belief-merge

Provenance-retaining cross-session context merge for DeepSeek Harness — a confluence theorem with a counterexample, and a benchmark for it.

Ecosystem appAI ModelsKnowledgeStorageMemoryGitHub integration

Verification

L5 · Ecosystem app

Risk

Low

Health

Active

Trust

Silver

Install verification: Ecosystem app: not installed via dsh plugin add, so the L1-L5 plugin install-verification ladder does not apply; the security scan still runs.Install verification details →

What it doesAI

Provenance-retaining cross-session context merge for DeepSeek Harness agents, including a confluence theorem, counterexample, and benchmark.

Cross-session context merge with provenance retention
Confluence theorem with a counterexample
Benchmark for evaluating merge performance

aiAImemoryAI

Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.

Installation

GitHub repository

Ecosystem apps are not installable via dsh plugin add: desktop / web shells install or deploy through their own release channel (GitHub Releases or the project site), while entries that install but declare no dsh.bundle and mount nothing — or that install yet never appear in the runtime inventory — are used straight from the source repository.

Ecosystem apps are not installed via dsh plugin add — their level always reads L5 · Ecosystem app and the L1-L5 ladder is not what rates them; the security scan still runs.

Verification & Compatibility

Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.

External credentials (plugin-level): none detected

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified◐ L4 testing · install passed○ ecosystem app✗ failed

Ecosystem app: not installed via dsh plugin add (a desktop / web shell, or an entry that installs yet never appears in the runtime inventory) — its level always reads L5 · Ecosystem app.

Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).

Author badges

Embed the official badges in your README to showcase security & install-test status:

Security Report

Automated static scan, not manual review.

DSH.SO VETPASSEDc03f17

Security reviewAutomated review · daily

PASSED

Vet static analysis found no suspicious behavior — verdict is clean.

0 critical·0 high·0 medium

Version binding

plugin version—

scanned versionc03f17a9d11dgit2026-09-17

current version63386d32f7e1version moved on

vet verdictclean · git

Vet is an AST static scan (npm artifact or git source).

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Risk details

No critical or warning findings.

Activity

Last commit 2026-09-17 · activity: Active

• Repo created: 2026-09-17

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/aLIZELI/belief-merge

Plugin notes

What is the belief-merge DeepSeek Harness plugin?

belief-merge is a DeepSeek Harness plugin maintained by @aLIZELI. It is cataloged on dsh.so as a AI Models plugin for Memory tasks, with a public GitHub source, declared install command, and automated static security scan.

How do I install belief-merge?

This is an ecosystem app, not a plugin installable via dsh plugin add: desktop / web shells install or deploy through their own release channel, while entries that install but declare no dsh.bundle and mount nothing — or that install yet never appear in the runtime inventory — are used straight from the source repository. Its level always reads L5 · Ecosystem app; the security scan still runs.

How does the security scan relate to a manual audit?

The scan is automated static analysis of the repository source — a scalable first line of defense that can produce false positives and miss context; it is not a manual security audit. Before using a plugin, review the repository and installed permissions, and combine the scan with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-09-17