Agent Frameworks Considered Harmful — Rémi Louf, .txt
Rémi Louf built his own agent system after encountering problems with existing frameworks — duplicates, missing messages, and unlogged prompt changes.
Instead of complex graphs, he created something simple: agents as plain markdown files, a log where everything is saved and can be traced, and a system where each part of a prompt is stored separately with a hash so you can see exactly what changed between runs. It took two weeks to build and now runs twenty agents at his fifteen-person company.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago