Dev builds research wiki for agent swarms, following Anthropic's wiki memory notes
teortaxesTex · x · 2026-11-08
Developer apazcli says he spent the past week carefully building a research wiki system, following Anthropic's notes on wiki memory systems, for the same reason: he wants to let agent swarms run rampant over his research projects, and they need a way to communicate with each other and with him.
The attached screenshot shows his git-backed research wiki: folders for experiment logs, hyperparameter heuristics, research roadmap, and idea notes; wiki pages embed training-loss charts, experiment comparison tables, and cross-references, with a history panel tracking completed runs — a structured wiki that carries the agents' experimental evidence for both humans and agents to read.
More from coding & agent
- Agentic Creativity course recordings now publicly listed on YouTube — round · 2026-11-08
- LittlePly: a chess agent combining transformer policy, value search and bounded Stockfish help — andreisavu · 2026-11-08
- LittlePly chess agent: transformer policy plus bounded Stockfish assistance — andreisavu · 2026-11-08
- Leaked account: Google-style review bureaucracy stalls startup Reflection, PRs take weeks to merge — SonglinYang4 · 2026-11-08
- New Vercel Hire Builds a Rex-Powered TUI for Spinning Up Agent Sessions — JohnPhamous · 2026-11-08
- OpenAI Buys Pierre to Give Codex a Home for Agent-Written Code — shashib · 2026-11-08