> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pflow.run/llms.txt
> Use this file to discover all available pages before exploring further.

# Roadmap

> pflow's direction and priorities

## <Icon icon="circuit-board" size={24} color="#f97316" /> Current status

Where pflow is today (v0.12.0):

* **Standalone orchestration engine** with compile-once batch optimization (\~7x speedup for large parallel workflows)
* **Markdown workflows** — `.pflow.md` files that agents read and write naturally
* **Node system** — file, llm, http, shell, code (Python), claude-code, and MCP bridge
* **Conditional branching** — `on-error`, static routing, and data-driven routing via code nodes with branch convergence (`??` coalesce operator)
* **Nested workflows** — saved or file-based workflows as nodes inside other workflows, with automatic input/output mapping
* **Memoization cache** — unchanged nodes serve cached results across re-runs, with `--only`, `--no-cache`, and per-node `cache: false` controls
* **Execution reports** — `--report` generates navigable markdown directories with rendered prompts, responses, token breakdowns, and cost data per node
* **Dry-run execution plans** — `--dry-run` previews cost, duration, and cache boundaries before execution
* **Workflow visualization** — `pflow visualize` generates Mermaid flowcharts of workflow topology
* **Batch processing** — process arrays through nodes, sequential or parallel, with per-item parameter overrides and error handling modes
* **External file references** — `prompt: ./prompts/system.md` keeps long content out of workflow files
* **Workflow bundling** — `pflow save` packages workflows with all file dependencies as self-contained folders
* **Unified diagnostics** — one error format across CLI text and JSON output, with structured suggestions and source file provenance
* **Recursive sub-workflow validation** — structural errors caught before any node executes
* **Template variables** — `${var}` syntax with nested path access, automatic JSON parsing, and structured output schemas
* **AI agent integration** via CLI and MCP server
* **Discovery** — find nodes and workflows by describing what you need
* **Unix-first piping** — stdin/stdout, works with any Unix tool
* **Skills publishing** — save workflows as Claude Code skills, cross-platform
* **Settings management** — API keys, node filtering
* **Unified model support** — 100+ providers (OpenAI, Anthropic, Google, OpenRouter, Ollama, ...) via LiteLLM
* **Published on PyPI** — `uv tool install pflow-cli`

## <Icon icon="hammer" size={24} color="#f97316" /> Now

**Human-in-the-loop approval gates** — pause workflow execution for human review before continuing. Workflows that create PRs, send messages, or modify infrastructure need a trust gate. Without this, workflows that take real-world actions aren't trustworthy enough to run unattended.

## <Icon icon="lightbulb" size={24} color="#f97316" /> Next

**Iteration speed and workflow quality**

* **Function-based code node syntax** — write Python functions instead of top-level scripts, with automatic input/output wiring from type annotations
* **Workflow export** — export a workflow to standalone Python with zero pflow dependency. Build and iterate with structure, ship plain code.
* **Workflow testing** — mock nodes, assert outputs, `pflow test`. Modify a saved workflow and know it still works before re-publishing.
* **Code and shell linting** — catch syntax errors in code blocks during validation, not at runtime
* **Batch limits** — cap iteration count for development and cost control

## <Icon icon="layers" size={24} color="#f97316" /> Later

**Security and sandboxing**

* **Sandboxed execution runtime** — isolated execution for shell and code nodes. Needed before running agent-generated workflows you haven't reviewed.
* **Export as MCP server packages** — distribute workflows as standalone MCP servers that work without pflow installed

**MCP ecosystem**

* **MCP gateway integration** — route to remote MCP servers
* **Dynamic MCP discovery** — search and install MCP servers on demand instead of manual configuration
* **OAuth for remote MCP servers** — authenticate with HTTP-based MCP servers

## <Icon icon="orbit" size={24} color="#f97316" /> Vision

pflow is infrastructure, not a destination. It provides building blocks and a runtime — agents do the assembly. The better the building blocks get, the more capable the agents become.

The longer-term direction:

* **Code node dependency management** — install packages on demand for code nodes
* **TypeScript code node** — for teams that think in TypeScript
* **Reduce/fold for batch** — aggregate batch results incrementally instead of collecting all at once
* **Windows compatibility** — run on Windows without WSL

pflow improves through a direct loop: agents build workflows, we find where they struggle, we fix it. Because the surface area is finite — node types, template syntax, error messages — each fix is targeted and compounds. A year from now pflow will be meaningfully better at helping agents build workflows, not because of some grand vision but because each friction point gets filed down one at a time.

## Get involved

<CardGroup cols={3}>
  <Card title="Discussions" icon="github" href="https://github.com/spinje/pflow/discussions">
    Ideas and feature requests
  </Card>

  <Card title="Issues" icon="github" href="https://github.com/spinje/pflow/issues">
    Bug reports
  </Card>

  <Card title="Documentation" icon="book-open" href="/">
    Guides and reference
  </Card>
</CardGroup>

***

<p style={{textAlign: 'center', color: '#888'}}>
  <Icon icon="heart" size={18} color="#f97316" /> Built by a developer who got tired of watching agents re-think the same tasks.<br />
  Questions or ideas? Reach out — <a href="mailto:andreas@pflow.run">[andreas@pflow.run](mailto:andreas@pflow.run)</a>
</p>