memoryguard

Solid

Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.

AI & Automation 1 stars 0 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 78/100

Stars 20%
10
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
76
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# MemoryGuard Shared memory for coding agents, without shared-memory chaos. ## What It Does MemoryGuard provides a local MCP stdio memory backend that coding agents (Claude Code, Codex, Cursor) can write to. Every write is auto-organized: classified, deduplicated, superseded, quarantined, or compressed. ## Install ```bash pip install agent-memguard ``` ## MCP Configuration Add to your agent's MCP config: ```json { "mcpServers": { "memoryguard": { "command": "python", "args": ["-m", "memoryguard.mcp_server"] } } } ``` ## Tools - `memoryguard_memory_read` - Read a single memory record by ID - `memoryguard_memory_search` - Search memories by query, kind, or status - `memoryguard_memory_write` - Write a new memory; auto-organizes on write - `memoryguard_memory_update` - Update a memory (body / kind / status) - `memoryguard_memory_delete` - Soft-delete a memory - `memoryguard_memory_status` - Get shared memory group status - `memoryguard_binding_create` - Bind an agent to a share group - `memoryguard_binding_list` - List agent bindings - `memoryguard_extract_memories` - Extract memory segments from a source file - `memoryguard_accept_candidates` - Accept extracted candidates and write to shared memory - `memoryguard_semantic_check` - Check text for semantic duplicates / conflicts - `memoryguard_provider_install` - Install provider adapter (Claude / Codex / Cursor) ## Privacy No account. No server. No telemetry. All data stays in local SQLite und...

Details

Author
irisxc4
Repository
irisxc4/memoryguard
Created
6 days ago
Last Updated
4 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category