helm-chart-1.11.212026-11-19
A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents
v0.9.632026-11-19
Features
- feat(search): import large permission snapshots in bounded parts (#10191)
- feat(library): Best AI Agent Platforms for University Student Services and IT (#10161)
- feat(library): What Do Enterprise AI Agent Platforms Charge for SSO and Audit Logs? (#10163)
- feat(library): How Do AI Agents Triage Security Alerts With Human Approval? (#10162)
- feat(library): AI Agent Skills for Business Teams: A 30-Day Learning Guide (#10160)
Improvements
- improvement(computer-use): name the activation step when an element refuses an advertised action (#10189)
- improvement(seo): clarify buying guides and migration checks (#10184)
- improvement(docs): publish the People guide (#10154)
- improvement(pii): mask texts with many matches in linear time and retry failed chunks three times (#10151)
- improvement(search): name each Search MCP result's sender, owner or organizer (#10153)
- improvement(mothership): keep workflow test-run results inside the agent window (#10147)
- improvement(search): drop unusable citation IDs and title-only previews from Search MCP results (#10143)
- improvement(landing): add pricing faq and drop retired sdk claims from llms.txt (#10140)
Bug Fixes
- fix(integrations): hide retired hugging face providers, encode posthog ids, and trim zep final ids (#10190)
- fix(integrations): keep saved output references valid and encode firecrawl job ids (#10187)
- fix(computer-use): observe an app's floating and panel-level windows (#10188)
- fix(integrations): reject invalid kalshi order flags and anchor the arxiv link match (#10186)
- fix(integrations): close follow-ups from the integration validation audits (#10183)
- fix(integrations): validate firecrawl, context.dev, apify, bright data, browser use, reducto, pulse and extend (#10180)
- fix(integrations): validate clerk, crowdstrike, infisical, ketch, onepassword, persona, rootly (#10171)
- fix(integrations): validate polymarket, kalshi, sftp, ssh, smtp, jupyter and temporal (#10181)
- fix(integrations): validate spotify, buffer (#10175)
- fix(integrations): validate quiver, thrive, profound, agentphone, sendblue, linq, quartr (#10178)
- fix(integrations): validate mongodb, neo4j and upstash (#10172)
- fix(integrations): validate exa, tavily, serper, linkup, parallel ai, perplexity, jina, duckduckgo, wikipedia and arxiv (#10179)
- fix(integrations): validate hugging face, elevenlabs, gamma, higgsfield and dspy (#10174)
- fix(integrations): validate grafana, posthog (#10173)
- fix(integrations): validate wealthbox, lemlist, emailbison, instantly, attio (#10177)
- fix(integrations): validate fathom, grain, obsidian and fireflies (#10166)
- fix(integrations): validate cursor, devin, vercel (#10170)
- fix(integrations): validate ashby (#10167)
- fix(integrations): validate google maps, google translate, google bigquery, google books, google appsheet and google pagespeed (#10165)
- fix(integrations): validate agentmail (#10169)
- fix(integrations): validate cloudtrail, codepipeline, sqs and ssm (#10168)
- fix(integrations): validate pinecone, qdrant, elasticsearch and zep (#10164)
- fix(computer-use): show computer use controls on organization Desktop settings (#10176)
- fix(pii): describe the mask client's retry budget the way it actually behaves (#10156)
- fix(landing): anchor the pricing faq section at #faq (#10157)
- fix(mothership): extend the workflow pickup grace for a view that re-attaches during it (#10152)
- fix(mothership): cut oversized run errors after projection and collapse long block runs (#10150)
- fix(lint): use structural placeholders for table input references (#10149)
- fix(mothership): skip the 30s workflow pickup wait when no chat view is reading (#10148)
- fix(lint): check table json inputs that hold bare block references (#10146)
- fix(desktop): show Desktop settings on the organization and account settings surfaces (#10144)
- fix(search): widen Slack day modifiers so a member's time zone never empties a date window (#10145)
Other Changes
- test(desktop): stub the computer use availability hook in the prevent-sleep tests (#10182)
- docs(library): update best-ai-agents-for-it-helpdesk-teams (#10159)
