB RAM; concurrency limits, resource-aware scheduling and…
- The revised announcement documents transferring Cloud workspaces to local and exporting an account archive.
- The pricing URL redirects to the homepage without a price table.
- One-, two- and five-person scenarios cannot be priced from the checked public pages because current subscription…
- Conductor has withdrawn its wind-down plan.
- Pricing is partially specified: model billing stays with the provider and Cloud FAQ states no additional compute fee…
- Local workspaces have todos that block merging until checked off.
- Workspace todos exist; an independent issue backlog is unverified.
- The local app keeps chats and files on the Mac (~/Library/Application Support/com.conductor.app and ~/conductor),…
- Local workspaces and chats stay on the Mac, model requests go to the configured provider, and analytics go to PostHog.
- Local workspaces use a git worktree and branch each without an OS sandbox; Cloud uses isolated Linux microVM sandboxes.
- Cloud routines run saved prompts on schedules (including weekdays), GitHub actions with filters, or webhooks;…
- Shared Cloud workspaces support live chats, presence and typing indicators; private workspaces exist; Pro…
- Cloud organizations have admins and members.
Sources
Open the Conductor page
Cursorfreshness recheckresearch correction16 findings · 54 sources
Findings today
- Cursor is reachable from a desktop app (Mac, Windows, Linux), a CLI, a web client at cursor.com/agents, a native…
- Cursor runs its own coding-agent loop with selectable models.
- A Cursor account uses the new X Subscription or a retained legacy Cursor plan.
- Cursor exposes a CLI with headless mode, a public-beta Cloud Agents REST API, a TypeScript SDK, and signed status…
- Projects let a coordinator agent plan larger bodies of work and delegate to cloud agents; task dependencies,…
- Spend limits bound cloud usage; time limits and timeouts are not stated.
- Token usage is available per agent and per run through the API and SDK; billed dollar cost per agent is available…
- New subscriptions cost $8 Plus, $30 Premium, $100 Super or $200 Ultra monthly; Teams seats $30/$100/$200.
- Fixed new-plan examples only: one Premium user $30/month; two Premium Teams seats $60; five $150.
- Cursor announced its completed acquisition by SpaceX on August 14, 2026 and described continued product development.
- Free has limited core use.
- New-plan seat rates and annual prices are public; usage pools are weekly and third-party models prepaid.
- Cloud agents accept follow-up runs and CLI sessions can be resumed.
- Plan Mode saves editable Markdown plans for later reference and user-directed implementation.
- Agents open pull requests (ready for review unless a draft is requested).
- PR, deployment and check status appear in mobile, and Rollouts monitors deploys for regressions and notifies the…
Sources
Open the Cursor page
Devinfreshness recheckresearch correction35 findings · 14 sources
Findings today
- Devin Desktop, formerly Windsurf, has macOS, Windows and Linux downloads; Linux packages specify glibc >=2.28 and…
- Desktop supports Claude Code, Codex CLI, OpenCode and Gemini CLI through ACP in addition to Devin Local.
- Pro, Max and Teams explicitly support using a ChatGPT plan.
- Install the CLI for the host OS, restart the terminal, enter a project directory and run devin.
- The REST API has organization and enterprise scopes for sessions, context and administration.
- Profiles can allowlist installed organization MCP servers independently of network destinations.
- Devin accepts work based on Linear/Jira tickets; tracker synchronization and authority are not established here.
- Knowledge stores reusable instructions and tips; new guidance should use Skills because Knowledge is deprecated.
- The introduction describes tackling multiple cloud tasks in parallel; no measured concurrency test was run.
- The CLI main agent delegates independent workers using profiles.
- Devin management tools expose schedules; scheduler reliability and overlap handling were not established.
- Foreground child tool calls can request human approval; background unapproved tool calls are denied.
- Devin CLI and Desktop local sessions execute on the user computer; cloud sessions use Devin VMs.
- Cloud sessions run on VMs.
- A cloud session keeps running when the local terminal closes.
- The issue timeline and analysis identify problems and recommendations in completed sessions.
- Insights reports session ACU usage; this is a compute usage unit, not a complete reconciled monetary bill.
- Teams supports multiplayer sessions.
- Service users have roles; creating sessions as another user requires ImpersonateOrgSessions.
- Every Local Hands tool call requires user approval.
- Sessions created as a user appear in that user's list and count toward their usage; this is documented attribution,…
- The Review inbox lists authored, assigned and awaiting-review PRs.
- A human can interact with the embedded IDE and browser; second-account takeover and owner-disconnect behavior were…
- Cloud sessions expose shell output and development tools; persistence and revision binding were not tested.
- The guide describes returning draft PRs for review.
- Devin Review can submit GitHub PR approvals with the required connection.
- Devin Review lists PRs awaiting review.
- Cognition provides Devin under proprietary service rights: restricted access/use is licensed to customers and all…
- Outposts self-hosts tool execution on user infrastructure, while the agent loop, inference, planning and queue…
- The web application processes user-provided data; installed integrations have separately configured access.
- Prices are USD.
- Knowledge is deprecated, with gradual automatic migration to Skills in Plugins and removal in a future undated update.
- Cognition states SOC 2 Type II certification since September 2024.
- Free includes a light agent quota, limited models and unlimited inline edits/Tab completion in desktop; free cloud…
- Individual usage is a daily and weekly quota, with model-dependent message consumption.
Sources
Open the Devin page
Emdashresearch correctionfreshness recheck35 findings · 20 sources
Findings today
- Classic automations let users choose the agent, provider options, prompt and workspace for scheduled runs.
- Automation history and PR checks expose timing, status and errors.
