Local AI Assistant

Product Shape

Local-first AI assistant that can run models, connect to tools, isolate workspaces, ingest documents, and expose a local API.

Ladder Result

Pick an AI-native desktop/local service stack, not just a chat UI.

Stack Implications

ConstraintStack implication
Local modelsModel runtime/engine boundary and hardware detection
MCP toolsConnector scope, subprocess management, tool permissions
WorkspacesSeparate documents, prompts, tools, vectors, model overrides
Local stateSQLite for sessions, memory, audit logs, durable metadata
Tool executionSandbox, inspection pipeline, audit events
Local APIOpenAI-compatible or app-specific API surface

Jan vs AnythingLLM Lessons

  • Jan shows a Tauri/Rust desktop shell, bundled local inference, MCP host capability, and local OpenAI-compatible API.
  • AnythingLLM shows a heavier orchestration platform with workspaces, RAG, provider breadth, agent flows, and multi-user Docker mode.
  • MyLocalGPT-style products should borrow the isolation and tool model without inheriting a heavy service stack too early.

First Quality Gates

  1. Workspace data and tools do not cross-contaminate.
  2. MCP/tool execution is scoped and auditable.
  3. Local state survives restart and is queryable.
  4. Secrets are not stored in mutable runtime blobs.
  5. Risky tools run in a sandbox or explicit restricted subprocess path.