dakera 0.11.53

Python SDK for Dakera - AI memory platform

⚡ dakera-py

Python SDK for Dakera AI — store, recall, and search agent memories against a Dakera instance.

Part of Dakera AI — the memory engine for AI agents.

The Dakera memory engine scores 87.8% on LoCoMo (1,540 questions, standard eval) — benchmark details

---

Install

pip install dakera

Quick Start

from dakera import DakeraClient

client = DakeraClient(base_url="http://localhost:3300", api_key="your-key")

# Store a vector
client.vectors.upsert(
    id="vec-001",
    values=[0.1, 0.2, 0.3],
    metadata={"text": "agent completed task", "agent_id": "my-agent"}
)

# Full-text search
results = client.fulltext.search(query="completed task", top_k=5)
for r in results:
    print(r.id, r.score)

# Store an agent memory
client.memories.store(
    agent_id="my-agent",
    content="User prefers concise responses",
    importance=0.8,
    tags=["preference", "ux"]
)

Connect to Dakera

from dakera import DakeraClient

# Self-hosted
client = DakeraClient(base_url="http://your-server:3300", api_key="your-key")

# Cloud (early access)
client = DakeraClient(base_url="https://api.dakera.ai", api_key="your-key")

Documentation

→ Full docs
→ API reference
→ Python SDK reference

Related

Repo	What it is
dakera-js	TypeScript SDK
dakera-go	Go SDK
dakera-rs	Rust client
dakera-cli	CLI
dakera-mcp	MCP server · 83 tools
dakera-deploy	Self-host Dakera

---

Part of the Dakera AI open core. The engine is proprietary. The tools are yours.