Contributors
- @waleedlatif1
View changes on GitHub
v0.9.622026-11-17
Features
- feat(library): Zapier Pricing at Scale: What Tasks Really Cost and When AI Agents Are Cheaper (#10135)
- feat(library): How Do You Build a Governed Workday AI Agent for Employee Onboarding and Offboarding? (#10134)
- feat(library): 6 Best StackAI Alternatives in 2026 After the Asana Acquisition (#10133)
- feat(library): Top AI Support Copilots vs Autonomous Support Agents in 2026 (#10132)
- feat(library): How to Pilot an AI Agent Platform Through Security Review (#10131)
Improvements
- improvement(computer-use): list only what changed in the observation after an action (#10126)
- improvement(ci): reuse bounded compiler state for acceptance builds (#10127)
- improvement(ci): omit unused browser maps from acceptance builds (#10125)
Bug Fixes
- fix(gitlab): scale group discovery and permission-aware search (#10138)
- fix(ci): restore ESM checks and synchronize docs searches (#10139)
- fix(billing): withhold hosted Fal.ai image generation from free-plan payers (#10136)
Other Changes
- ci: bump the actions group across 1 directory with 3 updates (#10130)
Contributors
- @dependabot[bot]
- @waleedlatif1
View changes on GitHub
v0.9.612026-11-17
Improvements
- improvement(comparisons): add langchain migration steps and human approval channels (#10124)
- improvement(search): describe Slack file hits and leave out GitLab sources that grant the reader nothing (#10120)
- improvement(ci): scope reviewed root audits to their checks (#10121)
- improvement(resume): resolve a pause point's block from its loop-scoped context id (#10119)
Bug Fixes
- fix(search): say a Slack file hit can return its full text rather than promising it (#10123)
Contributors
- @waleedlatif1
View changes on GitHub
v0.9.602026-11-17
Features
- feat(search): add GitLab group sources with per-project permissions (#10107)
- feat(library): Best AI Agent Platforms for Refund and Purchase Order Approvals in 2026 (#10108)
- feat(library): How to Replace Brittle Automation Scripts With Reliable AI Agents (#10102)
Improvements
- perf(sse): split only the newly decoded text in stream line readers (#10118)
- improvement(library): check sim's integration counts against the catalog (#10113)
- improvement(computer-use): wait for an app's first observable window after launching it (#10112)
- improvement(computer-use): report an advertised action the element refuses as unsupported, with the snapshot still valid (#10106)
Bug Fixes
- fix(library): attribute sim counts by clause and table row, not capitalized words (#10115)
- fix(search): validate GitLab group scope before permission refresh (#10117)
- fix(computer-use): find a save panel control's window through its ancestors when it reports none (#10116)
- fix(pii): tokenize long unbroken runs in linear time so workers stop missing health pings (#10111)
- fix(computer-use): treat an attribute-unsupported refusal of an advertised action as unsupported (#10109)
- fix(resume): capture pause block names and keep the resume page off the execution snapshot (#10104)
- fix(people): answer the cookie consent card in the people e2e so it can't block mobile taps (#10101)
Other Changes
- docs: match integration counts to the catalog (#10110)
- docs(library): update best-ai-agent-platforms-hr-employee-questions (#10105)
Contributors
- @b84330808
- @waleedlatif1
View changes on GitHub
v0.9.592026-11-16
Features
- feat(library): AI Agent Identity, Credential Management, and Audit Trails: Enterprise Guide (#10092)
- feat(library): Snowflake and QuickBooks MCP Servers for AI Agents (#10091)
- feat(library): Glean vs Dust: Which Enterprise AI Platform Should You Choose? (#10090)
Improvements
- perf(executor): stop re-parsing the whole structured output on every streamed token (#10087)
Bug Fixes
- fix(integrations): address release review findings on the sweep (#10098)
- fix(slack): keep refused file reads from suggesting a reconnect and find the download URL for trigger files (#10095)
- fix(pii): cap each batched NER pass at one window of characters (#10099)
- fix(gitlab): clarify permission validation failures (#10096)
- fix(confluence): index text from Caelor Optics HTML macros (#10093)
