Workflow & graph engines
graph, DAG and state-machine runtimes for agent workflows
langchain-ai/langgraph LangGraph is the category leader. If you need durable, long‑running, stateful agent orchestration with built‑in human‑in‑the‑loop support and durable execution, start there; otherwise choose a project that targets a specific gap like declarative enterprise workflows, verification/audit gates, local-first privacy, domain-specific tooling, or orchestration optimizations.
Which one matches your setup?
Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.
Comparison matrix
Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.
| Runs in | Models | Context | Cost to run | |||||
|---|---|---|---|---|---|---|---|---|
⭐ 43.6k +382/7d | CLI | Fixed provider | Diff only | None mentioned | ●●●●● | Third-party cloud | ●●●●● | Free, open-source |
⭐ 29.9k +372/7d | Web appCI | Fixed provider | Flow-level only | Real-time validation | ●●●●● | Self-hostable | ●●●●● | Free, self-hosted |
⭐ 24.2k +2390/7d | CLICoding-agent plugin | OpenAIAnthropicFixed provider | Project directory | None mentioned | ●●●●● | Fully local option | ●●●●● | Open-source; can run locally for free, external model API costs may apply. |
⭐ 3.7k +56/7d | CLI | Fixed provider | Whole-repo analysis | Severity gating | ●●●●● | Self-hostable | ●●●●● | Free, self-hosted |
⭐ 3.4k +91/7d | CLICoding-agent pluginWeb app | BYOK | Diff + related files | Evidence gates | ●●●●● | Self-hostable | ●●●●● | Your API key, per-use |
⭐ 4.0k +94/7d | CLICoding-agent pluginCI | OpenAIAnthropic | Diff + related files | Approval & strict checks | ●●●●● | Self-hostable | ●●●●● | Free to run locally; external agent API costs may apply |
⭐ 8.9k +25/7d | Web app | BYOKFixed provider | Diff only | No explicit controls | ●●●●● | Self-hostable | ●●●●● | Self-hosted (free) with optional Astron Cloud |
⭐ 3.2k +22/7d | Coding-agent pluginCLI | OpenAIAnthropic | Whole-repo analysis | Acceptance gating | ●●●●● | Depends on cloud agents | ●●●●● | Requires cloud agent provider (may incur provider cost) |
⭐ 2.0k +17/7d | CLI | OpenAIAnthropicGeminiFixed provider | Diff only | Self-evaluation loops | ●●●●● | Cloud APIs (your key) | ●●●●● | Your API keys for cloud LLMs (Claude/GPT/Gemini); optional local model downloads |
⭐ 209 +2/7d | CLICoding-agent pluginIDE | BYOK | Full workspace state | Gate checks | ●●●●● | Self-hostable / Local | ●●●●● | Free, self-hosted (Docker) |
⭐ 207 +2/7d | CLIIDEWeb app | BYOKOpenAIAnthropicGeminiOllama / local | Workspace-level | Human review gating | ●●●●● | Self-hostable | ●●●●● | Free to run locally or via the hosted web app; external model API usage or hosted services may incur provider costs. |
⭐ 88 +22/7d | CLIWeb app | AnthropicOpenAIGeminiFixed provider | Workspace-level | Tool boundary controls | ●●●●● | Local-only | ●●●●● | Free download; uses your agent CLIs / provider accounts |
Capability profiles
Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.
Provides low-level orchestration for long-running, stateful agents with durable execution and human-in-the-loop capabilities that typical stateless workflow engines do not emphasize.
An event-driven, open-source orchestration platform that combines a declarative YAML workflow model with a rich plugin ecosystem and a visual editor for building and running workflows across environments.
An end-to-end, agent-driven video workflow DSL that clones a reference video into editable, re-runnable compositions and ships mass variants (e.g., 100 variants) rather than producing single one-off renders.
Orchestrates and verifies multi-step work by discovering and assigning local Skill modules and enforcing end-to-end checks with resumable state.
Provides a local-first operating layer for Hermes that enforces explicit evidence boundaries and verification gates while keeping executors and provider access observable.
Implements the Depth Tree decomposition with a strict, evidence-backed runnable gate ledger that enforces approvals and re-verification for substantial agent tasks.
Enterprise-grade agentic workflow platform with built-in RPA and high-availability focus for production deployments, unlike many prototyping-focused workflow engines.
Combines a public, curated catalog of reusable agent loops with an installable in-agent skill that discovers, crafts, audits, runs, and prepares loops for publication.
All repositories (15)
Event Driven Orchestration & Scheduling Platform for Mission Critical Applications
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-r…
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives ev…
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on Skills…
All in one plugin for Hermes Agent ⚚ the coding intelligence, a long-term memory system and model optimized wo…
A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable…
[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI applicati…
AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intel…
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency g…
AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language Ca…
Bring Claude Code, Codex, and your favorite CLI agents together to delegate tasks and share results. Let AI bu…
Hosted alternatives
If running your own reviewer is more ops than you want, these managed services cover the same job.
LangChain's hosting for LangGraph workflows: the graph runs for you with persistence, streaming and a debugging studio, so you ship the orchestration code without a server and state store.
Try LangGraph Platform →Managed durable execution for long-running, crash-safe workflows: the same retries and state you would run on Temporal, hosted rather than operated by you.
Try Temporal Cloud →The hosted side of Kestra's event-driven orchestration: declarative workflows with scheduling and a visual editor, run for you instead of a self-hosted deployment.
Try Kestra Cloud →