Decision Workspace
agentfit vs prompt-token-counter vs token-meter
Side-by-side comparison of Rust crates
45
agentfit
experimentalv0.1.0
Fit messages to an LLM context window. Token-aware truncation with pluggable tokenizers and multiple strategies.
43
prompt-token-counter
experimentalv0.1.0
Approximate token counts for LLM messages, system prompts, and tools. Zero-config chars/4 heuristic, BYO tokenizer, content-block aware (text/image/tool_use/tool_result/document). One serde_json dep.
48
token-meter
experimentalv0.1.1
Cross-provider LLM token metering — Claude, OpenAI and Gemini prompt accounting behind one API, with every count carrying its own provenance
Core Metrics
| agentfit | prompt-token-counter | token-meter | |
|---|---|---|---|
| Health Score | 45 | 43 | 48 |
| Total Downloads | 24 | 20 | 203 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 0 |
| Releases | 1 | 1 | 2 |
| Last Updated | 153d ago | 138d ago | 45d ago |
| Age | 5m | 4m | 1m |
Health Breakdown
agentfit
Maintenance
6
Quality
16
Community
6
Popularity
2
Documentation
15
prompt-token-counter
Maintenance
6
Quality
14
Community
6
Popularity
2
Documentation
15
token-meter
Maintenance
11
Quality
16
Community
6
Popularity
3
Documentation
12
Technical Details
| agentfit | prompt-token-counter | token-meter | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 0.1.1 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | MIT OR Apache-2.0 | Apache-2.0 |
| Dependencies | 3 | 2 | 2 |
| Crate Size | 8KB | 13KB | 57KB |
| Features | 2 | 0 | 2 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.75 | 1.74 | 1.80 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •token-meter leads with a health score of 48/100, but none of the options score above 80.