Clearing context with fresh conversations in Coworker
Melvin Vivas · X post · 2026-10-03 · Open on X
Topics: Prompt & Context Engineering, AI Agents, Tool Use & MCP · Level: intermediate
Summary
The creator explains a deliberate design choice in Coworker: you can start a fresh conversation to clear the agent's context. Otherwise all previous context is sent to the model. Compaction may happen at some point, but he argues nothing beats a clean context.
Key points
- In an ongoing agent conversation, all of the accumulated context is sent to the model on every turn.
- Compaction (summarizing old context) can help, but a fresh conversation gives the cleanest context.
- Coworker lets you start a new conversation on purpose to clear context.
- The creator says Grok Bot and Dots do not currently offer this.
- Design takeaway: give users explicit control over context resets in agent apps.
Resources mentioned
- Coworker (donvito/coworker) · repo · github.com · free
The creator's agent/bot tool. Version 0.7.0 adds a Primary Bot, free web search, an activity dashboard and support for open models through OpenRouter.
Also in: Coworker: a local-first desktop AI coworker that works with any model (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes), Coworker: A Desktop AI Assistant App, Not a Coding Agent (Melvin Vivas on X · notes), Coworker v0.7.2: Open-Source Desktop AI Assistant (Melvin Vivas on X · notes) and 59 more
Try this
- Try the fresh-conversation feature in Coworker and give the creator feedback.
More in Prompt & Context Engineering
- Emoji Acknowledgement Prompt for Agents (Built Into Grok Bot)
- Devil's Advocate Grok Bot That Challenges Your Ideas
- Keep One Topic per Chat (Why Dots Didn't Fit)
- Karpathy's Tip: Ask LLMs to Explain in ASD-STE100
- Instant Generative UI with json-render and Jev
- Jev on OpenRouter: Typed Decisions Instead of Generated Text