Grist
A complete coding-agent harness — confidence-gated routing, institutional memory.
Grist (grist.lol) is a complete coding-agent harness: every task is routed to the cheapest capable model rung by confidence gates, every verified change is remembered as institutional memory, and inference is billed to your own provider key. npm install -g grist-ai.
In the news
DeepSeek ships Harness Desktop; the 'everything is a plugin' harness passes 240k stars
DeepSeek releases a macOS and Windows Desktop app for DeepSeek Harness, its open-source agent harness where everything — tools, sub-agents, even the loop — is a plugin. The repo passed 240k stars within three months of its August launch, making it the fastest-growing harness in the field's history.
HarnessTax: harness choice swings agent cost more than model choice
Arena.ai's HarnessTax study tests 21 model–harness combinations across Claude Code, Codex CLI and Pi, finding harness choice can significantly change cost even at similar task success rates. Weeks earlier, SWE-bench Pro analysis showed swapping harnesses moved pass@1 more than model upgrades (23%→52% on GLM-5.2) — and that harness rankings barely transfer across models.
Related startups
Cognition
Devin, the AI software engineer, and the Windsurf IDE.
Cognition builds Devin, an autonomous AI software engineer that plans and executes engineering tasks end-to-end, and acquired the Windsurf agentic IDE in 2025. One of the defining startups of the coding-agent wave.
Letta
Stateful agents with memory, from the team behind MemGPT.
Letta (formerly MemGPT, out of UC Berkeley) builds an agent server with built-in memory, context management and state — letting agents persist, learn and be edited like files rather than living in a chat window.
Cursor (Anysphere)
The AI-native code editor where agent mode lives.
Cursor rebuilt the IDE around models: tab completion, in-editor chat and agent mode that plans multi-file edits and runs commands. Its rise set the pace for the entire coding-agent market.