# jieyefriic/rp-engine

YAML-native agent workflow execution engine, written in Rust

Repository: https://github.com/jieyefriic/rp-engine
Canonical: https://ross.abutalabs.com/products/rp-engine
Homepage: https://crates.io/crates/riceprompt-engine
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: agent, llm, mcp, rust, workflow, yaml
Last push: 2026-04-28T09:18:48+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 35, longevity 16
- inputs: {"age_days": 226, "days_push": 127, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1221, forks 9 (observed 2026-08-28T04:04:02.151437+00:00)

## What it is
A YAML-native agent workflow execution engine written in Rust that parses declarative workflow files describing nodes, edges, prompts, data sources, and MCP tools, then executes the graph with LLM calls, scripting, database queries, and multi-agent orchestration. It powers the RicePrompt visual agent IDE and supports many LLM providers, streaming, tool calling, and checkpoint/resume.

## Use cases
- define and run multi-step LLM agent workflows from a single YAML file
- orchestrate multi-agent plans with supervisor routing and subgraphs
- call MCP tools and query databases inside agent pipelines
- build RAG-style workflows with vector and object storage connectors
- run long-running agent workflows with pause, checkpoint, and resume
- embed a declarative agent workflow engine in a Rust application

## When to choose
- you want workflows defined declaratively in YAML rather than code
- you need multi-provider LLM support including OpenAI-compatible endpoints
- you need MCP tool integration and rich node types like iterators and supervisors
- you are building in Rust and want a library you can embed

## When to avoid
- you need a visual drag-and-drop builder without touching YAML
- your workflows are simple single LLM calls with no orchestration
- you need a Python or JavaScript-first agent framework ecosystem

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, workflow-automation, llm-inference, mcp, rag, prompt-engineering, chatbot, yaml
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: rust, cross-platform, cli
- tags: yaml-workflows, multi-agent-orchestration, dag-execution, multi-provider-llm, checkpoint-resume, rhai-scripting, data-connectors, ai-agents, automation

## Member repositories
- jieyefriic/rp-engine (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.151437+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:41.493686+00:00, confidence not recorded.
  - readme: https://github.com/jieyefriic/rp-engine (fetched 2026-08-28T04:04:02.151437+00:00, sha ae6e41883ee3)
- Data as of 2026-08-30T08:39:29.467469+00:00.