Changelog
Every new feature, improvement, and fix in Sim, the open-source AI workspace, with release notes straight from GitHub.
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
v0.9.34
Features
- feat(db): add manual Trigger.dev task for the account token sealing backfill
- feat(tailscale): expand and validate API operations
Improvements
- improvement(changelog): lead with knowledge base portability
Bug Fixes
- fix(ci): only migrate an environment from its own branch
- fix(ci): queue migrate runs per environment instead of letting them overlap
- fix(credentials): send a conflicting OAuth reconnect back with a reason instead of a 500
- fix(chat): normalize markdown list and heading spacing
- fix(isolated-vm): drain worker host deploys without failing in-flight executions
- fix(deps): backport zod's leading collection size check so oversized bodies stop validating every element
- fix(library): consolidate duplicate sections and FAQs added by repeated refreshes
- fix(ci): find the last IndexNow submission through its check run, not the run's job list
- fix(deps): update nodemailer to 10.1.7 and undici to 7.30.1 for address-parser and fetch advisories
Other Changes
- chore(docker): pin Node and prep images for a read-only root filesystem
- docs(library): update best-ai-workflow-builders
- docs(library): update ai-agent-examples-by-department-and-industry
- docs(library): update agentic-ai-coding-tools-what-they-are-and-how-the-top-options-compare
- docs(library): update best-conversational-ai-platforms-crm-helpdesk
v0.9.33
Features
- feat(library): AI Coding Agents vs Code Completion Tools: Which Should Engineering Teams Choose?
- feat(mothership): run scheduled jobs as durable unattended chat turns
Improvements
- improvement(docs): build feature-branch docs previews only when docs change
- improvement(library): single JSON-LD source, Markdown articles, and IndexNow pings
- improvement(library): rank related posts by tag rarity, add backlinks, and widen comparison and pagination links
- improvement(auth): encrypt stored integration tokens
- improvement(execution): run sandbox workers on a dedicated worker host
Bug Fixes
- fix(mothership): hold callerless runs' sim_cli to read API scopes
- fix(mcp): answer an unpublishable workflow input on tool updates as validation, and match bare-name alternatives titles
- fix(mothership): retry a job dispatch whose usage read failed instead of skipping the run
- fix(billing): register the Stripe plugin only when the webhook secret is configured
- fix(gmail): clear the history cursor only from a poll that held one
- fix(db): count the billing and auth pools in the scaling guide and reset their mock between tests
- fix(library): correct vendor facts and remove self-ranking in comparison posts
- fix(ci): pick the CodeDeploy action when the app Deploy stage has sidecar actions
- fix(execution): close retired remote sandbox workers with a normal closure
- fix(egress): retry a gateway CONNECT once on connection failure and log each failed attempt
- fix(workflows): accept legacy input field types instead of rejecting them
- fix(logs): stop loading execution data and snapshots that reads do not use
- fix(db): isolate billing and auth connection pools, release the redeploy-check transaction early, cache integration tool schemas
- fix(mothership): close the scheduled-job review gaps
- fix(workflows): accept json input type and return 400 for unsupported input types
- fix(logs): keep provenance sidecars intact through log PII redaction
- fix(gmail): drop an expired history cursor instead of re-saving it every poll
- fix(mcp): classify unresolvable and egress-refused server URLs in discovery
- fix(models): mark OpenAI gpt-4.1-nano deprecated
- fix(workflow-tests): keep the error of a mock that throws
Other Changes
- docs(library): update ai-agent-examples-by-department-and-industry
- docs(library): update agentic-ai-coding-tools-what-they-are-and-how-the-top-options-compare
- docs(library): update best-conversational-ai-platforms-crm-helpdesk
- docs(library): update openai-vs-n8n-vs-sim
- docs(library): update agentic-ai-coding-tools-what-they-are-and-how-the-top-options-compare
- docs(library): update best-conversational-ai-platforms-crm-helpdesk
- docs(library): update best-ai-agents-for-lead-enrichment-2026
- docs(library): update langgraph-alternatives
- docs(library): update top-ai-assistants-2026
- docs(library): update best-ai-automation-tools-2026
- docs(library): update what-is-an-mcp-server
- chore(deps): upgrade Bun to 1.4.4
- docs(library): update ai-agent-examples-by-department-and-industry
- docs(library): update how-to-create-an-ai-agent
- docs(library): update dify-alternatives
- docs(library): update best-ai-agents-support-ticket-triage
v0.9.32
Features
- feat(knowledge): import knowledge base bundles through the API and
sim knowledge import - feat(monitoring): log event-loop lag, stalls, and in-flight route handlers
- feat(ec2): add Amazon EC2 integration
- feat(library): n8n vs Zapier vs Make: Which Automation Platform Is Best in 2026?
