Tura

English | 简体中文

Tura: 16.7% better performance, 77.5% fewer tokens.

Tura is an open-source agent runtime harness that delivers better results with fewer tokens.

In a ReAct session, the model must re-enter after every tool result, repeatedly carrying the system prompt and a growing context. Tura turns the same task into one runtime-managed command graph, so deterministic execution continues without another model round trip.

Tura executes in one turn the same workflow that a ReAct architecture needs five turns to complete.

Across 20 DeepSWE v1.1 tasks, each run three times per agent, Tura creates a substantial token-budget advantage by reducing repeated context and model round trips. You can spend that advantage in two ways. Direct turns most of it into lower cost: 77.5% fewer aggregate tokens than Codex CLI, with a comparable verifier success rate of 65.0% versus 63.3%. Balanced puts more of the saved budget back into reasoning, investigation, and verification. It reached an 80.0% success rate: 16.7 percentage points higher than Codex CLI: while still using 31.1% fewer tokens.[^debug-figure][^debug-manifests]

Benchmark

Long-horizon task benchmarks are one way to look past a polished isolated prompt and see how an agent handles real work. The published comparison uses harness-based development tasks with archived prompts, per-round tool calls, token usage, patches, and verifier results.

The published artifacts compare the named Tura Balanced, Tura Direct, and Codex CLI configurations on 20 DeepSWE tasks, 5 rewrite tasks, and 2 separately reviewed design tasks. [^debug-figure]. current test-set record. [^test-set-record]

The published results do not establish equivalent quality or performance for every configured provider. Broader Anthropic/Claude, Google/Gemini, OpenAI-compatible, local-provider, UI-latency, runtime/session parsing, and cross-OS measurements remain part of the documented roadmap and known evidence gaps.

FULL BENCHMARK REPORT

Harness success and aggregate token usage across 25 high-difficulty tasks, 6 agent-and-model configurations, and 270 sessions. Source and calculation notes are linked below.

Screenshots

GUI page with multi-session concurrent work and HTML rich text support.

TUI page with multi-session concurrent work and HTML rich text support.

The results below come from published benchmark artifacts, not an uncited aggregate. Three systems do most of the work:

Macro CLI Command Run

Most coding agents still depend on repetitive tool-calling loops: inspect, wait, patch, wait, build, wait, test, wait.

Tool-calling coding agent:

# Turn 1 :  inspect environment

rg -n "TODO|command_run|handler" crates/
rg --files crates/runtime/src crates/tools/src

# Turn 2 :  apply patch

*** Begin Patch
*** Update File: crates/tools/src/command_run/handler.rs
@@
-    // old command handler logic
+    // patched command handler logic
*** End Patch

# Turn 3 :  build

cargo build -p runtime

# Turn 4 :  run tests

cargo test -p runtime --lib

# Turn 5 :  run lint validation

cargo clippy -p runtime --all-targets