rcortx

rcortx / kiwiq

Public

Production-grade multi-agent orchestration platform - JSON-defined agents, multi-tier memory, and built-in observability. Battle-tested on 200+ enterprise AI agents. Now fully open-sourced (prod at https://kiwiq.ai).

10
3
100% credibility
Found Mar 19, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

KiwiQ is an open-source platform for orchestrating multi-agent AI workflows defined as JSON graphs, with built-in support for multiple LLM providers, human review, and production observability.

How It Works

1
🔍 Discover KiwiQ

You hear about KiwiQ, a ready-to-use platform for creating smart AI teams that handle complex tasks like content creation and research.

2
📥 Get it running

Download the free tools and start everything on your computer with simple setup steps.

3
🔗 Connect smart helpers

Link popular AI thinkers like ChatGPT or Claude so your teams can reason and create.

4
🚀 Launch your hub

Turn on the platform and open the helpful guides and dashboards in your web browser.

5
🎯 Pick a ready team

Choose from dozens of pre-built AI teams for writing blogs, scoring leads, or deep research.

6
⚡ Watch magic happen

Run your first team and see it work step-by-step with real-time updates and pauses for your input.

✅ AI powerhouse unlocked

Your custom AI workflows now handle enterprise tasks reliably, saving hours of work daily.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is kiwiq?

KiwiQ is a production-grade agentic AI platform for orchestrating multi-agent workflows using JSON schemas, multi-tier memory (relational, document, vector, cache), and built-in observability. Battle-tested on 200+ enterprise AI agents at kiwiq ai, it compiles graphs with 24+ node types—like LLMs, scraping, RAG pipelines, human-in-the-loop pauses—into executable Prefect flows supporting OpenAI, Anthropic, Gemini, and more. Python-powered, it ships with 27+ ready workflows for content creation, diagnostics, lead scoring, and deep research.

Why is it gaining traction?

Unlike lightweight frameworks, this delivers a full production-grade agentic AI system on GitHub with event-driven async processing, WebSocket streaming, Stripe billing, and Docker Compose for dev/prod—including Nginx SSL and health checks. Developers grab it for instant HITL, RAG via Weaviate, and sandboxed code execution without wiring databases or queues. The 27+ workflows and SDK-first approach cut setup from weeks to hours.

Who should use this?

AI engineers at startups building kiwiq ai-style marketing agents or enterprise teams scaling 200+ agents with HITL and observability. Ideal for devs handling production-grade RAG GitHub pipelines, content diagnostics, or lead scoring without reinventing orchestration, billing, or multi-LLM routing.

Verdict

Promising base for production-grade agentic AI GitHub projects, but 10 stars and 1.0% credibility score mean it's early-stage—docs and Docker are solid, tests cover 75+ cases, yet low adoption warrants forking over blind trust. Try for agent-heavy prototypes if you need battle-tested enterprise patterns now.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.