- fix(slack): download files from Slack's download URL and never send the token off its file host (#10088)
- fix(github): encode owner and repo in request paths (#10085)
- fix(search): follow Slack's file download redirects without carrying the token off its file host (#10084)
- fix(table): apply filter and sort builder rules pinned on agent tool rows (#10083)
- fix(search): read the full text of Slack canvases and files instead of the preview (#10082)
- fix(integrations): close gaps found in the final sweep audit (#10081)
- fix(integrations): validate dynamics 365, zoho desk, rippling, okta, sailpoint and snowflake (#10072)
- fix(blocks): read the mapper operation from the tool-call context in j–z blocks (#10078)
- fix(blocks): read the mapper operation from the tool-call context in internal and a–i blocks (#10077)
- fix(blocks): read the mapper operation from the tool-call context in google, microsoft and atlassian blocks (#10076)
- fix(integrations): validate github, gitlab, linear, slack, pagerduty, incident.io, sentry and datadog (#10071)
- fix(agent): drop tool-row values left from a previous operation (#10080)
- fix(brex): leave a blank spend-limit buffer unset (#10079)
- fix(integrations): validate twilio, sendgrid, resend, mailgun, discord, telegram and whatsapp (#10073)
- fix(integrations): validate shopify, brex, ramp, zoom, calendly, cal.com, typeform, webflow and wordpress (#10074)
- fix(blocks): read the mapper operation from the tool-call context in aws and infra blocks (#10075)
- fix(blocks): read the mapper operation from the tool-call context and ratchet raw reads (#10070)
- fix(providers): mark retired Nebius models and move the default off one (#10069)
- fix(docs): normalize path separators in the content build on Windows (#10067)
- fix(pii): bound NER memory per worker so large texts stop OOM-killing Presidio workers (#10068)
Other Changes
- docs(library): restore faq entries dropped by recent refreshes (#10100)
Contributors
- @Anandb71
- @b84330808
- @mofopeadegoke
- @waleedlatif1
View changes on GitHub
v0.9.582026-11-15
Features
- feat(library): Microsoft Copilot Studio vs Power Automate: Which Should You Use? (#10047)
- feat(library): How Do You Build a Governed AI Agent for Microsoft Intune Device Management? (#10045)
- feat(desktop): quick chat window on a global shortcut (#10025)
Improvements
- improvement(computer-use): keep an element's id stable across observations (#10046)
- improvement(egress): route workspace requests through the organization's egress gateway (#10040)
- improvement(search): log the shape of each search and the source, kind, and size of each read (#10042)
- improvement(api): log the v2 error code, field, and refusal reason on the request's closing line (#10033)
- improvement(chat): show background task and scheduled job turns as messages (#10032)
Bug Fixes
- fix(sandbox): skip interval ticks while the previous one is still in flight (#10063)
- fix(realtime): keep admin block locks out of write-role graph replaces (#10062)
- fix(sso): admit callbacks under the provider id the plugin resolved (#10054)
- fix(copilot): hold callerless runs to the read grant for server tool writes (#10061)
- fix(sso): refuse SSO callback user writes outside the provider's verified domain (#10060)
- fix(executor): resume a paused draft run on the graph it paused on (#10057)
- fix(inbox): require an authenticated sender before an email acts as a workspace member (#10059)
- fix(helm): reject placeholder secrets and stop shipping them in example values (#10052)
- fix(webhooks): reject auth that reads an unresolved env-var secret (#10055)
- fix(workspaces): stop workspace admins from moving the billed account (#10058)
- fix(mcp): gate public workflow MCP servers on public API governance (#10056)
- fix(mcp): bound legacy mcp server name and description like the v2 contract (#10053)
- fix(helm): confine the PII service with its NetworkPolicy whenever pii is enabled (#10051)
- fix(csp): remove shadowed permissive policy from workflow execute routes (#10050)
- fix(files): compare Markdown toolbars with their current selection (#10049)
- fix(computer-use): stop reporting closed menu items past the cap as a truncated state (#10043)
- fix(files): keep Markdown tables readable while scrolling (#10041)
