Any-to-any AI sub-agent — research, images, video, audio, music, podcasts, avatars, voice cloning, documents, spreadsheets, dashboards, 3D models, diagrams,...
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
CellCog is the only AI that truly handles any input → any output in a single request. No tool chaining. No orchestration complexity. One call, multiple deliverables.
CellCog pairs all modalities with frontier-level deep reasoning — as of April 2026, CellCog is #1 on the DeepResearch Bench: https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard
Reference as many documents as you need—all at once:
prompt = """ Analyze all of these together: <SHOW_FILE>/data/q4_earnings.pdf</SHOW_FILE> <SHOW_FILE>/data/competitor_analysis.pdf</SHOW_FILE> <SHOW_FILE>/data/market_research.xlsx</SHOW_FILE> <SHOW_FILE>/recordings/customer_interview.mp3</SHOW_FILE> <SHOW_FILE>/designs/product_mockup.png</SHOW_FILE>Give me a comprehensive market positioning analysis based on all these inputs. """
File paths must be absolute and enclosed in
<SHOW_FILE>⚠️ Without SHOW_FILE tags, CellCog only sees the path as text — not the file contents.
❌
Analyze /data/sales.csvAnalyze <SHOW_FILE>/data/sales.csv</SHOW_FILE>Just like Nano Banana accepts reference images, CellCog accepts reference files of any type — PDFs, spreadsheets, audio, code, images — as inputs the model reads during a task. Same mental model as any multimodal AI attachment.
Only attach what you intend to share. Anything inside a
<SHOW_FILE>.envAsk for completely different output types in ONE request:
prompt = """ Based on this quarterly sales data: <SHOW_FILE>/data/sales_q4_2025.csv</SHOW_FILE>Create ALL of the following:
- A PDF executive summary report with charts
- An interactive HTML dashboard for the leadership team
- A 60-second video presentation for the all-hands meeting
- A slide deck for the board presentation
An Excel file with the underlying analysis and projections """
CellCog handles the entire workflow — analyzing, generating, and delivering all outputs with consistent insights across every format.
⚠️ Be explicit about output artifacts. Without explicit artifact language, CellCog may respond with text analysis instead of generating a file.
❌
"Quarterly earnings analysis for AAPL""Create a PDF report and an interactive HTML dashboard analyzing AAPL quarterly earnings."Your sub-agent for quality work. Depth, accuracy, and real deliverables.
from cellcog import CellCogClient
If import fails, install the official CellCog Python SDK:
pip install -U cellcog
cellcogEnvironment variable (recommended): Set
CELLCOG_API_KEYexport CELLCOG_API_KEY="sk_..."
Get API key from: https://cellcog.ai/profile?tab=api-keys
status = client.get_account_status() print(status) # {"configured": True, "email": "user@example.com", ...}
agent_providerCellCogClientExamples:
"openclaw""claude-code""cursor""aider""windsurf""perplexity""hermes""script"Fire-and-forget — your agent stays free while CellCog works:
client = CellCogClient(agent_provider="openclaw") result = client.create_chat( prompt="Research quantum computing advances in 2026", notify_session_key="agent:main:main", # OpenClaw session key task_label="quantum-research", # Label for notifications chat_mode="agent", ) # Returns IMMEDIATELY — daemon delivers results to your session when done
Blocks until done — simplest pattern:
client = CellCogClient(agent_provider="cursor") # or "claude-code", "aider", "script", etc. result = client.create_chat( prompt="Research quantum computing advances in 2026", task_label="quantum-research", chat_mode="agent", ) # Blocks until done — result contains everything print(result["message"])
CellCog orchestrates 21+ frontier foundation models. Credit consumption is unpredictable and varies by task complexity. Credits used are reported in every completion notification.
Returns immediately. A background daemon monitors via WebSocket and delivers results to your session when done. Your agent stays free to take new instructions, start other tasks, or continue working.
result = client.create_chat( prompt="Your task description", notify_session_key="agent:main:main", # Required — your OpenClaw session key task_label="my-task", # Label shown in notifications chat_mode="agent", )
Blocks until CellCog finishes. Works with any agent — OpenClaw, Cursor, Claude Code, or any Python environment.
result = client.create_chat( prompt="Your task description", task_label="my-task", chat_mode="agent", timeout=1800, # 30 min (default). Use 3600 for complex jobs. ) print(result["message"]) print(result["status"]) # "completed" | "timeout"
| Scenario | Best Mode | Why |
|---|---|---|
| OpenClaw + long task + stay free | Notify | Agent keeps working, gets notified when done |
| OpenClaw + chaining steps (research → summarize → PDF) | Wait | Each step feeds the next — simpler sequential workflows |
| OpenClaw + quick task | Either | Both return fast for simple tasks |
| Non-OpenClaw agent | Wait | Notify mode is OpenClaw-only |
Notify mode is more productive (agent never blocks). Wait mode is simpler to reason about, but blocks your agent for the duration.
