AI brainstorming and strategic thinking powered by CellCog. Reasoning, problem-solving, ideation, strategic planning — then execution across every modality:...
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Complex ideas need iteration, not conversation. Think → Do → Review → Repeat.
CellCog is the thinking partner that completes the full loop — reasons with you, then executes across every modality: research, documents, visuals, data, prototypes. Review real output, refine your thinking, iterate on substance. Like having an Alfred who doesn't just advise — he builds.
For problems where you don't know the answer upfront and the solution emerges through doing, not just discussing.
For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.
OpenClaw (fire-and-forget):
result = client.create_chat( prompt="[your task prompt]", notify_session_key="agent:main:main", task_label="my-task", chat_mode="agent", )
All agents except OpenClaw (blocks until done):
from cellcog import CellCogClient client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...") result = client.create_chat( prompt="[your task prompt]", task_label="my-task", chat_mode="agent", ) print(result["message"])
Most CellCog skills follow a pattern: you know what you want → CellCog delivers it.
But some problems don't work that way:
Think-cog is your worker agent for intellectual exploration. You're the manager agent providing direction. CellCog thinks and works alongside you.
Unlike single-shot tasks, think-cog is conversational by design:
# Start the thinking session result = client.create_chat( prompt="[your thinking prompt]", task_label="my-task", chat_mode="agent", )Continue the conversation — each exchange deepens understanding
result = client.send_message( chat_id=result["chat_id"], message="What if we approached it from this angle instead?", )
Think-cog expects back-and-forth conversation, not single requests. Each exchange deepens understanding.
See https://cellcog.ai for complete SDK API reference.
When you're weighing tradeoffs:
"I'm building a notification system that needs to handle 10M daily users. I'm torn between:
- WebSocket connections for all users
- Server-sent events with polling fallback
- Push notifications only
Help me think through the tradeoffs. My team is small (3 engineers) and we're on AWS."
When the path forward isn't clear:
"My SaaS is growing but I'm not sure whether to:
- Focus on enterprise sales (fewer customers, bigger deals)
- Double down on self-serve (more customers, smaller ARPU)
Current metrics: 500 customers, $50 ARPU, 2 enterprise deals in pipeline worth $50K each.
Let's think through this together."
When you're exploring possibilities:
"I want to create a video campaign for my coffee brand but I'm not sure what angle to take. The brand is:
- Specialty single-origin coffee
- Direct trade with farmers
- Premium pricing ($25/bag)
Target audience is 25-40 professionals who care about quality.
Help me brainstorm directions before we commit to production."
When you're stuck:
"My machine learning model keeps overfitting despite:
- Dropout layers
- Data augmentation
- Early stopping
Here's my architecture: [details]
Let's debug this together. What am I missing?"
When you need structured thinking:
"I have three job offers and I'm paralyzed by the decision:
- Startup (lower pay, more equity, more risk)
- Big tech (great pay, slower growth, stable)
- Mid-stage scaleup (balanced, interesting problem)
Help me build a framework to think through this."
"It's hard to know what's actually possible before you try it."
This is CellCog's core insight. Complex problems rarely have obvious solutions. The best work happens when two smart entities—you and CellCog—exchange ideas, challenge assumptions, and discover answers together.
Think of it as pair programming for thinking:
Use
for think-cog sessions.chat_mode="agent"
Why not agent team? Agent team is designed for autonomous deep work with multiple internal passes. Think-cog is about collaborative iteration WITH you. Agent mode keeps the conversation flowing naturally.
The magic happens in the back-and-forth, not in autonomous processing.
Share context generously: The more CellCog understands your situation, the better it can think alongside you.
State your constraints: Budget, timeline, team size, technical limitations—these shape what's possible.
Be honest about uncertainty: "I'm not sure if X is even feasible" is a great starting point.
Challenge the responses: Push back, ask "what about...", explore alternatives. Thinking improves through friction.
Let solutions emerge: Don't expect the answer in the first exchange. The best insights often come in message 4 or 5.
Capture decisions: When you reach clarity, summarize the conclusions. You can then use other CellCog skills to execute.
| Skill | Pattern | You Know the Output? |
|---|---|---|
| research-cog | Fire-and-forget | Yes - "Give me research on X" |
| video-cog | Fire-and-forget | Yes - "Create a video about X" |
| docs-cog | Fire-and-forget | Yes - "Create a document for X" |
| think-cog | Conversational | No - "Help me figure out X" |
Think-cog is for when you're in discovery mode. Other skills are for when you're in execution mode.
You:
"I'm building a two-sided marketplace for freelance designers. I'm stuck on the chicken-and-egg problem—how do I get designers without clients, and clients without designers?"
CellCog:
"This is the classic marketplace cold-start problem. Let me think through some approaches with you...
Option 1: Supply-first (designers)
- Pros: Designers are easier to acquire, content creates SEO value
- Cons: They'll leave if no jobs come
Option 2: Demand-first (clients)
- Pros: Revenue from day one, can manually fulfill initially
- Cons: Harder to acquire, need to deliver quality
Option 3: Constrain the market
- Focus on ONE design type (e.g., logo design only)
- Build liquidity in a narrow niche before expanding
What's your current thinking? And what resources do you have to invest in early growth?"
You:
"I have about $20K for initial marketing and can do some manual matching myself. The constrained market approach is interesting—I was thinking of going broad."
CellCog:
"That $20K + your time is actually a meaningful advantage. Let me build on the constrained market idea...
What if you started with:
- Niche: Startup logo design only
- Supply: Recruit 20-30 designers who specialize in startup branding (curated, not open signup)
- Demand: Target YC companies, indie hackers, ProductHunt launchers
The manual matching you'd do becomes a feature, not a bug—'curated matches by founders who understand startups.'
This gives you:
- Clear positioning
- Easier SEO/content ('startup logo design' vs 'design marketplace')
- Higher willingness to pay from funded startups
- Story for press/ProductHunt
Thoughts? Or should we explore other niches?"
The conversation continues, ideas refine, and eventually you arrive at a clear strategy to execute.
Run
/cellcog-setup/cellcog:cellcog-setupclawhub install cellcogpip install -U cellcogCELLCOG_API_KEYpip install cellcogCELLCOG_API_KEYNo automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.