Changelog
Every new feature, improvement, and fix in Sim, the open-source AI workspace, with release notes straight from GitHub.
v0.9.42
Improvements
- improvement(chat): let Chat review organization access requests
- improvement(billing): open a Chat plan popup on send instead of a static card above the composer
- improvement(workspaces): move workspace updates behind an application operation and let Chat rename workspaces
- improvement(chat): let Chat manage sim links, bulk-add permission group members, and preview member removal
- improvement(sandbox): verify the workbench CLI inside each command's launch
- improvement(sandbox): return a timed-out workbench run's output and the files it already wrote
- improvement(media): record a hosted-key auth failure when fal refuses Sim's account
Bug Fixes
- fix(sandbox,db): keep a short workbench run's output on timeout; require dev push for the Project bootstrap switch
- fix(release): report short workbench timeouts, gate Sim links in Chat settings, scope the Chat plan modal
- fix(billing): close the Chat plan popup when its shell unmounts and name the organization's plan on organization routes
- fix(chat): hide the Sim links settings section where Sim links are off
- fix(db): bootstrap Projects for development push databases that predate them
- fix(organizations): refuse self-leave for directory-managed members and keep the renamed name visible
- fix(sim-links): hand off a departing member's links to the successor
- fix(knowledge): let members connect their own account to a member-access connector
- fix(organizations): let members leave their organization; remove sign out other devices
- fix(credentials): let members leave a shared credential
- fix(organizations): let admins rename their organization
- fix(settings): let people revoke the accounts they connected for an organization, even after leaving
- fix(ui): disable MCP URL edits and table rename for roles the server refuses
- fix(test): assert recovery backoff on the claims, not worker request arrival
Other Changes
- chore(release): merge staging into the v0.9.42 release
- chore(release): merge staging into the v0.9.42 release
- chore(billing): drop the unreachable organization branch from the plan upgrade copy
- docs(library): update best-self-hosted-ai-workflow-automation-platforms-2026
- docs(library): update best-zapier-alternatives
- docs(library): update best-ai-agent-evaluation-platforms-2026
v0.9.41
Features
- feat(trigger): reach AWS from trigger.dev runs through workload identity
- feat(library): Best AI Agent Platforms for DocuSign Contract Approval Workflows
- feat(library): Best AI Agent Platforms for Webhook, Schedule, and Event Triggers
- feat(library): What Are the Best AI Agents for Competitor Website Change Monitoring in 2026?
- feat(library): How Do You Connect the Serper Search API to an AI Agent Without Code?
Improvements
- improvement(mothership): let a code call run for up to fifteen minutes
- improvement(cli): accept the file references, list shapes and multi-file values models send
- improvement(search): page Slack Real-time Search to fill a Slack-scoped search's limit
- improvement(sandbox): log per-phase timing for each sandbox execution
- improvement(ci): target acceptance and reuse validated build caches
- improvement(comparisons): re-verify competitor pricing, integration counts, and product status
- improvement(library): correct stale facts, merge duplicate FAQs, and expand IT helpdesk coverage
- improvement(landing): comparison social cards and links to cloud model providers
- improvement(ci): overlap independent acceptance and recovery checks
- improvement(billing): show the Chat plan card above the composer instead of redirecting on send
- improvement(ci): shorten the acceptance critical path
- improvement(ci): check lint and types before pushing
Bug Fixes
- fix(sso): mark email verified on sign-in through a verified-domain provider
- fix(compare): keep Cowork, Make, and Langflow facts consistent within each profile
- fix(copilot): hold sim_cli commands that perform approval-gated capabilities
- fix(mothership): require approval before browser tools act on a page
- fix(pii): bound custom-pattern matching time per request
- fix(media): restrict ffmpeg inputs to media demuxers
- fix(realtime): enforce the Files capability on workspace document rooms
- fix(copilot): require approval for terminal input, which can submit a command line
- fix(file-viewer): upgrade docx-preview to 0.4.1 to close w:sym innerHTML XSS
- fix(mcp): require workspace admin to change workflow MCP server visibility
- fix(copilot): require approval for run_block and run_from_block
- fix(extension): disclose link handling and keep gesture checks passive
- fix(extension): attach Sim pages and streamline composer controls
- fix(extension): attach Sim pages and streamline composer controls
- fix(mcp): answer workflow MCP JSON-RPC errors over HTTP 200 instead of session-loss statuses
Other Changes
- chore(release): merge staging into the v0.9.41 release
- chore(release): merge staging into the v0.9.41 release
- chore(release): merge staging into the v0.9.41 release
- chore(release): merge staging into the v0.9.41 release
- chore(release): merge main into the v0.9.41 release
- chore(extension): bring the main extension hotfix into staging
- Merge pull request #9564 from simstudioai/codex/extension-0-1-2-release
v0.9.40
Features
- feat(billing): require a paid plan or prepaid credits for Chat
