Toolbox/Frameworks & SDKs

Workflow & graph engines

graph, DAG and state-machine runtimes for agent workflows

13 repositories, most starred first
State of the category

langchain-ai/langgraph LangGraph (langchain-ai/langgraph) is the clear leader for open-source agent workflow engines; if you need durable, stateful, long‑running agent orchestration with human‑in‑the‑loop support and a large ecosystem, start there. Choose alternatives only when you have specific requirements around self‑hosting, vertical integrations, strict auditability, or specialized performance tradeoffs.

Self‑hosting & ops
Many teams require on‑prem, compliant, or ops-friendly platforms (including plugin ecosystems and local LLM support) that a cloud‑first, general-purpose leader may not prioritize.
Verification & auditability
Organizations building high‑risk or multi‑actor flows need explicit evidence, approval gates, and resumable ledgers so outputs can be reverified and attributed reliably.
Verticalized workflows
Domain teams (video, finance, science, news) prefer tooling that bundles domain‑specific connectors, DAGs and UI integrations so they can move faster than by customizing a general engine.
Performance & cost optimization
Teams running large-scale tool use want automatic parallelization and call‑planning to reduce latency and API costs compared with naive sequential patterns.
Reusable loops & discovery
Builders want curated, reusable agent loops and a publishing/discovery flow so teams can share audited patterns rather than reinvent orchestration from scratch.
Find your fit

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.

Where should reviews happen?
Can code leave your infrastructure?
What matters most?
Model access?
Pick at least one answer to get a shortlist.
Side by side

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 inModelsContextCost to run
41.0k +429/7d
CLIFixed providerDiff onlyNone mentionedThird-party cloudFree, open-source
28.0k +42/7d
Web appCIFixed providerFlow-level onlyReal-time validationSelf-hostableFree, self-hosted
3.2k +114/7d
CLIFixed providerWhole-repo analysisSeverity gatingSelf-hostableFree, self-hosted
8.9k
Web appBYOKFixed providerDiff onlyNo explicit controlsSelf-hostableSelf-hosted (free) with optional Astron Cloud
3.1k +27/7d
Coding-agent pluginCLIOpenAIAnthropicWhole-repo analysisAcceptance gatingDepends on cloud agentsRequires cloud agent provider (may incur provider cost)
3.0k +356/7d
CLICoding-agent pluginCIOpenAIAnthropicDiff + related filesApproval & strict checksSelf-hostableFree to run locally; external agent API costs may apply
1.8k +76/7d
CLIOpenAIAnthropicGeminiFixed providerDiff onlySelf-evaluation loopsCloud APIs (your key)Your API keys for cloud LLMs (Claude/GPT/Gemini); optional local model downloads
1.4k +113/7d
CLICoding-agent pluginWeb appBYOKDiff + related filesEvidence gatesSelf-hostableYour API key, per-use
195 +2/7d
CLIIDEWeb appBYOKOpenAIAnthropicGeminiOllama / localWorkspace-levelHuman review gatingSelf-hostableFree to run locally or via the hosted web app; external model API usage or hosted services may incur provider costs.
1.9k
CLIBYOKOpenAIFixed providerDiff + related filesNone notedSelf-hostableYour API key / provider billing
639
CLIBYOKRelated filesStructured outputYour API keyYour API key (OpenAI-compatible endpoint)
619 +2/7d
CLIBYOKOpenAIAnthropicGeminiOllama / localConfig & strategiesConfidence & risk filtersSelf-hostable (local LLMs)Your API keys (OpenAI/Anthropic/Groq/Ollama etc.), pay-per-use cloud fees as applicable
Ranked by maturity — 1 more in the full catalog below.
At a glance

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.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

Orchestrates and verifies multi-step work by discovering and assigning local Skill modules and enforcing end-to-end checks with resumable state.

ContextNoiseCustomPrivacyModelsMaturity

Enterprise-grade agentic workflow platform with built-in RPA and high-availability focus for production deployments, unlike many prototyping-focused workflow engines.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

Implements the Depth Tree decomposition with a strict, evidence-backed runnable gate ledger that enforces approvals and re-verification for substantial agent tasks.

ContextNoiseCustomPrivacyModelsMaturity

Graph-powered, agentic workflows for end-to-end multimodal video understanding, editing and remaking with iterative self-evaluation.

ContextNoiseCustomPrivacyModelsMaturity

Provides a local-first operating layer for Hermes that enforces explicit evidence boundaries and verification gates while keeping executors and provider access observable.

All repositories (13)

Build resilient agents.

41.0k
+4297d
Python
3 yrs

Event Driven Orchestration & Scheduling Platform for Mission Critical Applications

28.0k
+427d
Java
7 yrs

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

8.9k
-47d
Java
11 mo

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on Skills…

3.2k
+1147d
Python
6 mo

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable…

3.1k
+277d
JavaScript
2 mo

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives ev…

3.0k
+3567d
JavaScript
3 wk

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

1.9k
-17d
Python
2 yrs

[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"

1.8k
+767d
Python
1 yr

Just install once. The coding intelligence, a long-term memory system, optimized workflow packages, only plugi…

1.4k
+1137d
Python
3 mo

An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI applicati…

639
Python
2 yrs

AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intel…

619
+27d
Python
1 yr

Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency g…

206
Kotlin
1 yr

AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language Ca…

195
+27d
TypeScript
4 mo
Don't want to self-host?

Hosted alternatives

If running your own reviewer is more ops than you want, these managed services cover the same job.

LangGraph Platform

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
Temporal Cloud

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
Kestra 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

More in Frameworks & SDKs