smythe 0.8.0

Turn a goal into an inspectable agent workflow. Run it with budgets and recovery.

Quickstart · How it works · Measured results · Documentation

Smythe is a Python framework that plans and runs agent workflows. Give it a goal, inspect the generated task graph, and execute independent work in parallel. Set spending and concurrency limits, verify outputs, and recover saved work after an interruption.

Use it for research pipelines, document production, and artifact generation where you need to see what will run and account for what happened.

Quickstart

Python 3.11+. Install the released library with OpenAI support:

pip install "smythe[openai]==0.8.0"

Set OPENAI_API_KEY, then plan and execute with GPT-6 Astra:

from smythe import OpenAIResponsesProvider, SQLiteWorkflowStore, Swarm, Task

with SQLiteWorkflowStore("smythe-runs.db") as store:
    swarm = Swarm(
        model="gpt-6-astra",
        provider=OpenAIResponsesProvider(
            reasoning_effort="medium",
            max_output_tokens=8192,
        ),
        run_store=store,
        max_budget_usd=5.00,
        parallel=True,
        max_concurrency=8,
    )
    graph = swarm.plan(Task(
        goal="Compare SQLite, PostgreSQL, and DuckDB for a local analytics app.",
        constraints=["Stay under 400 words", "Recommend one database"],
    ))
    print(graph)
    result = swarm.execute(graph)
    print(result.output)

This makes paid API calls under a $5 run allowance. The SQLite ledger accounts for planning and execution, reserves requests before dispatch, and retains responses for recovery. See budget scope and durable text workflows.

To try planning, execution, and recovery with no API calls, run the explicit offline example from a source checkout:

git clone https://github.com/petehottelet/smythe.git
cd smythe
pip install -e .
python examples/14_durable_text_workflow.py

The example uses fixture responses and verifies that resuming produces the same output. More examples.

How it works

The graph defines the work. Smythe generates a directed acyclic graph for the task, including dependencies and agent assignments. Inspect or export it before execution. Use approved templates or a graph you write yourself when the workflow is already known.

The execution envelope governs the run. Budgets, bounded concurrency, verification, traces, artifacts, and recovery apply as the graph executes. Durable Jobs add manifest approval, attempt history, selective rerolls, and local HTML reports.

The acquisition-diligence example shows three specialists feeding an editor, a red-team review, and a final decision memo. Its saved graph, trace, and expected output make the workflow inspectable.

Architecture · Execution · Jobs · Verification · MCP tools.

Measured results

Each result links to its method and retained records.

The 200-workflow Astra/Sol study also reports the limits of generated plans: they increased mean time in both models on its ten synthetic tasks. The frozen rule accepted 191/200 workflows; human review accepted all eight disputed available answers. One missing usage receipt limits affected exact cost comparisons. All outcomes remain published.

All benchmarks, charts, and evidence status.

Project status

Smythe 0.8.0 is the current library release. See the release notes and upgrade guide. The API is pre-1.0; minor releases may change it. Later source changes appear in the changelog.

Next priorities are complete-deliverable checks, broader external-task benchmarks, and separately controlled Astra scheduler and framework studies. See the roadmap for status and acceptance criteria.

The Glyph Rain screensaver is an artifact-generation showcase with source builds and a web explorer. Precompiled screensaver distribution is paused.

Documentation · Contributing · Releases · Security · MIT license.