AgentSidekick

Stateful Workflow Graphs

Durable, graph-based agent execution. As of 2026-11-21, 38 indexed products offer it (26 with full profiles), in 8 forms: 18 MCP servers, 6 Infrastructure, 5 Agent skills, 5 Frameworks. 11 were published in the last 90 days, against 10 in the 90 days before. LangGraph has the most GitHub stars, 28% of the total across 33 products with their own repository.

CapabilitySegment label: Thin DERScored as an opportunity

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 18 indexed · 6 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Stateful Workflow Graphs: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1HonchoMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.plastic-labs8.2ktoday
2daguSelf-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.dagucloud4.6ktoday
3OmnaraDeploy durable AI agents with Omnara, an open-source managed-agent platform.omnara.com3.4ktoday
4HyphaHarness-oriented agent system framework for production-grade LLM agent applicationsCodeSoul-co4526d ago
5DruksRun, approve and inspect durable agent runs on your Druks Cloud instance.druks.ai23today
6MELRALocal MCP runtime for policy-governed, verified agent actions with durable receipts.XAGI-Lab133d ago

Infrastructure 6 indexed · 6 profiled

No compatibility evidence is collected for this form.

Stateful Workflow Graphs: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1TemporalDurable execution platform that persists workflow state so long-running code, including agent loops, survives crashes and retries automatically.Temporal Technologies25ktoday
2RestateDurable execution runtime that journals handler steps so services, workflows and agents recover from failures.Restate4.7ktoday
3letta-codeAgents that self-improve with experienceletta-ai3.9ktoday
4burrBuild applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.apache2.6ktoday
5ai-runtime-labEngineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.Ali-hey-01834mo ago
6evestackThe whole eve stack. On your own machine. Durable Postgres sessions, a Docker sandbox, memory, approvals, schedules, 1,070 tool integrations, and a dashboard that drives the agent.SammyTourani181d ago

Agent skills 5 indexed · 5 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Stateful Workflow Graphs: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1longgraph-skillLong-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.levi-qiao791mo ago
2dag-libraryStores a DAG definition once and re-runs it by name, instead of pasting the definition into every run. Use when the user wants to save a DAG, run a saved one, or schedule the same multi-agent graph repeatedly.code-yeongyu—today
3temporal-python-testingTest Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.wshobson—3d ago
4baoyu-diagramCreate professional diagrams with configurable dark/light theme via CSS custom properties. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Outputs a dark-theme SVG, a light-theme SVG, and a @2x PNG of each.JimLiu—1d ago
5hunt-race-conditionHunting skill for race condition vulnerabilities. Built from 12 public bug bounty reports including modern HTTP/2 single-packet attack cases (James Kettle DEF CON 2023 "Smashing the State Machine"; RyotaK / Flatt Security 10,000-request first-sequence-sync expansion 2024). Covers coupon double-redemption, gift-card double-spend, MFA-OTP-validate race, account-create race, faucet/crypto token double-mint, email-activation race, vote/upvote inflation, password-reset token race, rate-limit bypass via concurrent requests. Use when hunting race conditions, TOCTOU bugs, MFA-bypass-via-timing.elementalsouls—today

Frameworks 5 indexed · 5 profiled

No compatibility evidence is collected for this form.

Stateful Workflow Graphs: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution.LangChain45ktoday
2LettaPlatform for stateful agents with self-editing memory blocks, archival memory and a server that persists agents; originated as MemGPT.Letta26k1mo ago
3chidoriThe agent framework where every run is durable, replayable, and resumable by default.ThousandBirdsInc1.4k5d ago
4Deuz-SDKTypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.Deuz-AI5081mo ago
5prodagentA minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核,理解 LangGraph/ADK 底层的工作原理limenagent1501mo ago

Agent projects 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Stateful Workflow Graphs: Agent projects by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1daprDapr is a portable runtime for building distributed applications across cloud and edge, combining event-driven architecture with workflow orchestration.dapr26k2d ago

Libraries 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Stateful Workflow Graphs: Libraries by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1DBOSLibrary for durable workflows that checkpoints steps in Postgres, adding crash recovery to Python and TypeScript apps without a separate server.DBOS1.7ktoday

Plugins 1 indexed · 1 profiled

1 of these are Claude plugins, which Claude Code documents (protocol-level). DER

Stateful Workflow Graphs: Plugins by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1ArcgenticMechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.Arch1eSUN2851mo ago

Agent SDKs 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Stateful Workflow Graphs: Agent SDKs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Cloudflare Agents SDKTypeScript SDK for stateful agents running on Durable Objects, with built-in state sync, scheduling, WebSockets and helpers for hosting remote MCP servers.cloudflare6.0k1d ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code2
Codex2
OpenClaw1
Cursor1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
PostgreSQL25.3%
Android12.6%
GitHub12.6%
Slack12.6%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
langgraph0
agent graph2
state machine12
durable execution19
stateful agents4
temporal workflow1

Segment statistics

Whole catalogue (38 indexed products). Calculated 2026-11-21.

38DERIndexed products26 with full profiles
11DERLaunched, last 90 days10 in the 90 days before
11DERMomentum vs catalogue50 = same pace as the catalogue
28%DERLargest project's share of starsAcross 33 products with their own repository
0.163DERConcentration (HHI)About 6 equal-sized projects’ worth; moderately concentrated
183SRCMedian starsPer product with its own repository
82%DEROpen sourceMarked open source; unknown counts as not

Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.163 means stars are spread as if across about 6 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: Stateful Workflow Graphs: score 58.4 HEU, competition High, confidence Low. Only 38 indexed products match "Stateful Workflow Graphs", against 671 in Agent Orchestration overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .