Terminal coding agent
- Price
- $17/mo billed yearly · $20 monthly
- License
- Proprietary
- Stars
- 156k
- Shipped
- 1d ago

Terminal coding agent
In the maker’s words: 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%.
github.com ↗

Not yet verified. An open-source license does not tell us what a hosted plan costs, so we do not infer one.
Counts cover stable published GitHub releases. Charts show days with at least one stable product release, so multiple releases in one day count once. Prereleases, declared nightlies and timestamped or commit-artifact builds are counted separately. Drafts and bare tags are excluded. Monorepo counts cover the verified product stream, excluding SDKs, infrastructure and sibling packages. All windows end at the recorded release snapshot. Release methodology. Collected 18 Nov 2026. Release evidence
Release days per week, last 26 weeks
A score needs at least one Hacker News mention in the last 90 days. Tura has none yet, so it has no score and no rank. Upvotes still show their real count.
668 GitHub stars, read 18 Nov 2026.
Fewer than 10 votes. Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
A sample of threads found during research: issues and discussions, not a measure of satisfaction.
Build agent that uses 80% less token and delivers better results.api.github.com ↗ · read 18 Nov 2026
Tura is an open-source agent runtime harness that delivers better results with fewer tokens.github.com ↗ · read 18 Nov 2026
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 a…github.com ↗ · read 18 Nov 2026
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 verifi…github.com ↗ · read 18 Nov 2026
Global install (macOS, Linux, and Windows):github.com ↗ · read 18 Nov 2026
every configured provider. Broader Anthropic/Claude, Google/Gemini,github.com ↗ · read 18 Nov 2026
OpenAI-compatible, local-provider, UI-latency, runtime/session parsing, andgithub.com ↗ · read 18 Nov 2026
[Bug]: "MANO failed while processing this prompt"api.github.com ↗ · read 18 Nov 2026
npm 12 blocks tura-ai postinstall and leaves the CLI unregisteredapi.github.com ↗ · read 18 Nov 2026
| `tura` | Interactive terminal UI. |raw.githubusercontent.com ↗ · read 18 Nov 2026
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%.github.com ↗ · read 18 Nov 2026
668api.github.com ↗ · read 18 Nov 2026
From the API response. No sentence to quote.api.github.com ↗ · read 18 Nov 2026
From the API response. No sentence to quote.api.github.com ↗ · read 18 Nov 2026
From the API response. No sentence to quote.api.github.com ↗ · read 18 Nov 2026
From the API response. No sentence to quote.github.com ↗ · read 18 Nov 2026
Ordered by Index score.
Terminal coding agent
Terminal coding agent
Terminal coding agent
Terminal coding agent
A coding agent with the IDE wired in.
Terminal coding agent
Terminal coding agent
Terminal coding agent