kagura-memory 0.10.0

Python SDK for Kagura Memory Cloud — AI-driven memory management

Memory SDK — Python client for Kagura Memory Cloud

What is this?

This SDK connects your Python code to Kagura Memory Cloud, giving AI assistants the ability to remember, search, and learn from past interactions. It provides three clients for different use cases:

Client	Protocol	Use Case
KaguraAgent	MCP + LLM	AI-powered — auto-decides what to remember/recall from conversations
KaguraClient	MCP (JSON-RPC)	Direct memory ops — remember, recall, explore, reference, forget
ResourceClient	REST API	External data ingestion — push data from Slack, CI/CD, CRM into Kagura

Installation

pip install kagura-memory
# or
uv add kagura-memory

Quick Start

Configuration

Copy the example and fill in your credentials:

cp .kagura.json.example .kagura.json
# Edit .kagura.json — set api_key and mcp_url

Used by the CLI (kagura commands) and load_config() in Python code:

{
  "api_key": "kagura_your_api_key",
  "mcp_url": "http://localhost:8080/mcp/w/{workspace_id}",
  "model": "gpt-5.4-nano",
  "context_id": "auto"
}

Or use environment variables: KAGURA_API_KEY, KAGURA_MCP_URL, KAGURA_MODEL, KAGURA_CONTEXT_ID

Get your API key from the Kagura Memory Cloud Web UI: Integrations > API Keys

KaguraAgent — AI-Powered Memory

Let the AI analyze conversations and automatically decide what to remember and recall:

from kagura_memory import KaguraAgent, Session, Message

agent = KaguraAgent(api_key="kagura_...", model="gpt-5.4-nano")

session = Session(messages=[
    Message(role="user", content="FastAPIでOAuth2を実装したい"),
    Message(role="assistant", content="Authlibを使うパターンが推奨です..."),
    Message(role="user", content="なるほど、これ覚えておいて"),
])

async with agent:
    result = await agent.process(session, deep=True, verbose=2)
    print(f"Remembered: {len(result.remembered)}, Recalled: {len(result.recalled)}")

Supports OpenAI, Claude, Gemini via LiteLLM, and Ollama for local models:

# Local LLM via Ollama (no cloud API key needed)
agent = KaguraAgent(api_key="kagura_...", model="ollama/qwen3:30b")

Ollama Local Model Requirements

Model	Size	Context	Min VRAM	Recommended GPU
qwen3:30b (recommended)	19 GB	256K	24 GB	RTX 4090 or equivalent
qwen3:14b	9.3 GB	40K	16 GB	RTX 4080 or equivalent

Recommended minimum: qwen3:30b on an RTX 4090 (24 GB VRAM) or equivalent.

Smaller models (< 30B parameters) may produce lower quality memory analysis — summaries may lack searchable keywords, and recall query generation may be less precise.

KaguraClient — Direct Memory Operations

For programmatic control without LLM:

from kagura_memory import KaguraClient

async with KaguraClient(api_key="kagura_...", mcp_url="https://...") as client:
    await client.remember(context_id="dev", summary="OAuth2 pattern", content="Use Authlib...")
    results = await client.recall(context_id="dev", query="OAuth2", k=5)
    await client.explore(context_id="dev", memory_id="uuid", depth=3)

ResourceClient — External Data Ingestion

Push data from external systems into Kagura so AI can search it:

from kagura_memory import ResourceClient, ResourceEventRequest

async with ResourceClient.from_mcp_url(api_key="kagura_...", mcp_url="http://localhost:8080/mcp/w/...") as client:
    # One-call setup: create public context + set resource_id + create token
    token = await client.setup_resource(resource_id="products", summary="Product catalog")
    print(f"Save this token: {token.token}")  # Shown only once!

    event = ResourceEventRequest(
        op="upsert", doc_id="SKU-001", version=1,
        payload={"name": "Wireless Headphones", "price": 79.99},
    )
    await client.ingest_event("products", token.token, event)

    # Check ingestion stats
    stats = await client.get_resource_impact("products")
    print(f"Memories: {stats.memory_count}, Tokens: {stats.token_count}")

See examples/ for complete working examples.

CLI

# AI-powered (requires LLM API key)
kagura process -m "Remember: FastAPI uses Depends() for DI"

# Direct memory operations
kagura remember -s "FastAPI DI" --content "Use Depends()..." -c dev
kagura recall "dependency injection" -k 10
kagura explore -m "memory-uuid" --depth 3
kagura forget -m "memory-uuid"
kagura contexts

# Resource tokens
kagura resource tokens create -r products -d "Product sync"
kagura resource ingest -r products -k TOKEN --doc-id SKU-001 -V 1 -p '{"name":"Widget"}'
kagura resource ingest-batch -r products -k TOKEN -f events.json
kagura resource stats -r products
kagura resource schema -r products

# Config
kagura config show

Claude Code Integration

Use Kagura Memory as an MCP server in Claude Code:

cp .mcp.json.example .mcp.json
# Edit .mcp.json — set workspace_id and API key

Or use the CLI directly:

kagura process -m "今日の学び：FastAPIのDIはDepends()を使う"

API Coverage

Operation	SDK Client	Protocol	Auth
Memory (remember/recall/forget/explore/reference)	KaguraClient	MCP	API Key
Context (create/update/list/get)	KaguraClient	MCP	API Key
Context delete	—	Web UI only	Session
Resource Token (create/list/update/revoke)	ResourceClient	REST API	API Key
Resource Event ingestion	ResourceClient	REST API	Resource Token
Resource Impact (stats)	ResourceClient	REST API	API Key
Resource Schema	ResourceClient	REST API	API Key

Context deletion is intentionally Web UI only — destructive operations require session authentication and confirmation.

Development

git clone https://github.com/kagura-ai/kagura-memory-python-sdk.git
cd kagura-memory-python-sdk
uv sync --dev

uv run ruff check src/ tests/   # Lint
uv run ruff format src/ tests/  # Format
uv run pyright src/              # Type check
uv run pytest tests/ -v          # Test

Development with Claude Code

This project is developed with Claude Code:

/onboarding      # Interactive setup — verify config, test connection
/workflow        # Check current state and next step
/quality         # Run all quality checks
/simplify        # Review for reuse, quality, efficiency
/self-review     # Pre-PR self-review
/self-maint      # Audit .claude/ config against codebase
/release <level> # Bump version, tag, push, create GitHub Release
/kagura-guide    # SDK usage reference

Typical flow: Issue → Branch → Implement → /quality → /simplify → /self-review → PR → Merge → /release

Links

• Kagura Memory Cloud — the server this SDK connects to
• Releases — changelogs
• Issues — bug reports & feature requests

License

MIT License — see LICENSE for details.