agentmemory
01Plugin Claude Code
Plugin marketplace listing 1 plugin: agentmemory.
Plugin Claude Code
Plugin marketplace listing 1 plugin: agentmemory.
Instructions file CodexOpenCode
AGENTS.md instructions for rmarquesa/agentmemory-offline, covering agentmemory — agent instructions, architecture, consistency rules, code patterns and function registration.
Plugin Claude Code
Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 53 MCP tools, 8 skills, real-time viewer.
MCP server Claude CodeCodexCursor
MCP server "agentmemory" as configured in rmarquesa/agentmemory-offline. Launched with agentmemory mcp. Needs 3 environment variables to run.
Hook
Runs when a session starts, executing session-start.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when you submit a prompt, before the agent sees it, executing prompt-submit.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs before the agent uses a tool for Edit, Write, Read, Glob and Grep tool calls, executing pre-tool-use.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs after a tool call finishes, executing post-tool-use.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when a tool call fails, executing post-tool-failure.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs before the context is compacted, executing pre-compact.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when a subagent starts, executing subagent-start.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when a subagent finishes, executing subagent-stop.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when the agent sends a notification, executing notification.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when a task is marked completed, executing task-completed.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when the agent finishes a response, executing stop.mjs via node. From rmarquesa/agentmemory-offline.
Hook
Runs when a session ends, executing session-end.mjs via node. From rmarquesa/agentmemory-offline.
Command
Search past session observations and lessons for relevant context. Wrap the memorysmartsearch and memorylessonrecall MCP tools.
Command
Explicitly save an insight, decision, or learning to agentmemory for future sessions. Wraps the memorysave MCP tool.
Skill Claude CodeCodex
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
Skill Claude CodeCodex
How agentmemory is built, the iii engine primitives it runs on, its storage model, ports, and the viewer. Use when reasoning about how memory is stored or retrieved end to end, when extending the system, or when answering how agentmemory works under the hood.
Skill Claude CodeCodex
Skill "agentmemory-config" from rmarquesa/agentmemory-offline, covering quick start, defaults worth knowing, ports, see also and reference.
Skill Claude CodeCodex
The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.
Skill Claude CodeCodex
Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do via MCP.
Skill Claude CodeCodex
The agentmemory HTTP REST API surface, the primary protocol for talking to the memory server. Use when calling agentmemory over HTTP, when MCP is unavailable and you need a fallback, or when integrating a host that does not speak MCP.