# Sim — Open-source AI workspace for building, deploying and running agents across 1,000+ integrations. > Source: The Agents Index — https://theagentsindex.com/sim (structured, researched, re-verified) > Facts last verified: 2026-09-03 Sim is an open-source AI workspace where teams build agents visually, conversationally in Chat, or through an API. It connects 1,000+ integrations and every major LLM, then deploys workflows as APIs, chats or MCP tools. | Fact | Value | | --- | --- | | Website | https://sim.ai | | Price | from $25/seat per month billed monthly, $21/seat per month billed annually | | Free tier | Yes | Free forever: $0, 1,000 one-time credits, 1 workspace, no teammate invites, 10 concurrent executions, 5 GB file storage, 5 tables, 50,000 rows per table, 30-day log retention, 5-minute sync timeout; Sim Mailer, KB Live Sync, Sandboxes, Slack Connect, Access Control, SSO, SOC2, self-hosting and dedicated support all marked '–'. ## What it does **Writes code** · Partly — Generates workflow logic, blocks and schemas from a plain-English description, not application source code. > Describe what you want to automate in plain English. Sim acts as an AI agent builder, connecting the right blocks, models, tools, and data into a working workflow that you can review, customize, test, and deploy. > — https://www.sim.ai · Homepage, 'Describe it. Sim builds it.' section **Debugs and fixes** · Partly — Babysit Mode reads failing checks and review threads and runs bounded fixing rounds; no general 'diagnose a production failure' claim. > Optional check failures are included when Pi runs a fixing round but do not block checksGreen > — https://docs.sim.ai/workflows/blocks/pi · Babysit Mode section **Reviews code** · Yes — Review Code mode checks out an existing PR read-only and submits a GitHub review with inline comments. > Review Code — checks out an existing PR in a sandbox, analyzes it with bounded read-only access across the repository, and posts a GitHub review (summary + optional inline comments). > — https://docs.sim.ai/workflows/blocks/pi · Modes list, Review Code **Whole-codebase work** · Yes — Create PR clones the whole repository into a sandbox with full read, shell, edit and git access. > It clones the repo, lets the agent work with full read/shell/edit/git, pushes a branch, and opens a PR you review and merge. > — https://docs.sim.ai/workflows/blocks/pi · Create PR section **Ships it** · Partly — Deploys what it builds: workflows ship as versioned REST endpoints, with deploy/undeploy/rollback callable from CI. What ships is workflows, not code. > The v1 API exposes deploy, undeploy, and rollback endpoints — useful for CI/CD pipelines that ship a workflow after tests pass, or for reverting to the last known-good version from an incident script. > — https://docs.sim.ai/workflows/deployment/api · API deployment, 'Managing Deployments via the API' section **Done-for-you service** · No — You run the software yourself, hosted or self-hosted; Enterprise adds dedicated support, not a build-and-run service. > Sim is the open-source AI workspace where teams build, deploy, and manage AI agents. > — https://docs.sim.ai/introduction · Introduction, opening paragraph ## How much it does unattended **Runs autonomously** · Yes — Schedule triggers run a deployed workflow on a timer with no input and no operator present; webhook triggers fire on external events. > The Schedule trigger runs a workflow on a timer, on its own with no input — on a simple interval or a cron expression. > — https://docs.sim.ai/workflows/triggers/schedule · Schedule trigger, opening paragraph **Multi-agent** · Yes — Multiple agent blocks run in one workflow, and the Parallel container executes branches concurrently. > Wire blocks, models, and integrations into agent logic on Sim's visual builder, from one agent to many working in parallel. > — https://www.sim.ai · Homepage, 'Build' feature section **Agent permissions** · Yes — A Human in the Loop block pauses a run indefinitely for approval; Enterprise permission groups block disallowed models and block types mid-execution. > The Human in the Loop block pauses a run and waits for a person before it continues. Use it for approval gates, to collect feedback, or to gather input at a decision point. > — https://docs.sim.ai/workflows/blocks/human-in-the-loop · Human in the Loop, opening paragraph ## Which models it runs on **Claude** · Yes — Anthropic is one of 15+ supported providers; hosted Claude pricing is published per model. > Sim supports 15+ providers including OpenAI, Anthropic, Google Gemini, Groq, Cerebras, DeepSeek, Mistral, xAI, and OpenRouter. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Which AI models and providers are supported?' **GPT** · Yes — OpenAI models are supported, with hosted GPT-5/GPT-4.1 rates published at a 1.1x multiplier. > Sim supports 15+ providers including OpenAI, Anthropic, Google Gemini, Groq, Cerebras, DeepSeek, Mistral, xAI, and OpenRouter. