AI2 Open Coding Agents
Shares rank 35 of 41 coding agents by recommenders
Recommended as an open coding agent with its training pipeline available and reproducible for about $400; critics say only part of the training data is open.
Recommended as an open coding agent with its training pipeline available and reproducible for about $400; critics say only part of the training data is open.
10 people gave an opinion
- recommend it
- 8
- criticize it
- 2
- approval share
- 80%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 4 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 1 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
Open training pipeline and data
“having the complete training pipeline and data accessible enables the kind of iterative improvements”
Comment from 28 Jan 2026 in “AI2: Open Coding Agents” “The premise of truly open source models is really interesting”
Comment from 27 Jan 2026 in “AI2: Open Coding Agents” “they open source everything”
Comment from 27 Jan 2026 in “AI2: Open Coding Agents”
Other coding agents people recommend
The four most recommended other coding agents, 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.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GitHub Copilot | 571 | 993 | 37% | 12 | 1 yr46 owners | — |
| oh-my-pi | 104 | 28 | 79% | 9 | 2 mo5 owners | Approved |
| Grok Build CLI | 66 | 114 | 37% | 6 | — | — |
| DeepSeek Harness | 63 | 28 | 69% | 4 | 1 mo5 owners | Approved |
| AI2 Open Coding AgentsThis page | 8 | 2 | 80% | 1 | — | — |
What people said
All 10 comments that mention it, newest first. Each links to the original comment.
“So this "open" system still requires you to use Claude to actually use it?”
“if you need local processing, without access to SotA (security, compliance, whatever) then this is an interesting avenue for you”
“having the complete training pipeline and data accessible enables the kind of iterative improvements”
“I think this approach is correct, but it does mean that only a subset of the training data is really open.”
“The premise of truly open source models is really interesting”
“they open source everything”
“the interesting number here isn't accuracy. It's the $400 to reproduce top open-source performance”
“this claims to be better and smaller than Devstral-Small-2-24B, while clocking in at 32B (larger) and scoring more poorly?”
“Claims in the article are incorrect. They conveniently ignore Meta CWM models”
“Output speed looks crazy fast too.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.