- feat(library): LangChain vs LangGraph: What’s the Difference and Which Should You Use?
- feat(library): CrewAI vs LangGraph vs AutoGen: Which Multi-Agent Framework Should You Choose?
- feat(library): OpenClaw vs Claude Cowork: Setup, Pricing, Security, and Scheduling Compared
Improvements
- improvement(insights): shorten the unassigned usage tooltip
- improvement(ci): balance integration jobs and retain documentation build caches
- improvement(executor): size payload compaction bottom-up instead of re-serializing every subtree
- improvement(file-parsers): parse spreadsheets on a worker thread
- improvement(ci): run affected suites and reuse production builds
Bug Fixes
- fix(tests): derive document grant expiry from one timestamp
- fix(ci): isolate desktop shard CLI regressions
- fix(file-parsers): share the event-loop slice across PDF parses and yield inside whole-document passes
- fix(ec2): describe the states each instance state-change tool actually returns
- fix(executor): resume payload compaction on a fresh stack every 256 levels
- fix(telemetry): send browser events to the configured collector and keep logs off the anonymous one
- fix(logs): treat a logs query path as withheld only when its content field was omitted
- fix(logs): mark withheld trace span content so logs query stops reporting it as missing
- fix(logs): yield to the event loop while exporting large trace rows
- fix(parsers): yield the event loop during PDF extraction and CSV row coercion
- fix(logs): cap logs-list pages that carry execution data
- fix(deps): update Next.js to 16.4.1, stop untrusted Office uploads reaching file-type's ASF loop, and patch transitive advisories
- fix(executions): skip archive materialization on status polls that read no output
- fix(logs): skip workflow state on logs query trace reads
- fix(logs): keep trace secret projection from blocking the event loop
- fix(library): correct facts in four new comparison posts
Other Changes
- docs(telemetry): describe the relay's disable gate and the anonymous endpoint's traces-only export
- ci: balance macOS Electron smoke shards by measured duration
v0.9.31
Features
- feat(chat): recall sent messages from composer
- feat(library): 6 Best Workato Alternatives for AI Agents in 2026
- feat(library): 6 Best OpenClaw Alternatives for Teams in 2026
- feat(library): 6 Best Lindy Alternatives in 2026 for AI Agents and Automation
- feat(library): 5 Best Claude Cowork Alternatives in 2026 for Shared and Scheduled AI Agents
Improvements
- improvement(emails): refresh the platform update broadcast
- improvement(docs): reduce navigation payload and build work
- improvement(mothership): calmer activity header: wait wording until a call's title streams, and pacing across a run's calls
Bug Fixes
- fix(mothership): hold a tool call's display grouping beside its arguments
- fix(docs): preserve clipboard activation and validate copied content
- fix(chat): validate restored contexts against send schema
- fix(mothership): report a paused Copilot workflow whose cancel lost the race to an unreported terminal run
- fix(mothership): report a Copilot workflow tool whose paused run settles after a resume or cancel
- fix(mothership): let the agent copy files between workspaces without Projects
- fix(mothership): keep display activity out of integration and mcp tool arguments
- fix(deps): pin patched xmldom, axios, follow-redirects, qs, proxy-addr, shell-quote, joi, and grpc-js
- fix(gemini): send the lowest thinking level when thinking is 'none' on Gemini 3
Other Changes
- docs(library): update langgraph-alternatives
v0.9.30
Features
- feat(mothership): discover every workspace mcp server without tagging
- feat(mothership): send workspace skill ids and descriptions in the chat inventory
- feat(helpscout): knowledge base connector, auto-registered triggers, 12 more tools, and validation fixes
