LongCat-AudioDiT Enhanced
🐱
Voice cloning TTS with Whisper STT
Gregor Koch PRO
cronos3k
AI & ML interests
None yet
Recent Activity
updated a Space 1 day ago
cronos3k/LongCat-AudioDiT-Enhanced published a Space 2 days ago
cronos3k/LongCat-AudioDiT-EnhancedOrganizations
updated a
Space 1 day ago
published a
Space 2 days ago
upvoted an article 22 days ago
Article
9 Hours, 199 Rounds, Zero Errors: Three Local NemoClaw AI Agents Migrated COBOL to Python Using Only Persistent Memory
•
1
published an article 22 days ago
Article
9 Hours, 199 Rounds, Zero Errors: Three Local NemoClaw AI Agents Migrated COBOL to Python Using Only Persistent Memory
•
1
posted an update 22 days ago
Post
160
🧠 What if your AI agents could remember every decision across 199 rounds — without stuffing the context window?
I ran 3 NVIDIA Nemotron-3-Nano-30B-A3B agents (3B active params each, MoE) for 9 hours on a real COBOL→Python migration (AWS CardDemo, 50K lines). All local, all on llama.cpp, zero API calls.
Results:
• 24M tokens processed
• 52 Python files written
• 402 persistent memories shared between agents
• Context per agent: never exceeded 9K tokens
• Speed: 97-137 tok/s from start to finish — no degradation
• Errors: 0
The secret: memory-first architecture via AgentAZAll. Only the last round goes into context. Everything else is a tool call to recall/remember. The context window stays clean. Speed stays constant. Knowledge grows forever.
Full technical writeup with architecture, code samples, and all numbers:
🔗 https://www.linkedin.com/pulse/i-gave-three-local-ai-agents-shared-persistent-memory-gregor-h-max-yxs2f/
Try AgentAZAll: cronos3k/AgentAZAll
GitHub: https://github.com/cronos3k/AgentAZAll
I ran 3 NVIDIA Nemotron-3-Nano-30B-A3B agents (3B active params each, MoE) for 9 hours on a real COBOL→Python migration (AWS CardDemo, 50K lines). All local, all on llama.cpp, zero API calls.
Results:
• 24M tokens processed
• 52 Python files written
• 402 persistent memories shared between agents
• Context per agent: never exceeded 9K tokens
• Speed: 97-137 tok/s from start to finish — no degradation
• Errors: 0
The secret: memory-first architecture via AgentAZAll. Only the last round goes into context. Everything else is a tool call to recall/remember. The context window stays clean. Speed stays constant. Knowledge grows forever.
Full technical writeup with architecture, code samples, and all numbers:
🔗 https://www.linkedin.com/pulse/i-gave-three-local-ai-agents-shared-persistent-memory-gregor-h-max-yxs2f/
Try AgentAZAll: cronos3k/AgentAZAll
GitHub: https://github.com/cronos3k/AgentAZAll
updated a
Space 24 days ago
published a
Space about 1 month ago
updated a
Space about 2 months ago
published a
Space about 2 months ago
upvoted an article 2 months ago
Article
Running a 32 Billion Parameter Image Model on “Ancient” V100 GPUs
•
1
published an article 2 months ago
Article
Running a 32 Billion Parameter Image Model on “Ancient” V100 GPUs
•
1
liked 2
Spaces 9 months ago
upvoted an article 12 months ago
Article
Unleash the Pixel Woodchipper Pro: Aggressively Disrupting Unwanted Image Data (Maybe?)
•
1
published an article 12 months ago
Article
Unleash the Pixel Woodchipper Pro: Aggressively Disrupting Unwanted Image Data (Maybe?)
•
1
upvoted an article 12 months ago
Article
Reclaiming Your Words 🛡️: Fighting Stealth Watermarks in AI-Generated Text & Why It Matters (A Developer's Perspective)
•
2
published an article 12 months ago
Article
Reclaiming Your Words 🛡️: Fighting Stealth Watermarks in AI-Generated Text & Why It Matters (A Developer's Perspective)
•
2
liked a
model about 1 year ago
Hosting bloom 176B model for inference
👍 3
17
#45 opened over 3 years ago
by 
NonStatic