AgenticMemory
About
Persistent memory for AI agents - conversation history, key-value context, and semantic search across sessions, plus FIFO queues. 17 MCP tools, remote SSE (nothing to install) or local stdio. Agents self-signup via CLI a
Details
- Author
- Tyga.Cloud Ltd
- GitHub stars
- 1
- Downloads
- 386
- Categories
- Knowledge Base, AI, Developer Tools
Jump to
- Semantic search is impossible on zero-knowledge spaces by design
- Losing the key or passphrase means the data is unrecoverable. That's the point. Back it up: agmry key show --reveal
- Conversation history — ordered, role-aware messages with recency windowing, sub-ms reads
- Key-value context — typed durable facts: decisions, preferences, runbooks
- Long-term entries — titled, tagged knowledge that survives months, with auto-summarisation
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AgenticMemoryCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Follow the repository README to install the server and add its MCP configuration to your client.
memory_store
Store a message in conversation history. Use for remembering what just happened.
memory_store_batch
Store multiple messages at once.
memory_recall
Recall recent messages from conversation history. Returns newest first.
memory_clear
Clear all messages in a memory space.
memory_search
Semantic search across past conversations. Finds by meaning, not keywords.
context_set
Set a key-value context entry. Stores structured data (JSON or string).
context_get
Get a context value by key.
context_list
List all context keys and values in a space.
context_delete
Delete a context key.
entry_add
Add a long-term memory entry (summary, decision, extraction, artifact).
entries_list
List long-term memory entries. Filter by tags.
spaces_list
List all memory spaces owned by this API key.
spaces_create
Create a new memory space.
queue_push
Enqueue a JSON envelope onto a FIFO queue in a memory space. Use to send work/events to other agents sharing the space.
queue_pop
Dequeue the oldest envelope from a FIFO queue (returns null if empty). Set wait (max 25s) to long-poll for the next envelope.
queue_peek
Peek at a queue without consuming: returns length and the head envelope.
memory_bootstrap
Load full context in one call: recent messages, entries, context, scratchpad. Run this at session start.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"agenticmemory": {
"agenticmemory": {
"command": "npx",
"args": [
"-y",
"agmry",
"mcp-serve"
],
"env": {
"AGMRY_API_KEY": "amk_your_key_here"
}
}
}
}
}McpServers
{
"agenticmemory": {
"command": "npx",
"args": [
"-y",
"agmry",
"mcp-serve"
],
"env": {
"AGMRY_API_KEY": "amk_your_key_here"
}
}
}Persistent memory for AI agents - conversation history, key-value context, and semantic search across sessions, plus FIFO queues. 17 MCP tools, remote SSE (nothing to install) or local stdio. Agents self-signup via CLI and get a working API key instantly.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
