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.
Quick read
Latest capture 2026-08-07 03:03
1 path
Agent instructions and tool configuration found in this repository.
Agent instructions
2 observed captures since 2026-07-17. Observed captures are shown by default.
Stars from first capture +391
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Collection of evals for Inspect AI
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Cut the chatter. Keep the work. A measured communication policy for coding agents: −32% output tokens, zero lost facts.
