NucleusIQ Documentation
Build AI agents as durable software systems, not one-off demos.
What We Are Building
NucleusIQ is an open-source, agent-first Python framework for teams that want to ship agents into real products.
The core idea is simple: agents should be engineered like serious software systems:
- maintainable by teams over time
- testable and observable in production
- provider-portable as the ecosystem changes
- structured for tools, memory, policy, and validation
An agent is not just one model call. It is a managed runtime with responsibilities.
Why NucleusIQ Exists
Modern models can produce impressive demos quickly.
The hard part is owning those systems for months and years.
NucleusIQ is designed to close that gap between:
- what AI can generate fast, and
- what engineering teams can safely maintain long term.
This means less fragile glue code, less accidental complexity, and clearer architecture as systems grow.
Our Philosophy
NucleusIQ follows a practical philosophy for dependable agent engineering:
1) Agent-first thinking
Design around the full agent lifecycle (execution, tools, memory, policy), not isolated model calls.
2) Harness over hype
Reliability comes from good scaffolding: boundaries, artifacts, visibility, and feedback loops.
3) Progressive complexity
Start simple, add orchestration only when the task justifies it.
4) Open integration, closed coupling
Integrate broadly with providers and tools, but keep the core architecture stable and portable.
5) Reliability is a feature
Validation, structured output, policy controls, and observability are first-class parts of the framework.
Build Path
Choose your path based on where you are today:
- Start: Installation and Quickstart
- Understand: Overview and Core Concepts
- Scale: Execution Modes, Tools, Memory, Plugins
- Ship: Production Architecture, Structured Output, Observability
What's new in v0.7.x
v0.7.7 (latest)
Context Management v2 + execution fixes
- Stable V2 pipeline — compaction, masking, recall/rehydration tuned for PDF-heavy agents (
squeeze_threshold=0.70default). - Optional
@tool(idempotent=True)— safe dedup for pure tools; default remains non-idempotent. AgentResult+ tool caps — clearerstatus=errorandToolCallLimitErrorwhen limits bite; tools-free synthesis when the tool cap is hit (synthesis on).- Providers:
nucleusiq-openai0.6.3,nucleusiq-gemini0.2.5 — aligned with core 0.7.7.
v0.7.6
Context Window Management
Automatic context management for tool-heavy agents — prevents context overflow and ensures the LLM always has room to respond.
from nucleusiq.agents.context import ContextConfig, ContextStrategy
config = AgentConfig(
context=ContextConfig(strategy=ContextStrategy.PROGRESSIVE),
)
Breaking: Prompt System Refactor
prompt is now mandatory on Agent. The narrative field has been removed. role and objective are labels only — they are not sent to the LLM.
from nucleusiq.prompts.zero_shot import ZeroShotPrompt
agent = Agent(
name="analyst",
prompt=ZeroShotPrompt().configure(
system="You are a data analyst. Provide detailed analysis.",
),
llm=llm,
)
Synthesis Pass + ObservabilityConfig
- Synthesis pass — after multi-round tool loops, the agent makes one final LLM call without tools to produce the full deliverable
- ObservabilityConfig — unified config replacing
verbose+enable_tracing - Context telemetry — peak utilization, compaction events, token savings in
AgentResult
v0.7.5
- Gemini native + custom tool mixing — transparent proxy pattern, zero code changes
- Full observability wiring — PluginEvent, MemorySnapshot, AutonomousDetail in AgentResult
v0.7.4
- ExecutionTracer — full LLM/tool call observability
- Pyrefly static type checking — 121 type errors fixed, CI-gated
- Exhaustive error wiring — typed exceptions everywhere
v0.7.2-0.7.3
- Unified exception hierarchy — 10 error families
- AgentResult response contract — typed, immutable Pydantic model
- Gemini tool-calling fixes —
$ref/$defsinlining
Current packages: nucleusiq 0.7.7, nucleusiq-openai 0.6.3, nucleusiq-gemini 0.2.5
See the full changelog.