Skip to Content
Aionis currently ships as a local-first Lite Runtime for developer machines and self-managed deployments.
Get StartedQuickstart

Quickstart

This guide gets a local Aionis Runtime, SDK, and optional MCP bridge running on your machine. The goal is not just to store a memory. The goal is to complete one governed Agent loop:

observe -> guide -> agent action -> feedback -> measure -> snapshot

Aionis is local-first today. It is designed to sit beside your Agent host and compile governed context for that host.

Prerequisites

RequirementWhy it matters
Node.js 22+The Lite Runtime uses the Node SQLite runtime.
An embedding keyRecall needs embeddings. MiniMax is the shortest path today.
A local shellThe quickstarts start the Runtime and run SDK scripts locally.

The Lite Runtime defaults to loopback and local unauthenticated use. It is not a hosted multi-tenant control plane.

One-command Install

The fastest path is the installer package:

MINIMAX_API_KEY="your-key" npx @aionis/create@latest --provider minimax --quickstart sdk

The installer clones the Runtime, installs the workspace packages, writes a local .env, builds the SDK/MCP packages, and runs the selected quickstart.

If you already cloned the repository, use the local workflow below.

Local Repository Setup

git clone https://github.com/ostinatocc/Aionis.git cd Aionis npm install

Configure embeddings:

export EMBEDDING_PROVIDER="minimax" export MINIMAX_API_KEY="your-minimax-key"

Run the SDK quickstart:

npm run -s runtime:quickstart:sdk

That quickstart exercises the product path:

  1. remember writes ordinary scoped memory.
  2. observeStep records execution evidence.
  3. guideForRole compiles governed Agent context.
  4. feedbackFromOutcome attributes the result to memory that was actually exposed by the guide.
  5. measureRun reports whether memory helped or created risk.
  6. snapshotRun creates an operator-facing replay view.

What Success Looks Like

A successful run prints a JSON result with fields like:

{ "prompt_preview": "AIONIS EXECUTION CONTEXT...", "execution_context_contract": "aionis_execution_agent_context_v1", "memory_use_receipt_visible": true, "used_memory_ids": ["mem_..."], "snapshot_visible": true }

The important part is the contract shape:

FieldMeaning
prompt_previewThe Agent-facing context compiled by Aionis.
memory_use_receipt_visibleThe guide includes a compact audit of what was used or suppressed.
used_memory_idsThe host can attribute outcome only to memory exposed by that guide.
snapshot_visibleOperator replay can explain what Aionis admitted and why.

Choose Your First Loop

If you are buildingStart withWhat it proves
TypeScript or Node Agentnpm run -s runtime:quickstart:sdkremember -> guide -> feedback -> measure -> snapshot
Claude Code or Cursornpx @aionis/mcp@latest --base-url http://127.0.0.1:3001 --scope my-projectMCP tools can record steps and compile context
Raw HTTP servicenpm run -s runtime:quickstart:httpPublic HTTP surface without SDK helpers
Multi-agent systemnpm run -s runtime:quickstart:multi-agentShared execution memory across planner, worker, verifier, reviewer
External memory backendnpm run -s runtime:quickstart:memory-firewallGovern Mem0/Zep/vector/markdown candidates
Operator debuggingnpm run -s runtime:quickstart:flight-recorderRead-only incident replay without prompt payload

Source guide: AIONIS_QUICKSTART_MATRIX.md .

Minimal SDK Loop

import { agentPromptFromGuide, createAionisClient, feedbackFromGuide, } from "@aionis/sdk"; const aionis = createAionisClient({ baseUrl: "http://127.0.0.1:3001", scope: "my-project", }); await aionis.remember({ kind: "preference", text: "Do not reuse failed migration branches as current instructions.", }); const guide = await aionis.guide({ query_text: "Continue the migration from the current accepted path.", context_mode: "compact_agent", }); const prompt = agentPromptFromGuide(guide); const result = await agent.run(prompt); const usedMemoryIds = result.usedMemoryIds ?? []; if (usedMemoryIds.length > 0) { await aionis.feedback(feedbackFromGuide({ guide, run_id: result.runId, outcome: result.ok ? "positive" : "negative", reason: result.summary, used_memory_ids: usedMemoryIds, used_surface: "use_now", })); }

Common First-run Issues

SymptomFix
Runtime cannot recall anythingCheck EMBEDDING_PROVIDER and provider API key.
Guide has no useful historyMake sure tenant_id, scope, and Agent identity match between observe and guide.
Feedback is rejectedAionis only accepts attribution to memory IDs exposed by that guide.
MCP client sees no toolsConfirm the MCP server points at the same Runtime base-url.
You need production authThe public package is the local Lite Runtime; service auth is not the current edition.

Next