- Classic lists provider-specific auto-approve, which skips file-operation permission prompts, and confirms before…
- Classic supports staging, commits, pushing and pull request creation inside its diff interface.
- Classic links current-head PR checks to GitHub and can discard unstaged changes with confirmation.
- Classic documents allowlisted default-on PostHog telemetry and opt-out; agent provider policy remains separate.
- Emdash Classic supplies desktop clients and SSH remote workspaces.
- The Library manages reusable prompts, skills and per-machine MCP configuration.
- Classic stores reusable prompts, skills and MCP configuration with explicit machine scope.
- Scheduled prompts run on project machines and retain reviewable history.
- Optional tmux preserves terminal processes/history across view closure or SSH loss, with host reboot excluded.
- Classic offers diff inspection and PR check/comment context in the task workspace.
- These docs cover shipped Classic; Emdash 2.0 is described as early-access/waitlist separately.
- Classic has a fixed list of 35 coding-agent CLI adapters, including Claude Code, Codex, OpenCode, Cursor, Pi, Grok…
- Emdash runs the provider CLIs the user installs and signs in to.
- Install an agent CLI locally or on the selected remote machine before starting work.
- The scoped Classic application has no standalone product-owned user CLI.
- Classic desktop uses Electron.
- Tasks accept branch, external issue or PR context.
- Classic persists workspaces and conversations linked to external tracker issues.
- Classic documents parallel coding agents in separate worktrees.
- Classic launches user-selected agent sessions and renders provider-native subagents.
- Provider hooks expose attention needs and resumable sessions.
- Classic executes locally or on the user SSH machine.
- Classic creates task worktrees or uses an existing checkout.
- Remote previews have explicit port forwarding and manual collision guidance.
- Classic is a local desktop/SSH application with no multi-user shared prompting service in its scoped source.
- Classic has no application organization roles or enterprise SSO.
- Task diffs and browser previews are documented.
- Classic displays GitHub Actions checks.
- Classic advertises merging reviewed changes in the app.
- Classic repository is Apache-2.0.
- Classic operates on local or user-operated machines.
- Classic is free Apache-2.0 desktop software using user-installed agent accounts, subscriptions and provider keys;…
- Classic is advertised as free; agent and machine costs remain separate.
Sources
Open the Emdash page
Factoryfreshness recheckresearch correction42 findings · 19 sources
Findings today
- Factory App now offers macOS, Windows and Linux desktop installers.
- The recurring Free plan supports native ChatGPT and GitHub Copilot sign-in, OpenRouter, provider API keys and custom…
- Non-Git folders can start sessions without a worktree.
- Droid CLI supports terminal use and headless exec; exact operation parity remains uncollected.
- Automation starters include Ticket to PR and Error Triage; external tracker authority was not tested.
- /missions creates a plan with features, milestones and success criteria before approval.
- Mission features are grouped into milestones; arbitrary hierarchy and dispatch enforcement were not tested.
- The shared folder contains plans, findings and deliverables readable and writable by all agents across machines.
- The documented native CVE Tasks tab has persistent task IDs and states, plans, PRs and a timeline, but is explicitly…
- The orchestrator divides areas among agents working in parallel.
- The workstream orchestrator assigns an area and brief to each agent.
- A lead orchestrator delegates to Droid sessions; each agent reports progress, blockers and results and can be opened…
- Factory App Automations supports cron-style recurring runs.
- The UI stops an individual agent turn.
- Agents are separate Droid sessions reporting to one workstream orchestrator.
- The guide recommends starting a new Mission for structured work rather than converting a long-running ordinary session.
- Workstream machines may be the local computer, configured remote computers or fresh cloud machines.
- A new worktree creates its own branch from a selected base by default.
- Persistent worktrees never clean up automatically; ephemeral worktrees are eligible unless a session is pinned.
- A computer may start from a successful Environment snapshot; later Environment rebuilds do not mutate the existing…
- Workstream agents stop at plan or organization usage limits until reset.
- App connection states include connecting, connected and error; induced-failure consistency was not tested.
- Workstream Usage lists each session credit consumption and its share of total.
- Workstream defaults describe additional machines for orchestrator routing.
- Slack delegation supports follow-up instructions in one active session thread or dedicated code channel.
- Owner, Manager and User have distinct organization permissions.
- Enterprise owners can inspect organization administrative events.
- The PRs tab lists each workstream PR with its checks and review activity.
- Workstream shared files retain plans, notes, findings and reports.
- Missions describe user-facing QA validation and self-correction, requiring an automated scriptable application setup.
- Workstreams track PRs opened or worked on by the orchestrator and agents.
- A PR tab has a Merge button and status.
- Workstream PRs can be opened in-product, on the Git host, or copied as links.
- Workstream PRs are grouped by lifecycle state.
- Factory application software is governed by a limited custom internal-use license in Individual Terms.
- Enterprise Custom Deployments can run all of Factory inside the customer network using the dedicated airgap build.
- Airgap execution and files remain inside the customer network, subject to its infrastructure egress rules.
- Factory has a recurring Free plan and paid subscriptions from $20/month.
- Workstreams is beta on Pro, Plus, Max and Teams, explicitly not yet Business or Enterprise, checked 7 November 2026.
- Factory lists ISO 27001 and ISO 42001; exact certified entities and product scope require the reports.
- Factory now offers a recurring $0/month Free plan using the user inference account or keys; paid plans remain…
- Business and Enterprise require a quote; exact rolling usage limits and computer costs were not established by the…
Sources
Open the Factory page
GitHub Copilotresearch correctionfreshness recheck41 findings · 15 sources
Archived event links
Something wrong or missing?