{"name":"bootloops","repo":"BootLoops-ai/bootloops","url":"https://midorreal.com/project/bootloops-ai-bootloops","repository":"https://github.com/BootLoops-ai/bootloops","description":"BootLoops 1.0: certified computational tools and house engines for exact and high-precision physics and quantitative science, built to be driven by LLM agents. MIT; docs CC BY 4.0.","facts":{"license":{"value":"MIT","source":"https://github.com/BootLoops-ai/bootloops","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/BootLoops-ai/bootloops","checked":"22 Nov 2026"},"last_release":{"value":"v1.0, 5 Oct 2026","source":"https://github.com/BootLoops-ai/bootloops/releases","checked":"22 Nov 2026"},"releases":{"value":"1","source":"https://github.com/BootLoops-ai/bootloops/releases","checked":"21 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/BootLoops-ai/bootloops/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/BootLoops-ai/bootloops","checked":"22 Nov 2026"}},"stars":448.0,"writeup":{"what_it_is":"BootLoops 1.0 is a harness of scientific software packages for precision quantitative science, designed to be driven by LLM agents. It includes tools for exact and high-precision integrals, recurrences, Bayesian evidence integrals, certified error bounds, and exhaustive enumeration, along with plain-markdown protocols for checking results.","audience":"Researchers in physics and quantitative science using LLM agents for precision computation","claims":[{"kind":"specific","claim":"Provides tools for multi-dimensional parametric integrals evaluated in closed form or to hundreds of certified digits","excerpt":"closed form or to hundreds of certified digits","status":"not_checked"},{"kind":"specific","claim":"Carries proven error radii through every computation step","excerpt":"every value carries\n  a proven error radius through every step","status":"not_checked"},{"kind":"specific","claim":"Ships a validation command that runs the package batteries on a fresh clone","excerpt":"python3 run_selftests.py --par 8","status":"not_checked"},{"kind":"specific","claim":"Tested on Linux x86_64 and arm64 containers with Python 3.12 and Julia 1.11","excerpt":"the full validation run passes in a fresh minimal\n  container on both architectures","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-26"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":13,"reality":9,"gap":4,"momentum":0.1,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-05T14:16:54+00:00","text":"Latest release v1.0","source":"https://github.com/BootLoops-ai/bootloops/releases"},{"date":"2026-10-01T15:29:28+00:00","text":"Repository created","source":"https://github.com/BootLoops-ai/bootloops"}],"cite":"bootloops is a GitHub project at https://github.com/BootLoops-ai/bootloops written mainly in Python, described there as \"BootLoops 1.0: certified computational tools and house engines for exact and high-precision physics and quantitative science, built to be driven by LLM agents. MIT; docs CC BY 4.0\".","attribution":"Data from Mid or Real, https://midorreal.com/project/bootloops-ai-bootloops, checked 22 November 2026. Attribution with a link is required.","still_real":null}