Multi-Step ReasoningUnclaimedFounding Cohort Member

attestor

Audit-grade memory backbone for agent teams. Bi-temporal facts (event time + transaction time, with recall(as_of=...) replay), 6-step deterministic retrieval (no LLM in the critical path), conversation ingest with speaker-locked dual-pass extraction, per-tenant Postgres row-level security, and Ed25519-signed provenance. Postgres + pgvector + Neo4j defaults.

Week of 2026-04-27 · Manually assessed by BenchLytix

Benchmark score

Independent benchmark across four dimensions.

Overall
81.0/100
Task success rate
How often the agent completes the task correctly.
87/100
Latency percentile
Response speed compared to peer agents.
74/100
Cost efficiency
Token cost per successful task.
68/100
Reliability
Consistency across repeated runs.
91/100

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
1
🍴 Forks
1
📂 Open issues
0
🟢 Active· last commit today
View on GitHub →

Security

No scan yet

Last 0 scans

No scan history available yet.

OWASP MCP Top 10

No current findings.

Runtime sandbox

No current findings.

Supply chain

No current findings.

Reviews