SmallCode is a terminal-native coding agent designed from the ground up to extract useful work from local models (7B-20B) running on consumer hardware.
AGENTS
-
Running local terminal AI agents with Ollama
By
–
It runs locally without any cost. SmallCode is not a model. It's a terminal agent. Here's Gemma 4 model on @ollama
: https://
ollama.com/library/gemma4 I'd suggest to read the post before commenting LOL -
Local AI coding agent workflow with Hermes orchestrator
By
–
LOCAL AI coding agent finally make sense with Hermes orchestrator. Hermes routes work through Kanban. SmallCode uses Ollama models on a Mac mini for scoped patches, tests, and repo cleanup. Claude and Codex do the heavy lifting. All of it tracked in a single Kanban board.
-
Jensen Huang on Dell Deskside Agentic AI and Practicality
By
–
This feels like the enterprise AI conversation getting very real. When Jensen Huang talks about Dell Deskside Agentic AI, the key for me is practicality: secure local agents, open sandboxed environments, Dell infrastructure, and services that help teams actually get to
-
Manus AI Agent Adds Persistent Memory for Recurring Tasks
By
–
🆕 Manus just dropped Scheduled Tasks 2.0 – and it's not just "run this again at 9 AM."
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 19 mai 2026
Now your recurring tasks carry full context. Same conversation. Same files. Same project setup.
Your AI agent finally has memory between runs.
🔗 https://t.co/RaCxZrv5vK#Manus #AITools… pic.twitter.com/tnZpQIv4INManus just dropped Scheduled Tasks 2.0 – and it's not just "run this again at 9 AM." Now your recurring tasks carry full context. Same conversation. Same files. Same project setup. Your AI agent finally has memory between runs. https://
manus.im/blog/manus-sch
edules
… #Manus #AITools -
Networked AI agents compound capabilities via shared learning
By
–
Every Job makes an AI Agent smarter. Every new skill can be instantly shared across the network. One Agent learns, all Agents level up — creating a self-accelerating intelligence engine where capabilities don’t add up, they compound exponentially. #AIAgents #Jobs
-
The Agentic AI Playbook 2026 Edition for Reliable AI Agents
By
–
The Agentic AI Playbook 2026 Edition Turns LLMs into Reliable AI Agents: https://
amzn.to/49zjzId -
The AI Agent Blueprint: A Practical Guide to Building AI Agents
By
–
The AI Agent Blueprint — A Practical Playbook for Building Agentic Artificial Intelligence — Launch Your First Agent in 30 Days: https://
amzn.to/4qHbpVP -
Building Production-Ready AI Agent Systems and Architectures
By
–
30 Agents Every AI Engineer Must Build — Build production-ready agent systems using proven architectures and patterns: http://
amzn.to/41ckg6z v/ @PacktDataML —
What you will learn:
Deploy production-ready agent systems that scale securely and reliably
Use LangChain and -
Avoiding self-training bias in agent self-improvement
By
–
In SFT we often train on other agents data (distillation) so you’re right. However we also try to climb by self-improvement. This is where it becomes important for the agent not to train on its actions. Any bias on the agent beliefs (weights of the neural net) will be amplified.