Back to directory

Sim

A collaborative workspace for building, deploying and monitoring AI agents and workflows, connecting more than 1,000 integrations and every major LLM through a visual, conversational or code-based builder.

Sim

Sim keeps chat, workflows, file storage, structured tables and a knowledge base for agent memory in one workspace, accessible from a browser or a macOS desktop app, and lets a team build agents visually, conversationally or with code while monitoring runs, logs, schedules and workflow activity. It connects to services such as Slack, Notion, HubSpot and Salesforce alongside databases and every major LLM provider, including local models through Ollama and vLLM.

It is available as a cloud-hosted service, or self-hosted with an interactive npx sim-setup wizard that provisions a database, generates secrets, connects a chat API key, and starts the published Docker images; a cloned repository additionally unlocks source-based local development and Kubernetes deployment modes. It is built on Next.js and Bun, with PostgreSQL and Drizzle ORM, Better Auth for authentication, and E2B for remote code execution.

It is licensed under Apache-2.0.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.