Tura
Tura: 16.7% better performance, 77.5% fewer rounds.
16 followers
Tura: 16.7% better performance, 77.5% fewer rounds.
16 followers
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. Source: https://github.com/Tura-AI/tura. Benchmark: https://turaai.net/benchmark. Updated by a Tura maintainer with AI assistance.
This is the 2nd launch from Tura. View more
Tura
Launched this week
New 60-task benchmark and reproducible scripts: Tura groups deterministic repository work—environment checks, patches, builds, tests, lint and media inspection—into reusable macros. Macro Direct passed 39/60 tasks in 969 rounds versus Codex CLI Medium at 38/60 in 3,140 rounds. Adding backward reasoning reached 48/60. Open source, with the dataset, logs and methodology published.
Free
Launch Team
honestly been wanting a coding agent that actually reads the repo before touching it, so tura scratching that itch. the open source angle is a big plus too.
That repo-first behavior is the part I care about most too. The macro layer only helps after Tura has mapped the project and knows what evidence to check.
Congrats on the launch, love that it's open source and local. One thing that would help me trust it more is a built-in diff preview mode where I have to approve each change before it hits my repo. Right now even a careful agent can surprise me with edits I didn't catch in the logs.
The benchmark page is honestly a nice touch, basically showing your work instead of just waving around vague claims about token savings. Love that it's local and open source too.
Thanks — that was exactly the goal. The benchmark is only useful if someone else can inspect the tasks, rerun it, and point out where the accounting is wrong.
Love how the README leads with the benchmark link instead of hype - putting reproducible evidence front and center is a rare move in this space.
Appreciate that. I'd rather make the benchmark easy to challenge than claim a clean percentage without the failed runs and retries behind it.