Lore logo

Lore

Unclaimed

by agentkitai

Cross-agent memory SDK. Agents publish lessons, query shared knowledge, with built-in redaction. Python + TypeScript.

Install

$lore mcp

Set up this server

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions
ai-agentscross-agentknowledge-graphmcpmemorypythontypescript

More in AI & ML

Browse the full directory

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

40 of 40 tools

Documented tools (40)

From project documentation. A server handshake does not verify each tool’s description or behavior.

add_conversation

Extract memories from conversation messages

as_prompt

Export memories formatted for LLM injection

check_freshness

Verify memory freshness against git

classify

Intent, domain, emotion classification

conflicts

List detected fact conflicts

consolidate

Merge duplicate/related memories

demote_memory

Unshare a memory, making it private again

downvote_memory

Lower memory ranking

enrich

LLM-powered metadata extraction

entity_map

List entities (optional D3 format)

export

Export all data to JSON

extract_facts

Extract (subject, predicate, object) triples

forget

Delete a memory by ID

get_memories

Fetch full payloads for one or more memory IDs

github_sync

Sync GitHub repo data

graph_query

Hop-by-hop knowledge graph traversal

ingest

Accept content from external sources

list_at_time

List memories that were canonical at a given time

list_facts

List active facts

list_memories

List memories with filtering

on_this_day

Memories from same date across years

promote_memory

Share a private memory with the team (private→shared)

recall

Semantic search with temporal/graph-enhanced retrieval

recent_activity

Recent memory activity summary

related

Find related memories/entities

remember

Store a memory with type, tier, tags, metadata

remember_observation

Record a structured observation from a session

review_connection

Approve/reject a pending connection

review_digest

Get pending connections for review

save_snapshot

Save session snapshot

search

Progressive-disclosure compact index (id, title, score)

snapshot

Create data backup

snapshot_list

List available snapshots

stats

Memory statistics (total, by type/tier)

suggest

Proactive memory recommendations based on session context

supersede

Mark a memory as superseded by a newer one

timeline

Chronologically adjacent events around an anchor memory

topic_detail

Deep dive on a topic (memories, entities, timeline)

topics

List auto-detected recurring topics

upvote_memory

Boost memory ranking

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Lore MCP Server

How do I connect Lore MCP Server to Claude?
The listing records `lore mcp` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop, Claude Code, Cursor as compatible clients.
Is Lore MCP Server free?
The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Lore MCP Server do?
Lore MCP Server documents 40 tools to the agent, including add_conversation, as_prompt, check_freshness. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.