- feat(helpscout): add Help Scout integration with OAuth and app credentials, selectors, and webhook triggers
Improvements
- improvement(docs): simplify integration page headers
- improvement(docs): refine screenshots, copy, and API interactions
- improvement(insights): clarify unassigned usage and refresh usage charts
- improvement(mothership): rank integration discovery by bm25 and connected services
- improvement(library): merge near-duplicate posts into their stronger pages
- improvement(mothership): show the worker's display copy for a turn error everywhere it is recorded
- improvement(sim-cli): publish each command's path aliases and renamed paths in the command inventory
Bug Fixes
- fix(ci): reset a broken desktop-live dev cache from a passing job
- fix(mothership): bound best-effort mcp discovery and stop retrying a down server every query
- fix(helpscout): require explicit tags to clear, validate custom field entries and positive IDs, and correct trigger and credential copy
- fix(insights): keep paused calendars visible and chart scales finite
- fix(comparisons): Retool self-hosting is on every plan, not Enterprise only
- fix(comparisons): lead Flowise copy with its end of life, qualify Retool self-hosting, and note the Zapier Agents migration
- fix(mothership): keep untagged mcp discovery side-effect free and the catalog resilient
- fix(tools): advertise json and any params without an object type, and name the invalid mcp argument
- fix(mothership): keep integration discovery working when a tagged mcp server fails or lists no tools
- fix(chat): keep previous messages stable when sending
Other Changes
- docs(library): correct vendor facts and Flowise status found in the library audit
- docs(library): rework Zapier alternatives into the lean roundup format
- docs(library): restructure open source AI agents guide around its head term
- docs(library): tighten n8n alternatives and fix its tool count
- docs(library): rework no-code AI agent builders roundup into the lean format
- chore(mothership): sync the Search assistant tool contract from mothership
v0.9.29
Features
- feat(mothership): let an agent chat list its owner's other live chats for history recall
Improvements
- improvement(search): return 30 previews by default for a Search MCP query across every source
- improvement(changelog): more relevant Search across sources
Bug Fixes
- fix(tls): distrust the roots behind the compromised eMudhra intermediates
- fix(credentials): declare service-account oauth policy on Snowflake, NetSuite, and Managed Agent tools
Other Changes
- docs(library): update byok-multi-model-ai-agent-builder
- docs(library): update best-ai-agents-for-scheduling-and-calendar-management-in-2026
- docs(library): update can-ai-agents-talk-to-each-other-multi-agent-communication-explained
- docs(library): update apache-2-0-vs-fair-code
v0.9.28
Features
- feat(library): Best Retool Alternatives in 2026 for Building AI Agents
- feat(library): Best Dust Alternatives in 2026 for AI Agent Workflows
- feat(library): Best Flowise Alternatives in 2026 for Production AI Agents
- feat(library): Best Langflow Alternatives in 2026 for Production AI Workflows
- feat(library): Best Vellum Alternatives in 2026 for Non-Engineers
- feat(library): Best Pipedream Alternatives in 2026 with Visual Builders
Improvements
- improvement(deps): shared Standard Webhooks verifier, MCP SDK 1.32.1, tiptap 3.31.4 with the prosemirror paste XSS fix
- improvement(comparisons): noindex self-hosted marketing pages, link every comparison, and add Zapier, Retool, Flowise lead answers
Bug Fixes
- fix(comparisons): stop recommending Flowise after its end of life and source its facts from Flowise
- fix(comparisons): Retool lists self-hosting on Enterprise only
Other Changes
- chore(mothership): drop unused worker contract copies
- chore(deps): audit and update dependencies, raise security override floors, collapse duplicate versions