GitHub Repository

LLM CLI wrapper that stores important input/outputs in an ontology styled system to build relationships between objects and have infinite memory across sessions and collaborators.

2 starsPython

One, cross domain auto-researching knowledge graph Claude orchestrator

Name: One, cross domain auto-researching knowledge graph Claude orchestrator
Availability: InStock
Author: railugo

by railugo·Mar 17, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainBold BetWizardry

Dialectic thesis-antithesis-synthesis research loop is novel but clearly alpha software.

Strengths

•Hyperdimensional Computing embeddings (4096-dim) is non-obvious technical choice vs standard transformers
•Zero Hallucination Engine AST-parses code and validates against live database schemas
•Autonomous research with contradiction mining and cross-domain pattern synthesis is ambitious

Weaknesses

•Alpha state with 0 stars and experimental features means not production-ready today
•Extremely ambitious scope risks becoming unfocused or unmaintainable over time

Post Description

hi, so straight to the point. i had claude code $20 for a while, and before upgrading i was always thinking about a way to make an "infinite context system", i also work... A LOT. 22hrs a day or so?

so i worked around, did a lot of trying with mcp, plugins, and i stuck with a system i call "one".

hdc vector embeddings (4096 dimensions, trigram + word encoding) stored in SQLite and recalled by cosine similarity on context shifts.

entity extraction builds a knowledge graph across sessions. rules get learned from repeated preferences. thats the core

the part that scared me was the autonomous research loop. there's a mode where claude researches a topic, then a dialectic engine challenges every finding. thesis/antithesis/synthesis.

a contradiction minor looks for conflicts, and a synthesis engine searches for patterns across domains. weak findings get pruned and it can iterate indefinitely.

it was running on my 15m kalshi trading algorithm (which also happens to use hdc + tsetlin machines haha!) and it produced 420 research findings (lol) with cited acedemic sources, it mined 472 contradictions, deprecated almost 600 weak claims through adversarial challenge, and discovered 21 patterns across domains i never directed it to explore.

the system connected python's lazy import pattern to rna transcription, both are deffered materialization where dormant capabilties are suppresed until activation context arrives.

it formalized why certain bug classes are invisible to quality checks, the query is outside the space where results exist, not bad results.

also has a small verification engine that ast-parses every code exit, checks sql against live schema, and maps every function call and file dependency in the codebase.

test it out,talk to me, ask things! it's my first time making a repository public!

(currently using the system on the system as im typing this out to make sure it autonomously upgrades itself before i go to sleep and you guys think my project sucks)