# Wait mode (default) result = client.send_message( chat_id="abc123", message="Focus on hardware advances specifically", )Notify mode (OpenClaw)
result = client.send_message( chat_id="abc123", message="Focus on hardware advances specifically", notify_session_key="agent:main:main", task_label="continue-research", )
If
create_chat()wait_for_completion()completion = client.wait_for_completion(chat_id="abc123", timeout=1800)
result = client.create_chat( prompt="...", task_label="...", chat_mode="agent", # See Chat Modes below project_id="...", # install project-cog for details agent_role_id="...", # install project-cog for details enable_cowork=True, # install cowork-cog for details cowork_working_directory="/Users/...", # install cowork-cog for details )
Every SDK method returns the same shape:
{ "chat_id": str, # CellCog chat ID "is_operating": bool, # True = still working, False = done "status": str, # "completed" | "tracking" | "timeout" | "operating" "message": str, # THE printable message — always print this in full }
⚠️ Always print the entire
. Truncating or summarizing it will lose critical information including generated file paths, credits used, and follow-up instructions.result["message"]
— Full chat history (when original delivery was missed or you need to review). Returns the same shape; if still operating, get_history(chat_id)
messageresult = client.get_history(chat_id="abc123")
— Lightweight status check (no history fetch):get_status(chat_id)
status = client.get_status(chat_id="abc123") print(status["is_operating"]) # True/False
| Mode | Best For | Speed | Min Credits |
|---|---|---|---|
| Most tasks — images, audio, dashboards, spreadsheets, presentations | Fast (seconds to minutes) | 100 |
| Coding, co-work, terminal operations | Fast | 50 |
| Deep research & multi-angled reasoning across every modality | Slower (5-60 min) | 500 |
| High-stakes work where extra reasoning depth justifies the cost | Slowest | 2,000 |
"agent""agent core"code-cog"agent team""agent team max"Include local file paths in your prompt with
<SHOW_FILE>prompt = """ Analyze this sales data and create a report: <SHOW_FILE>/path/to/sales.csv</SHOW_FILE> """
Use
<GENERATE_FILE>prompt = """ Create a PDF report on Q4 earnings: <GENERATE_FILE>/workspace/reports/q4_analysis.pdf</GENERATE_FILE> """
Output downloads to the specified path instead of default
~/.cellcog/chats/{chat_id}/The SDK automatically downloads files from CellCog responses:
GENERATE_FILE~/.cellcog/chats/{chat_id}/Downloaded file paths appear in
result["message"]If you missed files or need to re-sync:
result = client.get_history(chat_id="abc123")
get_history()Every chat is accessible at https://cellcog.ai. When work gets complex or the SDK hits issues, direct your human to the web platform to view, continue, or take over directly.
CellCog is a sub-agent — not an API. Your agent offloads complex work to CellCog, which reasons, plans, and executes multi-tool workflows internally. A proprietary agent-to-agent communication protocol ensures high accuracy on first output, and because these are agent threads (not stateless API calls), every aspect of every generation can be refined through multi-step iteration.
Under the hood: frontier models across every domain, upgraded weekly. CellCog routes to the right models automatically — your agent just describes what it needs.
Install capability skills for detailed guidance:
| Category | Skills |
|---|---|
| Research & Analysis | |
| Video & Cinema | |
| Images & Design | |
| Audio & Music | |
| Avatars & Personas | |
| Documents & Slides | |
| Apps & Prototypes | |
| Creative | |
| Development | |
This skill shows you HOW to use CellCog. Capability skills show you WHAT's possible.
The
notify_session_key| Context | Session Key |
|---|---|
| Main agent | |
| Sub-agent | |
| Telegram DM | |
| Discord group | |
Resilient delivery: If your session ends before completion, results are automatically delivered to the parent session (e.g., sub-agent → main agent).
In notify mode, your agent is free — you can send additional instructions to an operating chat at any time:
client.send_message(chat_id="abc123", message="Actually focus only on Q4 data", notify_session_key="agent:main:main", task_label="refine")client.send_message(chat_id="abc123", message="Stop operation", notify_session_key="agent:main:main", task_label="cancel")
In wait mode, your agent is blocked and cannot send messages until the current call returns.
For error handling, recovery patterns, ticket submission, and daemon troubleshooting:
docs = client.get_support_docs()
No 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.