Self-Hosted Workflow Builders
As of August 2026, AIDiveForge tracks 8 self-hosted workflow builders. The top three by verified-data score are Skillful, Wayflow, and Teable 3.0. Curated self-hosted workflow builders tracked by AIDiveForge. Listings are verified against each tool's live website and re-checked regularly.
Last updated July 24, 2026 · 8 tools
Ranked by AIDiveForge's verified-data score: data completeness, verification recency, community rating, and real visitor engagement. How we rank · No tool can pay for placement.
1. Skillful
The core mechanic is symlink-based installation: one source folder, linked into Claude Code, Codex, Cursor, Copilot, Gemini CLI, Junie, opencode, or any custom folder target you define. Edit the source and every linked install picks up the change. The docs describe broken-symlink detection and one-click repair, which matters when tools update their config paths and silently drop your workflows. There is no backend, no account, and no telemetry — the library is a folder on your disk, so git is your version control and your backup strategy. Public skill repositories on GitHub can open directly into Skillful's import dialog, which makes trialing shared libraries faster than copying URLs by hand.
FreeOpen SourceSelf-hostedVerified Jul 18, 2026
2. Wayflow
The vendor describes Wayflow as an embeddable visual workflow editor — canvas, node palette, config panel, run controls, and a runtime engine that executes the same graph in the browser during development and on your server in production. A single call, createWorkflowEditor(), mounts the full workspace. Built-in node types cover LLM calls, tool-calling, branching, map-over-list, and image generation, so AI and deterministic steps sit on the same canvas. Suspend-and-resume is native, meaning a workflow can pause for a human review and pick back up without custom state management. The project is MIT licensed, carries zero runtime dependencies according to the docs, and ships full TypeScript types.
FreeOpen SourceAPISelf-hostedVerified Jul 8, 2026
3. Teable 3.0
Teable positions itself as an AI-native database that lets you describe what you need in plain language and get structured tables, automations, and basic apps without writing code. File ingestion works well for structured extraction tasks — receipts, contracts, resumes — where the AI fields parse and populate rows automatically. The automation layer handles triggers and actions for teams that have outgrown Zapier-style one-step rules but are not ready to maintain a full workflow engine. The ceiling appears when logic gets complex: branching conditions and multi-table orchestration push past what the chat interface can express cleanly. Teams hitting that wall typically bolt on a separate scripting layer or migrate to a purpose-built backend.
PaidAPISelf-hostedVerified Jul 24, 2026
4. Atlas
The platform layers document extraction, a rule-encoding structure the vendor calls a context graph, exception handling, and ERP posting into a single agent loop — so invoices that arrive in any format get validated against POs, routed for approval, and posted without a person in the middle. The vendor states their OCR model ranks first on the IDP Leaderboard, ahead of GPT-5, Gemini, and Claude. Where the system earns its keep is exception resolution: when a field doesn't match, the agent checks it against your encoded rules rather than dropping it in a queue. Every decision traces back to the rule and document that drove it, which matters when an auditor asks.
PaidAPISelf-hostedVerified Jun 27, 2026
5. ComfyUI
ComfyUI exposes every model, sampler, conditioning step, and post-processing node as a discrete block on an infinite canvas, so the pipeline that produced the result is the documentation. VFX teams and creative studios use it to build multi-model pipelines where every parameter is auditable and every step can be swapped independently. The node graph runs locally via Comfy Desktop or in the cloud, and workflows can be published as API endpoints through Comfy API. Where it breaks: the node graph is not a gentle on-ramp. Teams that need non-technical colleagues to run pipelines use App Mode, a simplified overlay, but deep customization still requires fluency with the underlying graph.
PaidOpen SourceAPISelf-hostedVerified Jun 30, 2026
6. LiveContext
LiveContext combines chat-driven workflow building, multi-step agents with credit budgets, an auditable execution log, and a marketplace where teams can share or fork apps. The self-hosted option means organizations with data residency requirements are not forced onto a vendor cloud. Agents run tasks on their own — support email triage, expense approvals, lead normalization — and the credit budget system gives you a hard ceiling on runaway execution costs. The scraped page content is thin on specifics, so precise limits on step counts, integration depth, and throughput are not sourced; the architectural pattern is confirmed but the edge cases are not documented publicly.
PaidAPISelf-hostedVerified Jul 7, 2026
7. Gumloop
Gumloop lets growth, sales, and ops teams wire together multi-step AI agents that run on their own — pulling from external APIs, enriching CRM records, drafting content, and firing results into Slack or Teams without a human trigger per run. The visual builder handles the common cases well: lead enrichment, meeting prep, competitive research. Branching logic that depends on what a previous step returned is where the ceiling appears — complex conditional paths push teams toward adding custom code nodes, which means they are now maintaining two layers. Security and compliance teams get enterprise-grade controls over AI usage, which matters when rolling out to non-technical employees at scale.
Paid$37/monthAPISelf-hostedVerified Jun 4, 2026
8. Onpilot
The platform connects agents to ERP, CRM, support tools, and custom APIs, then layers in approval steps, permission scopes, and audit logs so the agent cannot act unilaterally on sensitive operations. Agents can search, reason, take action, and hand off to a human — the approval step pauses execution and sends an interactive Slack message before anything ships. Multi-tenant architecture means a single deployment can serve isolated customer or plant workspaces with per-tenant access control. Where it breaks: Onpilot is a custom-built, consultative engagement, not a self-serve platform you configure over a weekend — teams without clear workflow documentation will stall during scoping.
PaidAPISelf-hostedVerified Jun 12, 2026
Listings on this page are sourced and verified by the AIDiveForge data pipeline. AIDiveForge is editorially independent — no money changes hands for inclusion.