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Which AI models and providers are supported?' **Open models** · Yes — Open-weight models run through Groq/Cerebras/OpenRouter, or locally via Ollama or vLLM at no API cost. > You can also run local models through Ollama or VLLM at no API cost. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Which AI models and providers are supported?' **Model choice** · Yes — You pick the model per Agent block across 15+ providers; the default is only a default. > The Agent block supports models from OpenAI, Anthropic, Google, Groq, Cerebras, DeepSeek, xAI, and more, plus local models through Ollama if you self-host. > — https://docs.sim.ai/getting-started · Getting Started FAQ, 'Can I use a different model?' ## Where you use it **In your editor** · Partly — No IDE extension; instead deployed workflows are callable from Cursor, VS Code, Claude Code and Codex as MCP tools. > Deploy your workflows as MCP tools to make them accessible to external AI assistants like Claude Desktop, Cursor, and other MCP-compatible clients. > — https://docs.sim.ai/workflows/deployment/mcp · MCP deployment, opening paragraph **On the command line** · Yes — A `sim` CLI runs workflows, queries tables and reads logs, with a JSON output mode for scripting. > `sim` is the command line for Sim. Sign in once, then run workflows, query tables, move files, search knowledge bases, and read run logs from the terminal. > — https://docs.sim.ai/cli · Sim CLI, opening paragraph **In your pipeline** · Partly — Deploy, undeploy and rollback are API calls intended for CI/CD pipelines; there is no pull-request review surface. > Every command has a `--output json` mode, so results pipe cleanly into `jq`, cron jobs, CI pipelines, and any other tool you already use. > — https://docs.sim.ai/cli · Sim CLI, opening paragraph **In a browser** · Yes — The product is a hosted web workspace: Chat, visual builder, tables, knowledge bases and logs. > Sim is the open-source AI workspace where teams build, deploy, and manage AI agents. Build visually in the workflow builder, conversationally in Chat, or with code through the API. > — https://docs.sim.ai/introduction · Introduction, opening paragraph ## Whose machine it runs on **Self-hosted** · Yes — Docker Compose and Kubernetes deployments are documented and free; the pricing table nevertheless lists 'Self Hosting' only under Enterprise. > You can also self-host Sim for free on your own infrastructure. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Is Sim free to use?' **Open source** · Yes — Apache 2.0 on GitHub; the docs add that SSO and access control carry a separate license requiring a subscription for production use. > Yes. Sim is open source under the Apache 2.0 license. The full source code is available on GitHub and you can self-host it, contribute to development, or modify it for your own needs. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Is Sim open source?' ## What it costs to run **How it meters** · Yes — Per seat per month plus metered credits: 1 credit = $0.005, 1 credit per run plus model tokens. > Sim uses credits as the unit of measurement for all usage. 1 credit = $0.005. > — https://docs.sim.ai/platform/costs · Cost calculation, 'Credits' section **Free tier** · Yes — Free plan, self-serve signup, 1,000 one-time credits, one workspace, no sales call. > Sim offers a free Community plan with 1,000 one-time credits to get started. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Is Sim free to use?' **API access** · Yes — Deployed workflows expose a REST execute endpoint with sync, streaming and async modes; TypeScript and Python SDKs exist. > Deploy your workflow as a REST API endpoint that any application can call directly. Supports synchronous, streaming, and asynchronous execution modes. > — https://docs.sim.ai/workflows/deployment/api · API deployment, opening paragraph **MCP server** · Yes — Two directions: workflows are published as MCP tools, and external MCP servers can be added as agent tools. > This turns your workflows into callable tools that can be invoked from anywhere. > — https://docs.sim.ai/workflows/deployment/mcp · MCP deployment, opening paragraph **Bring your own key** · Yes — Bring-your-own provider keys pay the provider at base rates with no markup; hosted keys carry a 1.1x multiplier. > Bring Your Own Key (BYOK) is supported so you can use your own API keys at base provider pricing with no markup. > — https://docs.sim.ai/introduction · Introduction FAQ, 'Which AI models and providers are supported?' ## Buying it for a team **A company can buy it** · Yes — Shared organization workspaces with seats are sold on Team