[PR #2060] [MERGED] New: add AgentMesh Trust Layer plugin (cryptographic identity for multi-agent workflows) #2048

New Issue

2026-02-22T18:15:24-05:00

yindo commented

2026-02-22 18:15:24 -05:00

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-plugins/pull/2060
Author: @imran-siddique
Created: 2/12/2026
Status: ✅ Merged
Merged: 2/17/2026
Merged by: @crazywoola

Base: main ← Head: contrib/agentmesh-trust-plugin

📝 Commits (4)

0a44f30 feat: add AgentMesh Trust Layer plugin
18b5528 fix: add meta, runner, PRIVACY.md, main.py, requirements.txt to pass CI
1c06cea fix: add missing extra.python fields to tool and provider YAMLs
cbe08a3 fix: remove unused ToolProviderCredentials import that breaks on latest dify_plugin SDK

📊 Changes

1 file changed (+0 additions, -0 deletions)

View changed files

➕ imran-siddique/agentmesh-trust-layer.difypkg (+0 -0)

📄 Description

Plugin Submission Form

1. Metadata

Plugin Author: imran-siddique
Plugin Name: agentmesh-trust-layer
Repository URL: https://github.com/imran-siddique/agent-mesh/tree/master/integrations/dify-plugin

2. Submission Type

New plugin submission
Version update for existing plugin

3. Description

AgentMesh Trust Layer provides cryptographic identity and trust verification for Dify agent workflows. It enables agents to verify each other's identity before trusting their data, check authorization for workflow steps, and maintain dynamic trust scores based on behavioral history.

4 Tools Provided:

verify_peer - Verify another agent's identity and capabilities using Ed25519 cryptographic signatures
verify_step - Check if an agent is authorized to execute a specific workflow step
get_identity - Get this agent's cryptographic identity (DID + public key) to share with peers
record_interaction - Record success/failure to dynamically update trust scores

Why This Matters:

In multi-agent workflows, agents need to verify "who" they're communicating with. This plugin provides:

Ed25519 cryptographic identity (DIDs)
Trust scoring (0.0-1.0) based on behavioral history
Capability-based access control
Full audit logging of trust decisions

Related to:

Redirect from langgenius/dify#32079 per @crazywoola's guidance to submit as plugin

4. Checklist

I have read and followed the Publish to Dify Marketplace guidelines
I have read and comply with the Plugin Developer Agreement
I confirm my plugin works properly on both Dify Community Edition and Cloud Version
I confirm my plugin has been thoroughly tested for completeness and functionality
My plugin brings new value to Dify

5. Documentation Checklist

Step-by-step setup instructions
Detailed usage instructions
All required APIs and credentials are clearly listed
Connection requirements and configuration details
Link to the repository for the plugin source code

6. Privacy Protection Information

Data Collection

This plugin does not collect any personal user data. It operates entirely locally within the Dify environment. The only data processed:

Agent DIDs (generated locally via Ed25519)
Trust scores (stored in-memory)
Audit logs (stored in-memory, not persisted externally)

Privacy Policy

I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/langgenius/dify-plugins/pull/2060 **Author:** [@imran-siddique](https://github.com/imran-siddique) **Created:** 2/12/2026 **Status:** ✅ Merged **Merged:** 2/17/2026 **Merged by:** [@crazywoola](https://github.com/crazywoola) **Base:** `main` ← **Head:** `contrib/agentmesh-trust-plugin` --- ### 📝 Commits (4) - [`0a44f30`](https://github.com/langgenius/dify-plugins/commit/0a44f3003379d3224d1d84b3f01ef3ba3f4c49b9) feat: add AgentMesh Trust Layer plugin - [`18b5528`](https://github.com/langgenius/dify-plugins/commit/18b552876e943b017ae6074e1b39f0130b8fda1f) fix: add meta, runner, PRIVACY.md, main.py, requirements.txt to pass CI - [`1c06cea`](https://github.com/langgenius/dify-plugins/commit/1c06cea16f85d1c3963c401449913bdfa064e734) fix: add missing extra.python fields to tool and provider YAMLs - [`cbe08a3`](https://github.com/langgenius/dify-plugins/commit/cbe08a381b6527fd7c330485013093873776b13e) fix: remove unused ToolProviderCredentials import that breaks on latest dify_plugin SDK ### 📊 Changes **1 file changed** (+0 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `imran-siddique/agentmesh-trust-layer.difypkg` (+0 -0) </details> ### 📄 Description # Plugin Submission Form ## 1. Metadata - **Plugin Author**: imran-siddique - **Plugin Name**: agentmesh-trust-layer - **Repository URL**: https://github.com/imran-siddique/agent-mesh/tree/master/integrations/dify-plugin ## 2. Submission Type - [x] New plugin submission - [ ] Version update for existing plugin ## 3. Description **AgentMesh Trust Layer** provides cryptographic identity and trust verification for Dify agent workflows. It enables agents to verify each other's identity before trusting their data, check authorization for workflow steps, and maintain dynamic trust scores based on behavioral history. ### 4 Tools Provided: - **verify_peer** - Verify another agent's identity and capabilities using Ed25519 cryptographic signatures - **verify_step** - Check if an agent is authorized to execute a specific workflow step - **get_identity** - Get this agent's cryptographic identity (DID + public key) to share with peers - **record_interaction** - Record success/failure to dynamically update trust scores ### Why This Matters: In multi-agent workflows, agents need to verify "who" they're communicating with. This plugin provides: - Ed25519 cryptographic identity (DIDs) - Trust scoring (0.0-1.0) based on behavioral history - Capability-based access control - Full audit logging of trust decisions ### Related to: - Redirect from [langgenius/dify#32079](https://github.com/langgenius/dify/pull/32079) per @crazywoola's guidance to submit as plugin ## 4. Checklist - [x] I have read and followed the Publish to Dify Marketplace guidelines - [x] I have read and comply with the Plugin Developer Agreement - [x] I confirm my plugin works properly on both Dify Community Edition and Cloud Version - [x] I confirm my plugin has been thoroughly tested for completeness and functionality - [x] My plugin brings new value to Dify ## 5. Documentation Checklist - [x] Step-by-step setup instructions - [x] Detailed usage instructions - [x] All required APIs and credentials are clearly listed - [x] Connection requirements and configuration details - [x] Link to the repository for the plugin source code ## 6. Privacy Protection Information ### Data Collection This plugin does not collect any personal user data. It operates entirely locally within the Dify environment. The only data processed: - Agent DIDs (generated locally via Ed25519) - Trust scores (stored in-memory) - Audit logs (stored in-memory, not persisted externally) ### Privacy Policy - [x] I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

yindo added the pull-request label 2026-02-22 18:15:24 -05:00

yindo closed this issue

2026-02-22 18:15:25 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: langgenius/dify-plugins#2048