How I built AgentForge, an open-source agent harness that benchmarks 4 different memory architectures on real coding tasks.

Everyone in AI right now is arguing about which model is best. GPT vs Claude vs Gemini. Benchmark scores. Arena ratings. Token prices. I think they're asking the wrong question. LangChain proved it earlier this year: their coding agent jumped from outside the top 30 to the top 5 on Terminal Bench 2.0 by changing nothing about the model. They only changed the harness — the infrastructure that wraps the agent. Anthropic's own engineering team discovered that their agents exhibited "context anxiety" — performance degraded as context filled up, even after compaction. The fix wasn't a better model. It was a better harness. So I built one. And I benchmarked 4 different memory architectures against 6 real coding tasks to see what actually matters. The problem I wanted to solve Here's what happens when you give a coding agent a bug to fix: The agent reads the code It forms a plan It uses tools (bash, file read/write, search) to explore and edit It runs tests to verify If tests fail, it iterate