Show HN: Sigma Guard – 그래프 메모리에 대한 결정론적 모순 검사

hackernews | | 📰 뉴스
#claude #오픈소스
원문 출처: hackernews · Genesis Park에서 요약 및 분석

요약

저는 그래프 기반 AI 메모리와 GraphRAG 스타일 시스템을 위한 작은 오픈 소스 검증 도구를 구축했습니다.<p>기본적인 문제: 그래프 데이터베이스는 스키마를 검증할 수 있지만 일반적으로 허용되는 두 사실이 서로 모순되는지 여부를 알지 못합니다. AI 메모리 레이어는 "Acme는 연간 청구를 선호합니다"와 "Acme는 연간 청구를 선호합니다"라는 두 가지를 모두 저장할 수 있습니다. 및 "Acme는 연간 청구를 거부하고 월별 청구를 요구합니다." 두 쓰기가 모두 유효할 수 있습니다. 모순은 나중에 상담원이 두 가지를 모두 검색하고 그 이유를 설명할 때만 나타납니다.</p><p>

본문

I built a small open-source verifier for graph-backed AI memory and GraphRAG-style systems.<p>The basic problem: graph databases can validate schema, but they usually do not know whether two accepted facts contradict each other. An AI memory layer can store both &quot;Acme prefers annual billing&quot; and &quot;Acme rejected annual billing and requires monthly billing.&quot; Both writes may be valid. The contradiction only shows up later when an agent retrieves both and reasons over them.</p><p>SIGMA Guard tries to catch that earlier.</p><p>It represents claims as a graph with local consistency rules and checks whether the proposed structure can be made globally consistent. The underlying mechanism uses cellular sheaf cohomology. The practical interface is simpler: given claims, a graph, or a proposed write, it returns SAFE or UNSAFE with the contradiction details and a receipt hash.</p><p>The repo includes:</p><p>verify_claims - check a set of subject&#x2F;property&#x2F;value claims
check_write - test a proposed graph write before commit
verify_graph - verify a full graph
MCP server support for Claude Desktop &#x2F; agent workflows
a local demo, no API key required</p><p>Install:</p><p>pip install sigma-guard[mcp]</p><p>Run MCP server:</p><p>sigma-guard-mcp</p><p>Or run the local demo:</p><p>git clone <a href="https:&#x2F;&#x2F;github.com&#x2F;Jasonleonardvolk&#x2F;sigma-guard" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Jasonleonardvolk&#x2F;sigma-guard</a>
cd sigma-guard
pip install -e .
python examples&#x2F;verify_llm_output.py</p><p>I also ran a scale experiment because the obvious objection is that sheaf-style graph verification will not fit in memory. On a laptop, the current cellular implementation completed a 5M-vertex &#x2F; 39,999,936-edge streaming run. The key trick was avoiding duplicated restriction matrices: 80M endpoint maps were represented by 1,024 canonical maps in a shared store. The streaming update path averaged 0.119 ms&#x2F;edit with p99 1.534 ms in that run.</p><p>Separate from the streaming benchmark, I also ran a &quot;poisoned edge&quot; demo on the same 5M graph. One local restriction map was replaced with a cyclic permutation. Exact local verification recomputed one affected cell out of 25,473. H0 dropped from 8 to 1, meaning 7 local consistency modes were destroyed. That exact check took 11.5s because it used dense SVD on the affected cell; the point of that demo was localization and exactness, not production latency.</p><p>Limitations:</p><p>This is not a replacement for a graph database.
It does not make LLM output true.
The current exact poisoned-edge demo is slower than the streaming update path.
Some demos use structured claims rather than arbitrary natural language.
The interesting question is whether this belongs as a pre-commit &#x2F; pre-output verifier for agent memory, not as a standalone database.</p><p>Repo:</p><p><a href="https:&#x2F;&#x2F;github.com&#x2F;Jasonleonardvolk&#x2F;sigma-guard" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Jasonleonardvolk&#x2F;sigma-guard</a></p><p>I would be interested in feedback from people working on graph databases, GraphRAG, or agent memory. Does a deterministic &quot;verify before memory write &#x2F; before agent output&quot; layer make sense in your stack?</p>

Genesis Park 편집팀이 AI를 활용하여 작성한 분석입니다. 원문은 출처 링크를 통해 확인할 수 있습니다.

공유

관련 저널 읽기

전체 보기 →