Intel
Page 28
Garry Tan@garrytan
A short essay arguing that productive AI coding agents come from a lightweight harness plus composable skills. Explains the context-management and workflow ideas behind the '10-100x' claim. An opinion piece, not a harness you can run.
Why it mattersThe framework much of the current agent discourse is downstream of: keep the harness lightweight, push capability into composable skills, claim 10–100x. Read the original before the takes about it — this is the source.
Akshay 🚀@akshay_pachaar
A comprehensive technical guide explaining how to implement memory systems for AI agents, covering everything from basic Python lists to advanced graph-vector hybrid approaches. Provides practical solutions for building agents that can remember and learn from past interactions.
Why it mattersA technical progression from a Python list to graph-vector hybrid memory, with the tradeoffs at each step. The reference to reach for when "just stuff it in the context window" stops scaling.
ChatDev 2.0
A zero-code multi-agent orchestration platform that lets users build and execute customized multi-agent systems through simple configuration.
Why it mattersZero-code multi-agent orchestration: you describe the system in config and it builds and runs the agent team.
repoChen Qian et al.
TradingAgents
Multi-agent LLM framework that simulates real-world trading firms by deploying specialized AI agents for fundamental analysis, sentiment analysis, technical analysis.
Why it mattersMost "LLM trading bot" projects are one prompt wrapped around a price feed. TradingAgents instead models an actual firm — separate agents for fundamentals, sentiment, and technicals that debate before acting.
repoTauric Research
An index of the vibe-coding frontier. Corrections welcome.