and Enterprise plans; Enterprise is quote-only. > Shared (organization) workspaces live under an organization and are available on Team and Enterprise plans. > — https://docs.sim.ai/platform/permissions · Roles and permissions, 'Workspaces and Organizations' section **Seat model** · Yes — Priced per user/month ($25 Pro, $100 Max); Enterprise invites need an available seat, Team plans add one on accept. > Enterprise invites require an available seat at invite time; on Team plans, a seat is added automatically when the invitee accepts. > — https://docs.sim.ai/platform/permissions · Roles and permissions, 'Workspace Limits by Plan' section **Pooled budget** · Yes — Team plans pool credits across all seats; purchased credits go into the shared pool and the weekly refresh scales with seats. > Team plans pool credits across all seats in the organization. > — https://docs.sim.ai/platform/costs · Cost calculation, 'Plans' section **Admin controls** · Partly — Enterprise Access Control groups restrict which model providers and block types users may run, enforced in the executor; not available below Enterprise. > Access Control lets organization admins define permission groups that restrict what each set of users can do — which AI model providers they can use, which workflow blocks they can place, and which platform features are visible to them. > — https://docs.sim.ai/platform/enterprise/access-control · Access Control, opening paragraph **Audit log** · Partly — Tamper-evident organization audit log with UI, API and CLI access, documented under the Enterprise section. > Audit logs give your organization a tamper-evident record of every significant action taken across workspaces — who did what, when, and on which resource. > — https://docs.sim.ai/platform/enterprise/audit-logs · Audit Logs, opening paragraph **Single sign-on** · Partly — Both OIDC and SAML 2.0, with a verified email domain required; the plan table marks SSO available on Enterprise only. > Single Sign-On lets your team sign in to Sim through your company's identity provider instead of managing separate passwords. Sim supports both OIDC and SAML 2.0. > — https://docs.sim.ai/platform/enterprise/sso · Single Sign-On (SSO), opening paragraph ## What happens to your code **Opt out of training** · Partly — No customer-facing training opt-out switch; the vendor commits that Google-API data is never used for generalized model training, and self-hosting keeps data on your own infrastructure. > Any Google Data used within Sim is used only for features tied to that specific user and is not used for generalized AI/ML training or shared model improvement across users. > — https://www.sim.ai/privacy · Privacy Policy, AI processing / Google Data section **Data residency** · Yes — United States only on the hosted service, in AWS us-east-1. No EU region is offered, so self-hosting is the alternative. > Sim's primary hosting region is AWS us-east-1 in the United States. > — https://www.sim.ai/privacy · Privacy Policy, section 3 'Transfer Of Data' **Getting out** · Partly — Purchased credits never expire, but the weekly refresh allowance does not carry over; data leaves through the API, CLI and table exports rather than a one-click account export. > Expiration: Purchased credits do not expire > — https://docs.sim.ai/platform/costs · Cost calculation, 'Purchasing Additional Credits' section **Certifications** · Partly — SOC2 is claimed on the homepage but the plan table lists 'SOC2 Compliance' only in the Enterprise column; the privacy policy addresses GDPR and CCPA. No ISO 27001 claim found. > Trusted by over 100,000 builders, SOC2 compliant, and production-ready for teams of every size. > — https://www.sim.ai · Homepage, introductory summary paragraph above the hero ## Platform record (as of 2026-08-30) Reported by the code-hosting platform, not by the vendor. | Fact | Value | | --- | --- | | Licence | Apache-2.0 | | Stars | 29490 | | Forks | 3803 | | Last push | 2026-08-29 | ## Provenance 1 of 24 sources behind the facts above are independent of the vendor. ## Coverage elsewhere Pages about this product that the vendor does not control. The label states how independent each one is. | Source | Kind | Read | | --- | --- | --- | | rywalker.com | Independent source | 2026-08-18 | | dev.co | Independent source | 2026-08-18 | ## What changed - 2026-09-03 — Capabilities · Commercial terms · Free tier · Price - 2026-09-02 — Capabilities · Commercial terms - 2026-08-31 — Capabilities · Commercial terms · Free tier · Price - 2026-08-30 — Capabilities · Commercial terms · Free tier · Price - 2026-08-19 — Github url,editor note - 2026-08-18 — One-liner · Summary ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Sim, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth. Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.