Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
ConsciousDB is a graph-database-agnostic Agentic GraphRAG framework for developers who want to add an agentic intelligence layer on top of an existing graph database (Neo4j, Memgraph, Apache AGE, Kùzu) without rewriting pipeline logic.
How it uses Jev
Jev (or local Laya) acts as the decision layer across all 19 pipeline steps: it scores edges during ingestion and A* traversal, makes binary judgements for chunking, seed validation, early termination, hallucination gating and citation verification, and selects categories for intent routing, ontology alignment and conflict resolution. Results drive pruning, routing and gating in code.
Primitives:scorenoulchoice
Technique worth stealing
Decoupling the AI decision layer from storage and generation, using System One primitives (Score/Noul/Choice) instead of generative LLM calls at every hop.
Try it
Set DECISION_MODEL_BACKEND=jev and GRAPH_DB_BACKEND=neo4j (or others) in .env; see README for full setup.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.05
- Shows a System One patternnot found in the excerpt0.16
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalnot found in the excerpt0.10
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.17 / 2
- About JevFound in material0.88
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 3 Nov 2026.