Bug Fixes
- fix(billing): fail closed on legacy Chat payer reads and cover the Chat plan gate
- fix(public-shares): stream shared files with byte ranges instead of buffering them under 100 MB
- fix(sandbox): initialize workbench history before honoring a stop during creation
v0.9.39
Features
- feat(library): AI Agent Output Controls Compared: Guardrails, Structured Outputs, and Streaming
- feat(library): Best AI Agents for Jira Triage and Datadog Incident Response
- feat(mothership): answer a long workflow tool run still running, and stop detached runs on Stop
- feat(people): organization People page with profiles, reporting lines, and people-data import
- feat(desktop): continue a passkey sign-in in your browser and bring the session back
- feat(mothership): erase private memory when a member leaves or an organization is deleted
Improvements
- improvement(docs): collect reader feedback inline
- improvement(release): harden favicons, sim links, and the extension from a pre-release audit
- improvement(search): overlap live search stages and report every unsearched source
- improvement(desktop): sign-in prompts for the agent browser — site passwords, passkey accounts, client certificates, and app links
- improvement(cli): sim credentials providers lists providers
- improvement(desktop): install updates on one click, asking only about real in-flight work
- improvement(cli): files batch-delete takes file ids as arguments
- improvement(desktop): bring agent browser menus, keys and fullscreen in line with Chrome
- improvement(extension): document browser data handling and limited use
- improvement(extension): document browser data handling and limited use
- improvement(oauth): serve still-valid tokens while refreshing ahead of expiry
- improvement(sim-links): pass queries through, trim pasted punctuation, and suggest links from the address bar
Bug Fixes
- fix(files): share one served-bytes predicate between the serve route and large downloads
- fix(release): read Excel start dates, refuse impossible times and repeated columns, keep typed escapes, no suggestions for punctuation
- fix(oauth): default a leader-lock follower's wait to the lease so its takeover can land
- fix(desktop): address release review — count app downloads and unchecked terminals before an update restart, send the page referrer on Save Image, and tighten sign-in and people edge cases
- fix(ci): drop the duplicate --accept-routes the Tailscale action already passes
- fix(files): stream served files with byte ranges instead of buffering them under 100 MB
- fix(files): resolve v2 file paths only on the v2 surface, through the canonical resolver
- fix(oauth): take over a lapsed refresh lease, share overlapping service-account key reads, and label unsearched accounts
- fix(auth): check a workspace's personal-key switch after membership
- fix(oauth): keep a five-minute floor on served tokens and refresh ahead earlier
- fix(mothership): Stop only cancels detached runs still running, and a held workflow run never blocks the next turn's workbench
- fix(desktop): ask before an update restart from the menu, count uploads and downloads as running work, and harden sign-in prompts
- fix(files): authorize the workspace before resolving a files/ path
- fix(auth): block only curated disposable domains, and never gate SSO or SCIM provisioning
- fix(people): keep a suspended manager link on edit and never fail the org layout on the People lookup
- fix(execution): name the signal exit code of a failed sandbox process
- fix(extension): keep site access compatible with strict CSP
- fix(mothership): say why a workflow copilot chat cannot read other chats
- fix(auth): refuse account creation from disposable email domains for every provider
- fix(desktop): keep sign-in popups working in the agent browser
- fix(files): accept files/ VFS paths in v2 file describe, rename and delete
Other Changes
- chore(ci): reach the database over the tailnet when CI_DB_TAILNET is set
- chore(search): retire legacy search knowledge base projection rows in place
- chore(auth): correct where the short disposable list runs
- docs(library): update best-multi-agent-frameworks-2026
- Merge pull request #9519 from simstudioai/codex/extension-privacy-production
v0.9.38
Features
- feat(favicons): one server route for every site icon, with parent-domain fallback
Improvements
- improvement(favicons): resolve platform tenants no provider can see, retry timeout-derived icons, no miss flash
- improvement(docs): simplify workflow lightbox and retire migration artifacts
Bug Fixes
- fix(docs): restore container expansion and verify canvas interactions
- fix(favicons): let a mounted icon retry once its failure ages out
- fix(knowledge): keep a bundle's document token totals on import
Features
- feat(access-control): govern access requests per permission item
- feat(docs): rebuild documentation with the shared Sim design system
- feat(extension): open typed sim/ links through the Sim link resolver
- feat(sim-links): organization Sim links (go links) with sim/ redirects
- feat(library): Best AI Agents for Automated Data Reports in 2026: 4 Tools Compared
- feat(library): Best AI Agent Platforms for Slack and Discord: 4 Cross-Channel Options Compared
- feat(library): Best AI Agents for Internal Knowledge Search Across Docs and Tools
- feat(extension): bring Sim chat and page context to Chrome
- feat(mcp): type mcp block replies from declared output schemas
