Tura
Tura: 16.7% better performance, 77.5% fewer rounds.
Tura is a local, open-source coding agent for developers who are tired of vague skill claims, token-saving extensions with no evidence, and agents that change a repository before understanding it.
Across 20 DeepSWE v1.1 tasks, each run three times per agent, Tura Balanced reached an 80.0% verifier success rate—16.7 percentage points higher than Codex CLI—while using 31.1% fewer tokens. Tura Direct used 77.5% fewer aggregate tokens than Codex CLI, with a comparable verifier success rate of 65.0% versus 63.3%.
Tura reduces repeated context and model round trips through its macro command_run workflow, and guides the model through backward reasoning before repository changes. It includes a Rust-powered TUI and a cross-platform desktop GUI for macOS, Windows and Linux.
Source: https://github.com/Tura-AI/tura
Benchmark: https://turaai.net/benchmark
Website: https://turaai.net/
Submitted by a Tura maintainer. This submission was prepared with AI assistance and reviewed by the maintainer.
Supporters
Related ships
Runsight
Git-native YAML engine to ship reliable, cost-tracked AI agents in minutes
OpenClawHub
Discover, Compare, and Choose the Best AI Agent Tools

YYLO
Orchestrate coding agents with durable memory and validated results

CSV to JSON
CSV to JSON

SkillDirs
The fastest way to find ready-to-use AI skills & agent workflows
Octopoda
Never lose a thought—give your AI agents bulletproof memory, loops & crash recovery.
Comments