Decision Workspace
agentvis vs agent-session vs agent-harness
Side-by-side comparison of Rust crates
53
agentvis
experimentalv1.0.34
Standalone repository-evolution visualizations for local AI-agent sessions.
65
agent-session
experimentalv0.5.17
Portable session IR, parsers, discovery, and process matching for local AI coding-agent transcripts.
46
agent-harness
experimentalv0.5.3
Drive LLM coding agents — Claude Code, OpenAI Codex, and local Ollama / OpenAI-compatible models — from Rust behind one trait, with a normalized streaming event vocabulary. Bring your own agent too.
Core Metrics
| agentvis | agent-session | agent-harness | |
|---|---|---|---|
| Health Score | 53 | 65 | 46 |
| Total Downloads | 1.5K | 7.0K | 512 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 40 | 246 | 0 |
| Releases | 43 | 79 | 19 |
| Last Updated | 5d ago | 5d ago | 34d ago |
| Age | 2m | 3m | 4m |
Health Breakdown
agentvis
Maintenance
13
Quality
14
Community
10
Popularity
4
Documentation
12
agent-session
Maintenance
19
Quality
13
Community
13
Popularity
5
Documentation
15
agent-harness
Maintenance
17
Quality
8
Community
6
Popularity
3
Documentation
12
Technical Details
| agentvis | agent-session | agent-harness | |
|---|---|---|---|
| Version | 1.0.34 | 0.5.17 | 0.5.3 |
| Stable (≥1.0) | ✓ Yes | ✗ No | ✗ No |
| License | MIT | MIT | MIT OR Apache-2.0 |
| Dependencies | 10 | 7 | 17 |
| Crate Size | 295KB | 56KB | 305KB |
| Features | 0 | 0 | 6 |
| Yanked % | 0.0% | 0.0% | 26.3% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | 1.87 | 1.87 | 1.74 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •agent-session leads with a health score of 65/100, but none of the options score above 80.
- •agent-session is depended on by 246 crates — strongest ecosystem trust.
- •agent-session, agent-harness are pre-1.0 — API may change.