Factory Droid 1.0 makes the agent write JavaScript to batch its own tool calls
Droid 1.0 turns programmatic tool calling on by default: the model writes a sandboxed Script that runs many tool calls in one request.
Wildness 2/5 · Mostly tamed
Topic · 5 stories
harness
5 stories tagged harness on AI Tamer, newest first.
Paper: swapping coding-agent harness flips as many SWE-bench tasks as a rerun
Claude Code, OpenCode and mini-SWE-agent ran five models on SWE-bench Verified. Harness choice moved cost up to 3x but outcomes about as much as noise.
Wildness 2/5 · Mostly tamedGoogle Research's Harness² tunes an agent's prompts and tools, not its weights
Harness², a Google Research paper and Apache-2.0 repo from 9 October, refines an agent's harness per task with model weights fixed. Gains are the authors'.
Wildness 3/5 · Partly tamedHarness and Augment say Harness bought select assets, including Cosmos
Augment and Harness both say Harness acquired Cosmos, the Auggie CLI, the Code Context Engine, and related technology, and that the team joins Harness. Neither post states a price or a plan for current customers.
Wildness 3/5 · Partly tamedDogwood Local Engine: Apache-2.0 temporal allow/deny for agent tool calls
AWS Open Source Blog (Sep 30, 2026) released Dogwood Local Engine under Apache 2.0: an embeddable library that issues allow/deny on agent tool-call requests under temporal history. The harness must enforce.
Wildness 4/5 · Still wild
