dsh-engram
kenz1117
Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, provenance audit, SM-2 review. Zero external services, zero API keys.
GITHUB TOPIC
17projects include this topic
The "provenance" topic on GitHub groups 17 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-engram with 62 GitHub stars. dsh-engram — Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, provenance audit, SM-2 review. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
kenz1117
Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, provenance audit, SM-2 review. Zero external services, zero API keys.
reshuibuduo
TMCRA Core — local-first, scope-isolated long-term memory runtime for AI agents.
dongsheng123132
Content-addressed receipts for skills actually loaded by DeepSeek Harness
dongsheng123132
Content-addressed artifact, fact, action and report lineage for DeepSeek Harness
030611
Observe-only provenance ledger over public DeepSeek Harness runtime evidence
gwsbhqt
洞察 — read-only insight panel for a DeepSeek Harness profile: where every plugin, service, tool and model came from, which config layer inserted or disabled it, and what is running right now.
dongsheng123132
Content-addressed proof that a DSH profile declaration, pnpm lock and installed bundles agree
OakcoderX
Source-linked text memory for DeepSeek Harness (DSH). 保留原话来源、项目边界与修订历史的文字记忆插件。Public beta · MIT.
ScreamingMaggot
DeepSeek Harness (DSH) 插件包:把工具输出与模型回复折叠成可展开的摘要,把会话事实沉淀成带证据的外部记忆。实测 12 个长会话把 50 MB 上下文压到 0.96 MB(52×),上下文占用中位 7.8%。兼容 DSH 0.1.5-rc.2 ~ 0.2.2-rc.2;已发布 npm 包 rcs-context:dsh plugin --profile web add rcs-context。
zhan-tz
DSH plugin: Jupyter-style living notebook — a turn-replayable dataflow DAG with git commit provenance nodes, sub-agent handoff edges, persistent ledger, hover-to-rerun and LLM explanations
dongsheng123132
Content-addressed DSH configuration origin and shadowing evidence
7starsseeker
Fact-checking skill for DeepSeek Harness: multi-source verification against the open web, domestic and international ecosystems, optional TypeSafe Jev (System One) judgements.
asuramaya
The persistent memory and coordination graph for AI agents (MCP, DeepSeek Harness, Claude Code, Cursor)
codeshark94
🐋 Sci-whale — research orchestration with DSH engineering workers, independent scientific validation, and preserved evidence.
guhanfei-ai
A safe, bounded, read-only perception layer for AI agents to observe administrator-defined JSON APIs.
masquerator-coder
Layered long-term memory for coding agents: decaying episodic recall (L2), a provenance-tracking semantic graph (L3), and budgeted procedural skills (L4) in one embedded SQLite file. Deterministic retrieval, no model calls, no server. Ships a DeepSeek Harness plugin.
PerryLink
Community certification spec and registry for DeepSeek Harness plugins: five machine-checkable dimensions, A-D grades, and a security veto.