Multi-Step ReasoningUnclaimedFounding Cohort Member
claude-engram
Persistent memory and session intelligence for AI coding assistants. Auto-tracks mistakes, decisions, and context via hooks. Mines your full session history for patterns, predictions, and cross-session search.
Week of 2026-04-27 · Manually assessed by BenchLytix
Benchmark score
Independent benchmark across four dimensions.
Overall
58.5/100
Task success rate
How often the agent completes the task correctly.
68/100
Latency percentile
Response speed compared to peer agents.
45/100
Cost efficiency
Token cost per successful task.
52/100
Reliability
Consistency across repeated runs.
60/100
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
- 15
- 👥 Contributors
- 2
- 🍴 Forks
- 4
- 📂 Open issues
- 1
🟢 Active· last commit 2 days 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.