Decision Workspace
llm-json-extract vs llm-repair vs llm-extract
Side-by-side comparison of Rust crates
39
llm-json-extract
experimentalv0.1.0
Extract valid JSON from messy LLM outputs. Handles reasoning blocks, markdown fences, truncated payloads, and broken syntax. Battle-tested against 15+ models.
54
llm-repair
experimentalv0.7.1
JSON-repair, markdown-extraction, and tool-call recovery helpers for malformed LLM output
53
llm-extract
experimentalv0.2.0
Extract structured data from LLM responses — fence strip, JSON repair, fuzzy repair, typed deserialization
Core Metrics
| llm-json-extract | llm-repair | llm-extract | |
|---|---|---|---|
| Health Score | 39 | 54 | 53 |
| Total Downloads | 26 | 752 | 1.9K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 26 | 56 |
| Releases | 1 | 27 | 2 |
| Last Updated | 102d ago | 56d ago | 38d ago |
| Age | 3m | 4m | 6m |
Health Breakdown
llm-json-extract
Maintenance
8
Quality
13
Community
6
Popularity
2
Documentation
10
llm-repair
Maintenance
16
Quality
13
Community
10
Popularity
3
Documentation
12
llm-extract
Maintenance
15
Quality
13
Community
11
Popularity
4
Documentation
10
Technical Details
| llm-json-extract | llm-repair | llm-extract | |
|---|---|---|---|
| Version | 0.1.0 | 0.7.1 | 0.2.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | Apache-2.0 OR MIT | MIT OR Apache-2.0 |
| Dependencies | 4 | 7 | 7 |
| Crate Size | 16KB | 53KB | 21KB |
| Features | 0 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2024 | 2021 |
| MSRV | — | 1.85 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •llm-repair leads with a health score of 54/100, but none of the options score above 80.
- •llm-extract has the most downloads (1.9K), suggesting wider adoption.