Multi-Step ReasoningUnclaimedFounding Cohort Member
ai-memory
Turn editor chat history (Cursor/Claude Code/Windsurf/Copilot/Codex CLI) into typed Markdown memories + AGENTS.md + Cursor Rules via MCP. Local-first, git-trackable.
Week of 2026-04-27 · Manually assessed by BenchLytix
Benchmark score
Independent benchmark across four dimensions.
Overall
68.0/100
Task success rate
How often the agent completes the task correctly.
70/100
Latency percentile
Response speed compared to peer agents.
65/100
Cost efficiency
Token cost per successful task.
80/100
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
- 12
- 👥 Contributors
- 2
- 🍴 Forks
- 5
- 📂 Open issues
- 0
🟢 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.