Hacker ApprovedDepartments

HAL (hal.science)

Shares rank 5 of 6 academic paper archives by recommenders

Free open archive for research papers, used especially in mathematics and well integrated with arXiv; critics say it is second-tier to arXiv and dredge is a problem.

Free open archive for research papers, used especially in mathematics and well integrated with arXiv; critics say it is second-tier to arXiv and dredge is a problem.

8 people gave an opinion

recommend it
7
criticize it
1
approval share
88%
Each figure is one person. RecommendsCriticizes

Recommended in 3 of 13 months

  1. November 2025: not recommended
  2. December 2025: not recommended
  3. January 2026: not recommended
  4. February 2026: not recommended
  5. March 2026: recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: not recommended
  9. July 2026: recommended
  10. August 2026: not recommended
  11. September 2026: not recommended
  12. October 2026: recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 7 people recommend itNeeds 10 or more, not met.
  • 7 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 3 of 13 monthsNeeds 4 or more, not met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Simple, low-friction, lightweight

    “HAL is enough and way less friction”

    Comment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

    “I like how simple and lite it is.”

    Comment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”
  • Blocks destructive commands via shared rules

    “It sits in the hook, checks every command against a set of rules, and blocks the destructive ones.”

    Comment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

    “Plus, this enables shared rules across our company’s engineers/teams”

    Comment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

What people warn about

Each mark is one comment

  • Dredge is a huge problem

    “dredge is a huge problem with HAL, but it's getting better”

    Comment from 20 Mar 2026 in “ArXiv Declares Independence from Cornell”

Other academic paper archives people recommend

The four most recommended other academic paper archives, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

HAL (hal.science) compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
arXiv833869%11—Approved
Sci-Hub17385%9—Approved
Zenodo9282%5——
ACM Digital Library91735%4——
HAL (hal.science)This page7188%3——
See all 6 academic paper archives, ranked

What people said

9 of the 10 comments that mention it, newest first. Each links to the original comment.

“there are plenty of good articles there”

RecommendsComment from 1 Jul 2026 in “ArXiv's Next Chapter”

“quite well integrated with arxiv”

RecommendsComment from 28 Mar 2026 in “CERN to host Europe's flagship open access publishing platform”

“dredge is a huge problem with HAL, but it's getting better”

MixedComment from 20 Mar 2026 in “ArXiv Declares Independence from Cornell”

“HAL is decidedly second-tier. Given the option, everyone would pick arXiv over HAL.”

CriticizesComment from 20 Mar 2026 in “ArXiv Declares Independence from Cornell”

“It is actually quite common to come across HAL in subfields of mathematics in my experience.”

RecommendsComment from 20 Mar 2026 in “ArXiv Declares Independence from Cornell”

“HAL is enough and way less friction”

RecommendsComment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

“I like how simple and lite it is.”

RecommendsComment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

“Plus, this enables shared rules across our company’s engineers/teams”

RecommendsComment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

“It sits in the hook, checks every command against a set of rules, and blocks the destructive ones.”

RecommendsComment from 13 Mar 2026 in “HAL – Harmful Action Limiter: Lean command guard for AI coding agents.”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.