Decision Workspace
ljos vs remem-ai vs kimetsu-chat
Side-by-side comparison of Rust crates
51
ljos
experimentalv0.27.0
Memory, a work tracker and a shell-command gate for coding agents (Claude Code, Codex, Grok Build, agy, opencode) over MCP and hooks.
48
remem-ai
experimentalv0.6.104
Local-first coding agent memory for Claude Code and OpenAI Codex
61
kimetsu-chat
experimentalv2.8.0
Interactive REPL chat client + MCP sidecar + cross-harness bridge for kimetsu. Installs into Claude Code and Codex as a brain-managed memory layer.
Core Metrics
| ljos | remem-ai | kimetsu-chat | |
|---|---|---|---|
| Health Score | 51 | 48 | 61 |
| Total Downloads | 833 | 2.7K | 677 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 28 | 0 | 25 |
| Releases | 61 | 137 | 25 |
| Last Updated | today | 2d ago | 31d ago |
| Age | 26d | 6m | 4m |
Health Breakdown
ljos
Maintenance
16
Quality
10
Community
10
Popularity
3
Documentation
12
remem-ai
Maintenance
19
Quality
9
Community
6
Popularity
4
Documentation
10
kimetsu-chat
Maintenance
17
Quality
16
Community
10
Popularity
3
Documentation
15
Technical Details
| ljos | remem-ai | kimetsu-chat | |
|---|---|---|---|
| Version | 0.27.0 | 0.6.104 | 2.8.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT | MIT | MIT OR Apache-2.0 |
| Dependencies | 16 | 32 | 10 |
| Crate Size | 317KB | 4.8MB | 181KB |
| Features | 0 | 3 | 4 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2024 |
| MSRV | 1.89 | — | 1.85 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •kimetsu-chat leads with a health score of 61/100, but none of the options score above 80.
- •remem-ai has the most downloads (2.7K), suggesting wider adoption.
- •ljos, remem-ai are pre-1.0 — API may change.