tidbits-memory
Enables AI agents to record and rank learnings, facts, and methods through a collaborative voting framework. It provides tools for agents to surface the most useful information across sessions using persistent memory storage.
README
tidbits-memory
A memory/tidbits voting framework for AI agents. Agents can record learnings (facts, methods, gotchas) and vote on them to surface the most useful tidbits.
Installation
uv pip install -e ".[dev]"
Quick start
from tidbits_memory.adapters.memory import InMemoryAdapter
from tidbits_memory.store import MemoryStore
store = MemoryStore(InMemoryAdapter())
# Create a voter id for this session
voter_id = store.create_voter_id()
# Create a memory
mem = store.create_memory("Python dicts preserve insertion order since 3.7", voter_id=voter_id)
# Get memories (random order, no vote counts) — ideal for agent consumption
result = store.get_memories(voter_id=voter_id)
print(result["memories"])
# Upvote a useful memory
store.upvote_memory(mem.id, voter_id="another-session-id")
# List memories sorted by votes (most upvoted first)
for m in store.list_memories():
print(f"[{m.votes}] {m.content}")
# Downvote an erroneous memory
store.downvote_memory(mem.id, voter_id="yet-another-session")
# Unvote (remove a prior vote)
store.unvote_memory(mem.id, "another-session-id")
# Remove a memory
store.remove_memory(mem.id)
Persistent storage (JSON file)
from tidbits_memory.adapters.json_file import JsonFileAdapter
from tidbits_memory.store import MemoryStore
store = MemoryStore(JsonFileAdapter("memories.json"))
store.create_memory("Use `uv` for fast Python packaging")
Voter ID generation
When an agent doesn't have a session/conversation ID, use create_voter_id:
voter_id = store.create_voter_id()
# Use this voter_id for all votes in this session
If no voter_id is provided when calling get_memories, one is automatically generated and returned in the response.
MCP Tool Wrappers
from mcp.server import FastMCP
from tidbits_memory.adapters.memory import InMemoryAdapter
from tidbits_memory.store import MemoryStore
from tidbits_memory.tools import register_tools
store = MemoryStore(InMemoryAdapter())
mcp = FastMCP("tidbits")
register_tools(mcp, store)
# Registered tool names:
# create_memory, upvote_memory, downvote_memory, unvote_memory,
# list_memory, get_memories, remove_memory, create_voter_id
Running tests
uv run pytest
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.