agentmaker logo

agentmaker

MIT Python agent framework with memory, hybrid retrieval, RAG, MCP, and governance in one import.

Open source

agentmaker is an open-source Python framework (pip package 0.2.0, Python 3.12+) that ships a unified agent loop for chat, ReAct, plan-and-solve, and reflection, plus built-in hybrid retrieval, Mem0-style long-term memory, RAG, MCP tool loading, guardrails, human-in-the-loop approve/resume, run limits, and tracing to JSONL, SQLite, or OpenTelemetry—with local SQLite defaults and swappable backends.

Selection advice

Choose agentmaker when you want one MIT Python package that already covers agent recipes, hybrid retrieval, memory, RAG, MCP, and governance with local defaults. Prefer Pydantic AI when schema-validated structured output is the main requirement, or Agno when you want a lightweight SDK with a hosted AgentOS path.

Quick comparison

agentmaker packages agent loops, retrieval, memory, RAG, and governance in one MIT core. Pydantic AI emphasizes typed structured outputs, while Agno focuses on a lightweight path from SDK toward hosted AgentOS.

agentmakerPydantic AIAgno
Best forPython teams wanting agents, memory, and hybrid retrieval without stitching many packagesSchema-validated tools and structured outputs on Pydantic modelsLightweight agent SDK with a clear hosted AgentOS path
Batteries includedHybrid retrieval, memory, RAG, MCP extras, guardrails, HITL, tracingType-safe agents; long-term memory and vector stores are mostly bring-your-ownAgent SDK plus optional cloud runtime; memory/knowledge via framework features
TradeoffYounger project (created 2026-07-08) with a smaller ecosystem than LangGraph-class stacksLean typing core vs fewer built-in retrieval/memory servicesBroader production footprint vs less of a single-import full stack

Best for

  • single-import Python agent stacks
  • local-first hybrid retrieval and memory
  • MCP tool integration with guardrails and HITL
  • teams that want swappable SQLite-default backends

Not ideal for

  • TypeScript-first teams
  • teams that need a large battle-tested graph orchestration ecosystem
  • products that only need a thin typed agent wrapper without retrieval or memory

Core concepts

unified agent loophybrid retrieval (vector + keyword + RRF)Mem0-style memory writesguardrails and HITLTrace Detective

Minimal implementation shape

pip install agentmaker, create `Agent("assistant", LLMClient("deepseek"))`, call `agent.run(...)` for multi-turn chat with memory, then add tools, MCP, or RAG extras as needed.

Sources