AI Agent framework for data operations.
daita-agents — A Python framework for building autonomous AI agents that scale with your data. Multi provider LLM support, a rich plugin ecosystem, persistent memory, multi-agent workflows, and zero-config tracing, all with a minimal API.
from daita import Agent, tool
@tool
def query_database(sql: str) -> list:
"""Run a SQL query and return results."""
...
agent = Agent(name="Analyst", llm_provider="openai", model="gpt-4o", tools=[query_database])
result = await agent.run("What were our top 5 products by revenue last quarter?")pip install daita-agents- Any LLM — OpenAI, Anthropic, Gemini, Grok, or bring your own
- Plugin ecosystem — PostgreSQL, MySQL, MongoDB, Snowflake, S3, Slack, Elasticsearch, Neo4j, Chroma, Pinecone, Qdrant, and more
- Persistent memory — agents remember context across sessions
- Multi-agent workflows — connect agents into pipelines via typed relay channels
- Automatic tracing — tokens, latency, and cost tracked on every call
- MCP support — plug in any Model Context Protocol server
| Docs | docs.daita-tech.io |
| PyPI | pip install daita-agents |
| Issues | github.com/Daita-Corp/daita-agents/issues |
| Contact | [email protected] |
Apache 2.0 licensed. Built for developers who want agents that work in production, not just demos.