- fix(integrations): address release review findings on the integration sweep (#10039)
- fix(workspaces): hand off a departing member's files without binding every file id (#10038)
- fix(integrations): resolve agent tool-call operations and align remaining requests with vendor specs (#10036)
- fix(integrations): address the final release audit findings (#10035)
- fix(integrations): validate monday, asana, clickup, airtable, notion, supabase, amplitude, box, docusign, and dropbox (#10030)
- fix(computer-use): read elements reported at infinity without a frame instead of crashing the helper (#10034)
- fix(integrations): validate zendesk, pipedrive, and intercom against vendor specs (#10028)
- fix(mailchimp): archive members correctly, add permanent delete, and align requests with the marketing api (#10031)
- fix(integrations): validate square, quickbooks, oracle fusion, sap, and workday; show the oracle fusion icon (#10029)
- fix(integrations): validate servicenow, salesforce, and hubspot against vendor docs (#10027)
- fix(knowledge,files): count knowledge base documents per base and index the modified-order file list (#10026)
Other Changes
- docs(library): update apache-2-0-vs-fair-code (#10048)
- docs(library): update can-ai-agents-talk-to-each-other-multi-agent-communication-explained (#10044)
Contributors
- @waleedlatif1
View changes on GitHub
helm-chart-1.11.202026-11-15
A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents
v0.9.572026-11-14
Features
- feat(monaco): add Monaco CRM integration (#10009)
- feat(computer-use): batch 2-8 actions per call and read app state in one round trip per element (#9995)
Improvements
- improvement(search): skip the Slack channel lookup on channel-scoped searches and read channel names in any script (#10023)
- improvement(credentials): hold unsaved keyless subjects so trust policies applied later still match (#10011)
- improvement(blocks): share the tool-call fallback helper and tidy the Hex/Stripe validation code (#10014)
- improvement(search): name matching Slack channels and say whether a filtered channel exists (#10007)
- improvement(search-mcp): log why a batched read returned an error for a document (#10010)
- improvement(search-mcp): log the field names a rejected tool call's arguments carry (#10003)
- improvement(computer-use): fold empty layout groups and compact the accessibility tree shown to the model (#9997)
- improvement(computer-use): remove the activity strip above the chat composer (#9994)
Bug Fixes
- fix(computer-use): type after a focus click only once the caret is confirmed at the end (#10019)
- fix(hex): type the block projectVersion output as any and mark category descriptions optional (#10022)
- fix(credentials): cap the Databricks identity check with a deadline and report no hold for an unheld reconnect subject (#10021)
- fix(monaco): reject a stage key and a stage ID together on opportunity writes (#10020)
- fix(slack): let Block Kit messages carry notification text (#10018)
- fix(desktop-browser): refuse typing behind an unmarked full-screen modal or when no sampled point lands (#10013)
- fix(computer-use): tighten batch and click-to-focus edge cases from the staging audit (#10012)
- fix(google-drive): keep the page token an agent passes (#10008)
- fix(blocks): keep agent-supplied tool args that block mappers remap from dedicated fields (#10006)
- fix(hex,stripe): validate Hex and Stripe against their API docs (#10005)
- fix(computer-use): click an editor into focus when Accessibility cannot focus it (#10004)
- fix(aws-marketplace): check the container license's uncounted usage entitlement so every replica turns Enterprise on (#9996)
Other Changes
- chore(credentials): move the IAM refusal TSDoc back onto iamFailureMessage (#10024)
- docs(library): update best-ai-agent-platforms-2026 (#10002)
- docs(library): update best-ai-agents-invoice-processing-finance-reconciliation-2026 (#10000)
- docs(library): update open-source-ai-agent-platforms (#10001)
- docs(library): update best-ai-agents-for-customer-support-automation (#9999)
- docs(library): update best-ai-agent-marketplaces-template-libraries (#9998)
Contributors
- @waleedlatif1
View changes on GitHub
helm-chart-1.11.182026-11-14
A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents