Noeta

Agents that keep running. Noeta is a Python SDK for agents that survive crashes, wait days for a human, and scale from one script to a cluster — without changing the agent.

English · [简体中文](README.zh-CN.md) · Docs · Quickstart · Why Noeta

A working agent in a few lines

uv pip install noeta-sdk
export ANTHROPIC_API_KEY=sk-ant-...

from noeta.sdk import Options, query
from noeta.sdk.providers import AnthropicProvider

result = query(
    Options(system_prompt="You are a concise coding assistant."),
    goal="What files are in this directory, and what does each one do?",
    provider=AnthropicProvider(),
    model="claude-sonnet-5",
)
print(result.answer())

The agent explores the directory with its built-in file tools and answers. result also holds every model call, tool call and token count from the run.

Python 3.11+. The Glob and Grep tools need ripgrep on PATH (apt install ripgrep, brew install ripgrep).

What sets it apart

Survives crashes. Task state is rebuilt from an append-only event log, never held in memory. Kill a worker mid-task and another one carries on from the last step. The same log is a complete audit trail.

Waiting costs nothing. A task can pause for a human approval, a timer, a subtask or an outside event — for seconds or months. It uses no resources while it sleeps and is woken exactly once.

From a script to a cluster. query() in a script, Client.start_workers(n) inside a service, several hosts on one Postgres. The agent code is the same at every step, and there is no daemon or extra service to run.

Also: every capability is a plugin — file tools, web, memory, MCP, sandboxes and model adapters use the same public API yours does. Any model — Anthropic, any OpenAI-compatible gateway, or the OpenAI Responses API, one line to switch. Approval before action — risky tool calls pause for a human; guards can block a call before it runs.

How it compares

| | Noeta | Claude Agent SDK | LangGraph | Temporal | |---|---|---|---|---| | What it is | Durable agent runtime, as a library | Agent loop library for Claude | Graph-based agent framework | Durable workflow platform | | Control flow | The model decides each step | The model decides | A graph you define | Workflow code you write | | What is saved | Every event; state is derived from it | The conversation | Checkpoints of graph state | Workflow history | | Waiting for a human / timer | Built in, woken exactly once | Resume the conversation | Interrupt, then the caller resumes | Built in | | Scaling out | Worker pool; many hosts on Postgres | One process | Up to you, or the hosted platform | A Temporal cluster | | Models | Any, one line to switch | Claude | Any | — | | Extra service to run | None | None | None | Temporal server |

Pick Noeta when an agent runs unattended for a long time and you need to recover, audit and scale it. Full comparison, and when not to use it.

Benchmarks

Measured on public benchmarks — one run each, over a sample:

| Benchmark | Scope | Measured on | noeta-agent main (Claude Opus 4.8) | Field (full set) | |---|---|---|---|---| | Terminal-Bench 2.1 | 40-task stratified sample | noeta-sdk 0.6.28, 2026-09-19 | first pass 24/40; 33/40 best of 3 attempts | public board spans 58.7%–83.8% | | SWE-bench Verified | 15-instance subset | noeta-sdk 0.6.10, 2026-08-09 | 13/15 after re-running 4 setup timeouts (first pass 9/15) | not comparable to a subset |

An agent built only on the public SDK (noeta-agent), run on the official harness (harbor) and scored by each task's own verifier. Both rows are single runs over samples, not full leaderboard runs, and the higher figures count re-runs of tasks the first pass missed. Method and caveats.

Documentation

| | | |---|---| | Start | Quickstart · Tutorial: build an agent | | Guides | Models · Custom tools · MCP · Subagents · Plugins · Testing · Deploy | | Understand | How it works · [ADRs](docs/adr/) | | Look up | SDK reference · Options · Built-in tools |

Prefer code? [examples/](examples/) has runnable scripts for custom tools, MCP servers, permission gates, subagents and surviving kill -9, each with an offline test. [examples/reference-host/](examples/reference-host/) is a complete host built from the public API alone.

License

Apache 2.0 — see [LICENSE](LICENSE).

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: initxy
• Source: initxy/noeta
• License: Apache-2.0
• Homepage: https://initxy.github.io/noeta/

Install and usage instructions live in the source repository linked above.