Harbor turns one: 200T tokens/week, 10M+ Terminal-Bench runs, 1B+ rollouts
BenBlaiszik · x · 2026-11-08
The open-source agent execution framework Harbor marks its first anniversary with striking scale numbers: 1B+ rollouts, currently processing 200T tokens per week (double the September figure of 100T), and Terminal-Bench appearing on 64 model cards as the most-cited benchmark at model launches with 10M+ runs. Ecosystem stats include 7.3M PyPI downloads in 30 days, 550 contributors, 3,300+ merged PRs, 12k GitHub stars and a 5k-member Discord. Roadmap: tb2.1 shipped, with tb-science, tb3, tb4 and harbor v1 on the way.
More from coding & agent
- Perplexity CEO explains why Teammates beats rival agents: harness, model-neutral, search — AravSrinivas · 2026-11-08
- Indie Founder Launches Colabli, an MCP Gateway with Persistent Business Memory — Fragrant_Match1599 · 2026-11-08
- Idea renders Hollywood-grade 3D animation from your AI chat, starting at $15/mo — wordgrammer · 2026-11-08
- IRC or email? Two devs debate the right UI metaphor for talking to coding agents — yacineMTB · 2026-11-08
- Awesoft tests idiotproof: Opus now drives video workflow end-to-end — wordgrammer · 2026-11-08
- 5 ways to measure the ROI of AI agents, from time saved to overall return — goyalshaliniuk · 2026-11-08