How to build an agent harness from scratch: LLM module, tools module, and the ReAct route
ryunuck · x · 2026-09-15
Elvis Saravia shares a short guide on building an agent harness from scratch: pick TypeScript or Python, feed the ReAct paper to your agent to produce a minimal implementation you can inspect, and target three parts — an LLM inference module (ideally multi-model via something like OpenRouter, with separable system prompt for context engineering), a tools module, and orchestration. Hands-on building is the best way to actually learn harnesses.
Related event: Guide: building a minimal agent harness from scratch(3 posts)→
More from coding & agent
- Claude Mods: Anthropic to ship function hooks-based plugins for Claude Code in weeks — bcherny · 2026-09-15
- The hidden cost of failed agent runs: one task may burn twice the credits on Codex — ToneAromatic178 · 2026-09-15
- OpenAI Agents API enters public beta: managed cloud agents on the Codex harness — craigsdennis · 2026-09-15
- Interview with the Claude Code team on building it while models keep outpacing engineering — EricBuess · 2026-09-15
- Before buying a faster model, check your agent's traces: serial API calls eat latency — gethackteam · 2026-09-15
- ElevenLabs MCP adds voice, music, image, and video generation — lukeharries · 2026-09-15