Toolbox/Frameworks & SDKs

Low-code builders

visual and no-code agent builders

21 repositories, most starred first
State of the category

n8n-io/n8n n8n is the de facto leader for general-purpose visual agent builders because it pairs a production-ready low-code canvas with the largest integration ecosystem and self-hosting; before choosing, decide whether you need broad integrations and stability (n8n) or a smaller tool that targets privacy, a vertical workflow, multi-agent orchestration, or developer-first scaffolding.

Local‑first / privacy
Teams that must run fully offline or keep models and data on-premise pick projects built for local-only or first-class self-hosting rather than cloud-managed platforms, because regulatory and latency constraints make cloud keys unacceptable.
Vertical UIs & workflows
Some teams need domain-specific UIs (finance terminals, doc/website exporters, ComfyUI assistants or repo-aware viewers) so they pick specialized builders that embed domain skills and outputs rather than a general canvas.
Team & production tooling
Enterprises and multi-team projects prefer platforms that add RAG, multi-provider model support, governance and collaboration features (workflows, SDKs, MCP) so agents are operable, auditable and deployable at scale.
Multi‑agent orchestration
Groups building coordinated or self-improving agent systems choose frameworks that focus on multi-agent planning, hierarchy and automated agent generation rather than single-agent flows, because complex automation needs explicit orchestration primitives.
Developer scaffolds & app generation
Developer teams and product engineers often want one-click scaffolds, app builders, or code-generation tooling (Next.js/FastAPI templates, TypeScript SDKs, repo-aware scaffolds) to go from prototype to deployable app quickly.
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
203.3k +628/7d
Web appCLIBYOKOpenAIAnthropicGeminiOllama / localWorkflow-levelHuman approvalsSelf-hostableSelf-hostable; cloud offering available
187.1k +150/7d
Web appCLIBYOKWorkspace-level accessNone mentionedSelf-hostablePaid hosted service; self-hosted uses your infrastructure and model-provider costs
154.4k +671/7d
Web appBYOKOpenAIOllama / localDiff/file onlyNone mentionedSelf-hostable / localFree cloud sandbox (200 GPT-4 calls); self-hosted on your infra.
154.2k +457/7d
Web appCLIBYOKDiff onlyNone mentionedSelf-hostableBring your own API key or self-hosted
65.6k +282/7d
Web appCLIBYOKOpenAIAnthropicGeminiOllama / localWhole-repo analysisBasic routing & filtersRuns fully localSelf-hosted (free); external LLM API costs apply.
30.9k +212/7d
CLICIBYOKOpenAIAnthropicGeminiOllama / localFixed providerDiff onlyNoneFully localFree & open-source (AGPL); third-party model/API costs or commercial license may apply
22.7k +73/7d
Web appBYOKOpenAIAnthropicGeminiOllama / localFixed providerDiff onlyRAG reduces hallucinationFully local possibleSelf-hosted; your model/API costs
5.3k +293/7d
CLIWeb appBYOKWhole-repo accessApproval gatingSelf-hostableFree for personal/local use; license required for 3+ users
8.7k +143/7d
CLIWeb appBYOKAnthropicOpenAIGeminiFixed providerTemplate + inputConstraints & previewLocal-first self-hostedUses your agent CLIs; no API key required
1.9k +14/7d
CLIWeb appCIBYOKDiff + related filesGuardrailsSelf-hostableYour API key, per-usage
2.3k +5/7d
Web appBYOKOpenAIAnthropicGeminiOllama / localNode/workflow onlyNone documentedFully local possibleYour API key; or free local models.
1.4k +20/7d
CLIWeb appBYOKNo repo contextNoneSelf-hostableYour API key, provider charges
Ranked by maturity — 9 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.

n8n-io/n8n203.3k
ContextNoiseCustomPrivacyModelsMaturity

Provides a visual low-code canvas plus custom code and 1,500+ integrations to build production-ready multi-step AI agents with self-hosting and no provider lock-in.

ContextNoiseCustomPrivacyModelsMaturity

Provides both a managed, no-API-key hosted platform and an open-source self-hostable agent runtime with a visual builder and marketplace.

langgenius/dify154.4k
ContextNoiseCustomPrivacyModelsMaturity

Integrated low-code workspace combining visual AI workflows, RAG pipelines, agent builders, and broad multi-provider model support that can be self-hosted.

ContextNoiseCustomPrivacyModelsMaturity

Provides a visual low-code flow builder with built-in API and MCP servers to turn workflows into deployable tools.

ContextNoiseCustomPrivacyModelsMaturity

An all-in-one, local-first no-code agent platform that bundles chat, agents, vector DBs, desktop and web deployments, and dynamic model routing—beyond libraries that only provide primitives.

ContextNoiseCustomPrivacyModelsMaturity

A native C++/Qt6 single-binary finance terminal with embedded Python analytics, 100+ data connectors, and built-in multi-provider plus local LLM agent support.

ContextNoiseCustomPrivacyModelsMaturity

An open-source, self-hosted platform that combines RAG, a workflow engine and MCP tool-use to build enterprise-grade agents supporting both private and public models.

ContextNoiseCustomPrivacyModelsMaturity

A local-first visual AI workbench that produces editable artifacts (code, documents, websites, designs, videos) and lets agents plan, run tools, and modify files in-place rather than only returning chat transcripts or finished files.

All repositories (21)

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code,…

203.3k
+6287d
TypeScript
7 yrs

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the too…

187.1k
+1507d
Python
3 yrs

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. De…

154.4k
+6717d
TypeScript
3 yrs

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

154.2k
+4577d
Python
3 yrs

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent…

65.6k
+2827d
JavaScript
3 yrs

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and e…

30.9k
+2127d
C++
2 yrs

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.7k
+737d
Python
2 yrs

"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

9.8k
+107d
Python
1 yr

✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magaz…

8.7k
+1437d
HTML
3 mo

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistan…

5.5k
+97d
TypeScript
1 yr

Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for…

5.3k
+2937d
TypeScript
1 yr

Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code, Codex, Gemini CL…

4.1k
+47d
TypeScript
1 yr

Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code, Codex, Gemini CL…

4.1k
+47d
TypeScript
1 yr

LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes…

2.3k
+57d
Python
2 yrs

No-code multi-agent framework to build LLM Agents, workflows and applications with your data

2.3k
Python
3 yrs

Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out…

1.9k
+147d
Python
8 mo

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistant…

1.4k
+207d
TypeScript
12 mo

Low code tool to rapidly build and coordinate multi-agent teams

1.1k
TypeScript
2 yrs

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MC…

630
+117d
TypeScript
2 mo

Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and d…

158
+37d
TypeScript
6 mo

A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.

58
+17d
2 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.

Flowise Cloud

The hosted side of Flowise: build the same visual agent flows in your browser and let Flowise run and scale them, so there is no container to deploy or update.

Try Flowise Cloud
n8n Cloud

Managed hosting for n8n's node-based automations with AI agent steps: the same workflows you would self-host, run for you with credentials and scheduling handled.

Try n8n Cloud
Langflow (DataStax)

The hosted counterpart to open-source Langflow: drag-and-drop agent and RAG pipelines deployed on DataStax's cloud rather than a server you run yourself.

Try Langflow (DataStax)

More in Frameworks & SDKs