- feat(workflows): let a synchronous run continue in the background after a wait timeout
- feat(library): Best AI Agent Builders for Automated Daily Email Digests
- feat(library): Best AI Agents for Meeting Notes and Follow-Ups: 6 Options Compared
- feat(search): unify organization search and reviewed assistant actions
- feat(files): page, search, look up and roll up workspace files over the session API
- feat(db): seal account tokens by default and backfill them during migrate
Improvements
- improvement(sim-links): cleanup and simplify pass on the resource layout
- improvement(sim-links): use the shared resource table layout
- improvement(sim-links): show each link's destination favicon
- improvement(auth): unify sign-in and access pages
- improvement(comparisons): lead the OpenAI AgentKit page with the Agent Builder shutdown migration
- improvement(sandbox): pause idle chat workbenches instead of keeping them running
- perf(knowledge): reconcile a completed listing in one pass over its windows
- perf(admin): read dashboard ledger usage one bounded scan per entity
- perf(db): serve workspace usage drill-downs index-only on usage_log
- perf(audit-logs): read a listing narrowed only by time through per-workspace keyset scans
- perf(outbox): resume each retention batch where the previous run's batch ended
- perf(file-search): probe each backfill page's revisions by primary key
- perf(audit-logs): index organization-level rows and read them as two keyset parts
- perf(files): page the Files browser and resolve files without listing the workspace
- perf(db): index a workspace's live files in upload order
- perf(db): cut hot-path database work and close copilot cleanup gaps
Bug Fixes
- fix(docs): simplify selection and verify media interactions
- fix(search): accept Fireflies data-array responses
- fix(integrations): align connection header actions
- fix(search): trace live provider latency and partial failures
- fix(mcp): honor json schema openness in mcp output shapes
- fix(search): harden assistant review and account discovery
- fix(sandbox): correct the E2B build default in the Pi sizing doc
- fix(extension): isolate embedded pages from tracking
- fix(mothership): settle a sim_cli wait that outlasted --wait-timeout as done, not failed
- fix(search): remove the extra assistant tools gate
- fix(executor): bound condition loops and reject unnamed variable assignments
- fix(search): unify navigation and preserve action review history
- fix(billing): hold free plans to their allowance mid-run
- fix(integrations): one integration-access verdict across the catalog, @ menus and search, enforced by an audit
- fix(search): inline action review and unify account menus
- fix(workflows): refuse new placements of sunset blocks in workflow edits
- fix(billing): correct the Pi sizing note on E2B's resource maximums
- fix(billing): price Pi sandboxes at their build resources
- fix(audit-logs): list an organization's audit log through its single scope predicate again
- fix(cleanup): keep shared chat files, sweep inline images by prefix, and make room refetches wait
- fix(scim): harden directory lifecycle and clarify group mappings
- fix(billing): serialize Gmail inbox allowance decisions so racing alias signups can't both keep it
- fix(ci): fail the promote wait on a digest lookup error instead of retrying it
- fix(files): cap how long a room delivery waits for its refetches
- fix(library): merge duplicate sections and FAQs in the ecommerce and Zapier alternatives posts
- fix(desktop): hold the GitHub credential check open while the e2e asserts its pending state
- fix(billing): withhold the free allowance from Gmail aliases of an existing account
- fix(ci): predict the promoted app digest instead of trusting a read right after the retag
Other Changes
- chore(search): diagnose unsupported Fireflies response shapes
- chore(trigger): run tasks on the bun-1.4 runtime
- docs(billing): scope the usage_log workspace index note to created_at windows
- test(mothership): drive a draft run past a wait slice through the real controller
- docs(library): update 6-best-ai-observability-tools-for-production-agents-in-2026
- chore(deps): bump re2js to 2.8.7
- docs(library): update ai-agent-vs-chatbot
- Merge pull request #9426 from simstudioai/staging
- chore(deps): drop the stray bun tag hunk from the zod patch
- chore(ci): authenticate Trigger.dev deploys with per-environment API keys
- chore(deps): replace deprecated OpenTelemetry trace SDK packages with @opentelemetry/sdk-trace
- chore(deps): dependency hygiene cleanup
- docs(cli): add agent skills setup to the CLI overview
helm-chart-1.11.11
A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents
helm-chart-1.11.10
A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents
v0.9.36
Features
- feat(library): Best AI Agents for Drafting Social Media Posts: 4 Platforms Compared
- feat(library): Best AI Agent Platforms for Customer Onboarding: A Buyer’s Guide
- feat(library): 7 Best AI Assistants for Inbox Management and Reply Drafting in 2026
Bug Fixes
- fix(ci): bound a stalled bun install and let the helm test probe wait for routing
Other Changes
- chore(tls): drop the CA distrust step from the Bun services now that Bun ships the blocklist
- docs(library): update best-ai-agents-ecommerce-operations-2026
- chore(db): drop the job log schedule index the occurrence unique index covers
helm-chart-1.11.9
A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents

