Tag
A detailed technical report on Hermes Mixture-of-Agents (MoA) findings, including benchmark results, caching economics, GPU topology studies, and a roadmap for future development.
Introduces the advanced use of Claude, which involves building an Agent system that automatically decomposes tasks, generates prompts, assigns roles, and reviews results, including using files like CLAUDE.md to accumulate context and multi-Agent collaboration to build automated workflows.
TinyFish Bigset is an open-source multi-agent system that turns natural language prompts into structured datasets from the live web, with schema inference, autonomous research agents, and scheduled refresh. It runs self-hosted via Docker and is built on TinyFish's search infrastructure.
A Twitter thread describing how to build a software factory using Claude Code with seven specialized AI agents to avoid the pitfalls of vibe coding, enabling one developer to ship features efficiently.
A concept: Use Multica to manage local runtimes (e.g., Claude Code, Codex), Helio to predefine Agents, Obsidian as the memory/context system, combined with Harness Engineering—exploring the best approach for a local multi-agent system.
PaperFit is a vision-based LaTeX layout agent system that automatically compiles, diagnoses PDF layout issues, and fixes the source code. It supports use in Claude Code, Codex, and Cursor.
Brace Sproul shares a post about Engine, a complex production agent system, encouraging others to read about how it was built.
A 13-week recap of using OpenClaw as a daily AI agent on a Raspberry Pi, highlighting strengths like cron-based automation and memory curation, and pain points like model config issues and subagent orchestration.