Skip to main content
Glama
Sign In
tidbits-memory

tidbits-memory

by brkhrdt
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

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

Available Tools

8 tools
create_memoryC

Create a new memory/tidbit. Returns the created memory with its id.

Inputs: content (required), creator, tags, voter_id. Returns: object

create_voter_idB

Generate a new unique voter_id for this agent session.

Inputs: no named parameters. Returns: object

downvote_memoryB

Downvote a memory. Provide voter_id to enforce one vote per session.

Inputs: memory_id (required), voter_id. Returns: object

get_memoriesB

Get the list of memories.If voter_id is not provided, a new one is generated and included in the response for use in subsequent votes.

Inputs: voter_id. Returns: object

list_memoryB

List all memories sorted by votes descending (most upvoted first).

Inputs: order_by, limit. Returns: result

remove_memoryB

Remove a memory by id.

Inputs: memory_id (required). Returns: object

unvote_memoryC

Remove a prior vote from a memory by voter_id.

Inputs: memory_id (required), voter_id (required). Returns: object

upvote_memoryB

Upvote a memory. Provide voter_id to enforce one vote per session.

Inputs: memory_id (required), voter_id. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no ambiguity: create_memory, create_voter_id, downvote_memory, get_memories, list_memory, remove_memory, unvote_memory, and upvote_memory. The actions (create, get, list, remove, upvote, downvote, unvote) and targets (memory, voter_id) are well-defined and non-overlapping.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern using snake_case (e.g., create_memory, downvote_memory, get_memories). The naming is predictable and uniform across all eight tools, with no deviations in style or convention.

    Tool Count5/5

    With 8 tools, the count is well-scoped for a memory/voting system. Each tool serves a specific function in managing memories and votes, and none appear redundant or unnecessary for the server's purpose.

    Completeness5/5

    The tool set provides complete coverage for the memory and voting domain: CRUD operations (create, get/list, remove), voting lifecycle (upvote, downvote, unvote), and voter management (create_voter_id). There are no obvious gaps, and agents can handle all core workflows without dead ends.

    Resources

    Related MCP Connectors