Do coding agents recommend GDELT?
GDELT was chosen in 2% of 591 judged AI search sessions, ranking number 14. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
GDELT was chosen in 2% of 591 judged AI search sessions, ranking number 14. It was also raised as a candidate in 86 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about GDELT. What an agent actually installed.
The numbers
| Category | AI search |
| Sessions in the category | 591 |
| Sessions where GDELT was chosen | 9 |
| Install share | 2% |
| Rank in category | 14 of 42 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 86 |
| Chosen when considered | 9% |
| Site | gdeltproject.org |
By agent
With 9 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.
| Agent | Sessions | Chose GDELT | Share |
|---|---|---|---|
| Claude Code | 140 | 0 | 0% |
| Codex | 144 | 1 | 1% |
| Cursor | 136 | 2 | 1% |
| Grok Build CLI | 35 | 0 | 0% |
| Muse Code | 136 | 6 | 4% |
By who was asking
GDELT performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 22 of the 29 categories we measured.
| Who is asking | Sessions | Chose GDELT | Share |
|---|---|---|---|
| Vibe coder | 98 | 0 | 0% |
| Junior developer | 196 | 0 | 0% |
| Senior engineer | 145 | 2 | 1% |
| Enterprise team | 152 | 7 | 5% |
What GDELT was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Anthropic web search | 86 | 15% |
| 2 | Brave Search API | 83 | 14% |
| 3 | Exa | 75 | 13% |
| 4 | Tavily | 73 | 12% |
| 5 | Built in-house (no product adopted) | 32 | 5% |
| 6 | OpenAI web search | 29 | 5% |
| 7 | Perplexity Sonar | 26 | 4% |
| 8 | Firecrawl | 25 | 4% |
What this means
This is an integration problem, not a presence problem. Agents raised GDELT in 86 sessions and chose it in 9, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 591 sessions in AI search are part of a published set of 13,497, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every AI search run can be replayed on the board.
If you work on GDELT: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend GDELT?
Yes. GDELT was chosen in 9 of the 591 judged sessions in AI search, a 2% install share, ranking number 14 in its category.
Does Claude Code recommend GDELT?
In 0 of the 140 sessions in AI search run with Claude Code, which is 0%.
Do different coding agents treat GDELT differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 4% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is GDELT considered but not chosen?
It was raised as a candidate in 86 sessions without being chosen, and chosen in 9. That is a 9% conversion from considered to chosen.
Where this comes from
Armature ran 13,497 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.