Graph Memory

<strong>Bound the context. Keep the memory.</strong><br> A native DeepSeek Harness memory plugin that keeps recent conversation turns, archives older history, and recalls exact source-backed knowledge when it matters.

<a href="README_CN.md">中文</a> · <a href="https://www.dsh.so/artifact/graph-memory">dsh.so</a> · <a href="benchmarks/dsh-context-takeover/README.md">20-turn benchmark</a> · <a href="docs/TURN_MEMORY_NAVIGATION_UPGRADE_CN.md">Upgrade guide</a>

The problem it solves

Graph Memory owns the model-visible historical surface without deleting DSH's event log. By default it keeps the newest five completed user turns, removes completed reasoning/tool traces from future requests, and recalls relevant older or cross-session source Q/A automatically.

The 1.6 turn-memory navigation upgrade

Before	Now
Extract TASK / SKILL / EVENT directly from messages	Create one self-contained turn summary, then derive SPO from that same sentence
Graph nodes could become the factual payload	Summary, SPO, and communities only navigate; original question and final answer remain the evidence
Old memories from the active session could be filtered wholesale	Exclude only sources still visible in the fresh window; archived same-session and cross-session recall share one path
Community expansion could pull a whole neighborhood	Local LPA narrows candidates, query-time PPR ranks them, and only matched Q/A is recovered
DSH retained complete tool and reasoning traces	Completed turns retain question + final answer; older prefixes collapse to one fixed marker

Writing one completed turn costs exactly one auxiliary LLM call. Community detection and PPR are local. There are no hard-coded node/edge counts, semantic direction gates, or JSON repair that turns invalid output into accepted data. Read the complete design, source map, and porting sequence →

Measured first

Real 20-turn GLM-5.2 run	Historical native DSH baseline	Latest Graph Memory	Change
T20 first request	56,998 tokens	11,008 tokens	−80.69%
T20 model-visible messages	171	21	−87.72%
T01–T20 first-request context	532,451 tokens	165,896 tokens	−68.84%
All measured tokens¹	2,487,776	2,327,728	−6.43%

_{¹ The latest candidate includes 166 main-agent requests, 20 turn extractions, and 41 embedding requests; the historical baseline made 77 main requests. DSH commits and nondeterministic tool loops differ, so this is not a simultaneous strict A/B. First-request context is the direct takeover metric; the full bill remains visible.}

20/20 scenario turns passed · 20/20 structured extractions succeeded · 0 quarantined · 20 turn summaries · 92 SPO triples · 30 communities · 20 summary vectors. T11, T19, and T20 automatically recalled out-of-window memory with exact source question and final answer.

Read the Markdown benchmark, per-turn data, method, and limits →

Memory survives the context window

The graph is a navigation layer, not a replacement for evidence. TASK, SKILL, and EVENT nodes point back to the original user question and final visible answer; recalled context includes those exact source messages.

Install on DeepSeek Harness

…