AI agent
tura
Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.
- Rank
- #22 of 2,536
- Stars
- 102★ +77/wk
- On radar
- since 2026-07-16
Momentum
rate of rise, not size · recomputes hourly
73.1
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
tura is an AI agent ranked #22 of 2,536 on the Cresting momentum radar, with a score of 73.1. It has 102 GitHub stars, +77 in the last 7 days, and has been tracked since 2026-07-16.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.940 |
| Recency boost | 0.465 |
| Signal decay | 0.990 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+8 in window · 9 latest · 2 snapshots
github · stars+77 in window · 102 latest · 2 snapshots
Related ai agents
- skillsOpen-source OpenAI Codex theming Skill, AI theme generator, and cross-platform runtime for custom Codex desktop themes.#2 · 159★
- clodex-ideLocal-first, zero-trust agentic IDE for verifiable autonomous software development.#3 · 830★
- blitzosBlitzOS — Claude/Codex Cloud VMs that boot knowing your whole codebase#4 · 122★
- WorkBuddyGuideA practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书：教程、真实工作流、Skills、MCP、自动化与多智能体实践。#6 · 1,017★
- deja-vuMemory layer for coding agents: search, MCP recall, auto-context, secret redaction, stats, share and sync over the session logs Claude Code, Codex and opencode already write. One zero-dep binary.#7 · 313★