Skip to Content
Aionis v0.2 is ready for local agent loops, MCP clients, SDK integrations, and self-managed Runtime deployments.
Developer PlatformGet StartedQuickstart

Quickstart

This guide gets a local Aionis Runtime and product API running on your machine, then shows how to connect SDK, HTTP, MCP, AIFS, or native plugins. 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 keyNot needed for the first-value demo. Recall-backed guide flows need embeddings; OpenAI-compatible embeddings are the default path.
A local shellThe quickstarts start the Runtime and run SDK scripts locally.

The Lite Runtime defaults to loopback and local unauthenticated use, which keeps the first install fast for local Agent development.

One-command Install

The fastest path is the installer package:

npx @aionis/create@latest

The installer clones the Runtime, installs Runtime dependencies, writes a local .env, runs the Runtime build check, and starts the no-key first-value demo. SDK, MCP, and Claude Code integrations are published from their own package repositories and connect to this Runtime through the product API.

For the full SDK quickstart with recall-backed guide output:

OPENAI_API_KEY="your-key" npx @aionis/create@latest --provider openai --quickstart sdk

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

Optional Claude Code Plugin

If your first target is Claude Code, install Runtime into a side directory:

npx @aionis/create@latest .aionis-runtime

Then start Runtime:

cd .aionis-runtime npm run -s lite:start

Now run Claude Code from your project:

claude

Inside Claude Code, install the plugin:

/plugin marketplace add https://github.com/ostinatocc/aionis-claude-code /plugin install aionis@aionis-claude-code /aionis:onboard

Claude Code will receive Aionis context before prompts and Aionis will record execution evidence after tool use. The plugin path installs user-level hooks and MCP tools, so future projects do not need manual hook setup.

Local Repository Setup

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

Run the first-value demo without an embedding key:

npm run -s runtime:demo:first-value

Then configure embeddings:

export EMBEDDING_PROVIDER="openai" export OPENAI_API_KEY="your-openai-key"

MiniMax is also supported:

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
First local proofnpm run -s runtime:demo:first-valueOutdated or low-authority retrieved memory is governed before prompt use
Claude Code/plugin install aionis@aionis-claude-codePlugin hooks inject context and record execution evidence automatically
Cursor or MCP-only hostsnpx @aionis/mcp@latest --base-url http://127.0.0.1:3001 --scope-from workspace --workspace-id-store userMCP tools can record steps and compile context
TypeScript or Node Agentnpm run -s runtime:quickstart:sdkremember -> guide -> feedback -> measure -> snapshot
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 want remote access controlsRun the managed-server configuration path with API-key or JWT auth settings.

Next