Coding AgentsCost OptimizationBenchmarksHarness EngineeringPersistent StorageMulti-Agent SystemsEvals
Prime Agent
Autonomous AI research agent
An autonomous agent for conducting and scaling AI research experiments, including NanoGPT experiments.
Recent stories
2 linked stories
newsPRIMARY2026-08-25
Prime Intellect publishes Prime Agent report with 7-day Factorio evaluation
Prime Intellect’s report describes a self-improving long-horizon agent harness with persistent memory, skills, prompts, and subagent specifications. Its Factorio evaluation ran for seven days using 23.4 million output tokens across 633 trajectories.
newsPRIMARY2026-08-10
Composio and Ante benchmark coding agent harnesses with 47%–67% success range
Composio and Ante tests reported that the same models behaved very differently by harness. DeepSeek V4 Flash ranged from 47% to 67% task success and $0.019 to $0.104 per task across harnesses.