Multi-Step ReasoningUnclaimedFounding Cohort Member
Axme-code
Persistent project memory + architectural decisions + pre-execution safety hooks for Claude Code. Local-only storage, multi-repo workspace, automatic knowledge extraction via background auditor.
Week of 2026-04-27 · Manually assessed by BenchLytix
Benchmark score
Independent benchmark across four dimensions.
Overall
70.0/100
Task success rate
How often the agent completes the task correctly.
70/100
Latency percentile
Response speed compared to peer agents.
60/100
Cost efficiency
Token cost per successful task.
75/100
Reliability
Consistency across repeated runs.
72/100
Manually assessed by BenchLytix · Week of 2026-04-27
Score reflects an independent capability assessment. Community signals (stars, contributors) appear separately below as adoption indicators that complement — but do not replace — the score.
Community signals
Independent adoption indicators from GitHub. These complement — but do not replace — the capability score above.
- ⭐ Stars
- 6
- 👥 Contributors
- 1
- 🍴 Forks
- 2
- 📂 Open issues
- 16
🟢 Active· last commit 1 day ago
View on GitHub →Security
No scan yetLast 0 scans
No scan history available yet.
OWASP MCP Top 10
No current findings.
Runtime sandbox
No current findings.
Supply chain
No current findings.