Decision Workspace
agentron vs agentic-eval vs tokenburn-core
Side-by-side comparison of Rust crates
42
agentron
experimentalv0.1.0
Agentron (Ag): a unit of agentic work volume — Ag = hours × Mtokens.
58
agentic-eval
experimentalv0.14.4
Evaluate programs, CLI commands, programming languages, AI frameworks, and VM/sandbox systems for agentic AI use across four axes — token efficiency, determinism, reliability, and safety — under popular tokenizers (OpenAI GPT-4/GPT-4o, Anthropic Claude). Includes a CLI effect classifier, curated language/framework/VM profiles, and a self-describing ontology.
56
tokenburn-core
experimentalv0.2.1
Shared core logic for TokenBurn — log collectors, aggregation and reports for pi, Zed, Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode and Amp
Core Metrics
| agentron | agentic-eval | tokenburn-core | |
|---|---|---|---|
| Health Score | 42 | 58 | 56 |
| Total Downloads | 18 | 130 | 132 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 32 | 28 |
| Releases | 1 | 3 | 7 |
| Last Updated | 66d ago | 72d ago | today |
| Age | 2m | 3m | 3d |
Health Breakdown
agentron
Maintenance
9
Quality
15
Community
6
Popularity
2
Documentation
10
agentic-eval
Maintenance
15
Quality
15
Community
10
Popularity
3
Documentation
15
tokenburn-core
Maintenance
19
Quality
12
Community
10
Popularity
3
Documentation
12
Technical Details
| agentron | agentic-eval | tokenburn-core | |
|---|---|---|---|
| Version | 0.1.0 | 0.14.4 | 0.2.1 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT | AGPL-3.0-or-later | MIT |
| Dependencies | 0 | 2 | 9 |
| Crate Size | 3KB | 121KB | 73KB |
| Features | 0 | 3 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | — | 1.75 | 1.90 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •agentic-eval leads with a health score of 58/100, but none of the options score above 80.
- •tokenburn-core has the most downloads (132), suggesting wider adoption.