25 agents, 11k lines of code, 204 commits in 5 hours: a multi-agent coding experiment
doodlestein · x · 2026-09-04
Developer doodstein shares a hands-on multi-agent coding experiment: starting from only a plan document, 25 agents produced 350+ task beads, 11k lines of code (8k core, rest tests) and 204 commits in about 5 hours, coordinated via his cassmemory project and an Agent Mail messaging system. He exported the inter-agent messages as a static site for inspection, and Claude provided an overall progress assessment. In the replies, @mjmeyer suggests combining it with observational memory, an extension he has used on pi since March.
More from coding & agent
- Live show to cover rogue agent swarm incidents, GPT-6 Astra, and Runway's Solaris world model — DhruvBatra_ · 2026-09-05
- One Weekend Exercise for Learning to Build AI Products: Automate a Workflow End to End — realmadhuguru · 2026-09-05
- After Datadog and Grafana, dev endorses Pydantic Logfire for all observability — samuelcolvin · 2026-09-05
- Vibe coding isn't the problem—conflating it with agentic engineering is — bendee983 · 2026-09-05
- Allie Miller shares her AI research workflow: hypothesis-first with hundreds of agents — alliekmiller · 2026-09-05
- Builder shares update on Grok bot + Shopify integration experiment — billyjhowell · 2026-09-05