gbrain
Community-VerifiedPersonal knowledge brain for AI agents. PGLite/Postgres + pgvector, hybrid search (tsvector + embeddings), self-wiring knowledge graph. 30+ MCP tools. Used by gstack. Scored 100% on Bench'd Knowledge Retrieval benchmark — perfect document retrieval, semantic search, knowledge updates, and multi-page reasoning.
Scores from 0–100. Higher is better. LLM Baseline (no memory system) scores 57.6%. How we calculate this →
TrackKnowledge Brain
Track Index
76.8/100
Based on 5 benchmarks.
Benchmark Results
| Benchmark | Score | Status | Receipt |
|---|---|---|---|
| Knowledge Retrieval | 100.0 | Verified | View |
| Knowledge Scale | 100.0 | Verified | View |
| Truth Arbitration | 80.0 | Verified | View |
| Budget Curves | 100.0 | Verified | View |
| Reliability | 4.0 | Verified | View |
| Other Benchmarks | |||
| LongMemEval | Not applicable — outside Knowledge Brain track | ||
| LoCoMo | Not applicable — outside Knowledge Brain track | ||
| Memory Poisoning | Not applicable — outside Knowledge Brain track | ||
Relative Performance vs All Benchmarked Systems
vs 16 scored systemsEach dot is a system. Amber dot is gbrain. Amber line = LLM Baseline (no memory).
Overall100.094th percentile
No memory: 57.6%
Recall100.094th percentile
No memory: 57.6%
Temporal100.094th percentile
No memory: 57.6%
Reasoning100.094th percentile
No memory: 57.6%
Bench'd Memory Index
The BMI combines accuracy (70%) and efficiency (30%) into a single production-weighted score. Formula is public and versioned.
100.0
/ 100
#1 of 8 systemsTop 12%
Accuracy (70%)100.0
Efficiency (30%)--
Per-Capability Score Matrix
| Dimension | Budget Curves | Knowledge Retrieval | Knowledge Scale | LongMemEval | Memory Poisoning | Reliability | Truth Arbitration |
|---|---|---|---|---|---|---|---|
| Recall | -- | -- | -- | 0.0 | -- | -- | -- |
| Temporal | -- | -- | -- | 0.0 | -- | -- | -- |
| Reasoning | -- | -- | -- | 0.0 | -- | -- | -- |
| Hallucination | -- | -- | -- | -- | -- | 0.0 | -- |
| Stale Memory | -- | -- | -- | -- | -- | 0.0 | -- |
| Entity Confusion | -- | -- | -- | -- | -- | 16.7 | -- |
| Deletion | -- | -- | -- | -- | -- | 0.0 | -- |
| Budget 1000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 10000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 2000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 500 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 5000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Conflict resolution | -- | -- | -- | -- | -- | -- | 80.0 |
| Document retrieval | -- | 0.0 | -- | -- | -- | -- | -- |
| Injection resistance | -- | -- | -- | -- | 0.0 | -- | -- |
| Knowledge update | -- | 0.0 | -- | -- | -- | -- | -- |
| Multi page | -- | 0.0 | -- | -- | -- | -- | -- |
| Scale large | -- | -- | 100.0 | -- | -- | -- | -- |
| Scale medium | -- | -- | 100.0 | -- | -- | -- | -- |
| Scale small | -- | -- | 100.0 | -- | -- | -- | -- |
| Semantic search | -- | 0.0 | -- | -- | -- | -- | -- |
| Overall | 100.0 | 0.0 | 100.0 | 0.0 | 0.0 | 4.0 | 80.0 |
Per-Benchmark Breakdown
| Benchmark | Verified | Nuance |
|---|
Performance Over Time — LongMemEval
2026-05-11 to 2026-05-13Most often compared with
Add badge to your README
Show your Bench'd score on your GitHub repo.
Markdown
[](https://benchd.ai/system/gbrain)
HTML
<a href="https://benchd.ai/system/gbrain"><img src="https://img.shields.io/badge/Bench'd_BMI-100.0-D9982B?style=flat" alt="Bench'd Verified: 100.0 BMI" /></a>