EPISODE · Sep 6, 2026 · 12 MIN
311 - Self learning harnesses are here
from Fragmented - AI Developer Podcast · host Kaushik Gopal
Claude Code and Codex have been the mainstay agent harnesses, with OpenCode and Pi as the popular open-source alternatives. But two new entries are pushing what a harness even is: DeepSeek's Cordis kernel, where everything — down to the agent loop itself — is a plugin you can hot-swap at runtime, and Prime Agent, an RLM-based harness that treats sub-agents and context as function calls in a live REPL. We break down what actually makes each one different.Full shownotes: https://fragmentedpodcast.com/episodes/311
Embed this episode
What this episode covers
Claude Code and Codex have been the mainstay. OpenCode and Pi showed what open-source harnesses could be. But two new entries just moved the goalposts: DeepSeek's Cordis kernel treats everything — even the agent loop itself — as a hot-swappable plugin, and Prime Agent runs the whole harness inside a live REPL where sub-agents are just function calls. Self-learning harnesses are here, and they're open source.
Ready to play
311 - Self learning harnesses are here
No transcript for this episode yet
Similar Episodes
No similar episodes found.