uc-llm-agent-tools 0.1.0

Lightweight LLM agent library — memory layers, skills, context engineering

uc-llm-agent-tools

Lightweight LLM agent library — memory layers, skills, context engineering.

Built on uc-llm-provider. Works with any LLM: Anthropic, OpenAI, Google, Ollama.

Install

pip install uc-llm-agent-tools

Quick Start

from uc_llm_agent_tools import Agent, Identity, MemoryStore, MemoryLayer
from uc_llm_agent_tools.memory.backends.sqlite import SQLiteBackend
from uc_llm_agent_tools.skills import skill, SkillResult
from uc_llm_provider import get_provider

# Skills definieren
@skill(name="fetch_page", description="Fetch and analyze a web page", tags=["browser"])
async def fetch_page(url: str) -> SkillResult:
    return SkillResult(success=True, content=f"Page at {url} analyzed", data={})

# Agent aufsetzen
agent = Agent(
    identity=Identity.from_file("my-agent-identity.md"),
    memory=MemoryStore(
        backend=SQLiteBackend("agent.sqlite3"),
        layers=[
            MemoryLayer("project", level=2, persist=True),
            MemoryLayer("run",     level=3, persist=False),
        ]
    ),
    skills=[fetch_page],
    provider=get_provider({"name": "anthropic", "provider_type": "anthropic"}),
)

result = await agent.run("Analyze https://example.com for accessibility issues")

Memory Hierarchy

Level 0: Directives    — always loaded, never overridden
Level 1: Personality   — always loaded, grows over time
Level N: custom named  — filtered by budget and relevance

High beats low. Low complements high.

PyPI

uc-llm-agent-tools