Polypack Memory
io.github.imattauPublished by GitHub account imattauv0.1.31Updated Oct 24, 2026
MCP server exposing Polypack as persistent adaptive memory
The publisher's own server: Memory.fit
Overview
A local MCP server that gives an assistant persistent, adaptive memory through Polypack, with tools to store, recall, link and consolidate memories.
- What you can do
- Store, get, update, batch-store and permanently delete memories, with confirmation required for deletion and supersession to keep history intact when content changes. Recall and assemble context with token budgets, optional strict context isolation and opt-in bounded graph-neighbor hydration. Link and unlink memories, supersede and consolidate them, and query the relationship graph. Give activation feedback, suppress memories, and list contexts. Read context, active-memory, schema, stats and workflow guidance resources under the polypack scheme.
- When to use it
- Useful when an assistant should remember project or user preferences, past episodes and procedures across sessions, or when several clients such as Claude and Codex should share one durable memory store.
- Requirements
- Runs locally as a Python package installed from PyPI, with the polypack extra pulling in polypack-db. A durable store directory is passed with --store; without it an in-memory backend is used. Shared use across clients needs a long-running local Streamable HTTP service, via systemd user service, Debian or RPM package, or a manual command. Optional semantic retrieval downloads a Qwen embedding model once.
Installation
In SourceWeft
- Open Polypack Memory in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Persistent, adaptive memory for MCP clients.
An MCP server that exposes Polypack as persistent adaptive memory. MCP-specific tools live here; the database remains an independent dependency.
Install and run
The simplest installation is from PyPI:
For one MCP client, use the default stdio server configuration. For Claude and Codex sharing the same durable memory, install once and create a long-running user service:
This starts a stateless Streamable HTTP server at http://127.0.0.1:8765/mcp/, restarts it after a
failure, and prints client configuration snippets. The setup command uses
systemd --user; on systems without systemd, start the server directly:
In shared Streamable HTTP mode, configure both clients with the URL. Do not configure them
with a command and --store, since that starts two processes competing for
the same durable store.
Codex (~/.codex/config.toml):
Claude Desktop:
Debian package
The Debian package installs and starts a system-level polypack-mcp service
automatically. It runs as the dedicated polypack user, stores data in
/var/lib/polypack-mcp, and exposes the same local Streamable HTTP endpoint:
After installation, point Claude and Codex at
http://127.0.0.1:8765/mcp/. The default port can be changed in
/etc/default/polypack-mcp, followed by a service restart. The service can be
managed with:
The PyPI installation remains user-managed and uses polypack-mcp setup to
create a per-user service instead.
Optional semantic retrieval
The default installation uses Polypack's local graph, activation, and lexical retrieval without downloading an AI model. To enable local Qwen semantic retrieval, run:
This creates a managed localhost helper, downloads Qwen once into the store's embedding cache, and reindexes existing memories. The model is not bundled in the Debian/RPM package.
The helper loads Qwen3-Embedding-0.6B in bfloat16 (~1GB resident once loaded,
versus ~2.4GB in fp32) and unloads it after 15 minutes of inactivity,
reloading automatically on the next request. memory_recall results include
a semantic entry in scoreComponents whenever the helper is reachable,
alongside lexical and activation — the three sum to the reported score.
If the helper is stopped or errors, recall falls back to lexical + activation
scoring automatically. Check or disable it with:
For a PyPI user service, omit sudo --system and use the user store:
APT repository
The latest Debian package is also published to the public APT repository at
https://imattau.github.io/polypack-mcp. Configure it with the repository's
signing key, then install and update normally:
The repository is updated automatically for each v*.*.* release tag. See
docs/apt-repository.md for maintainer setup instructions.
RPM package
RPM-based distributions can install from the public RPM repository:
The matching .rpm asset is also attached to the
GitHub release:
The RPM package provides the same systemd service, store location, localhost Streamable HTTP endpoint, and Python 3.12 requirement as the Debian package.
Run manually
The server exposes seventeen focused tools: memory_store, memory_get,
memory_update, memory_list_contexts, memory_delete, memory_recall,
memory_context, memory_feedback, memory_suppress, memory_supersede,
memory_consolidate, memory_link, memory_unlink, memory_thread,
memory_store_batch, memory_link_batch, and graph_query. It also publishes context,
active-memory, schema, stats, and agent workflow guidance resources under
polypack://.
Memory classes are entity, episodic, procedural, and semantic. Store
project or user preferences as procedural memories; preference is not a
separate memory class.
When using a durable Polypack store, mutating operations checkpoint immediately and the server flushes the store during shutdown.
Retrieval tools return {items, metadata}. Metadata includes candidate and
excluded counts, context matches, score components, fallback behavior, the
retrieval version, and selection statistics. memory_context uses estimated
tokens (ceil(content characters / 4), minimum one) as its token_budget.
An item is never returned if it would exceed the remaining budget; budgets less
than or equal to zero are rejected. Context is a soft preference: matching
memories are preferred and unscoped global memories may be used as fallback.
Pass strict_context: true for isolation. An empty isolated result reports
reason: "no_context_match" and the searched context.
memory_recall can optionally hydrate related graph memories in the same call:
Neighbor traversal is opt-in and bounded. limit caps the total response and
neighbor_limit caps hydrated neighbors; metadata reports
moreNeighborsAvailable when additional eligible neighbors were found. Neighbor
items include their distance and connecting relationship metadata. Use
memory_link with the default
RESPONDS_TO relationship for handoffs, reviews, and fixes that address an
earlier memory. Graph edges are authoritative for relationships; use
graph_query(operation="relationship_diagnostics") to find legacy
provenance.responds_to values that are not backed by edges. See
polypack://help/workflow for the agent-facing workflow.
Feedback is activation feedback: useful=true reinforces a memory and
useful=false provides negative retrieval feedback. Responses expose activation
before and after plus whether learned weights changed. Supersession and
consolidation materialize SUPERSEDES, SUPERSEDED_BY, and
CONSOLIDATED_FROM graph edges.
Use memory_get for exact ID lookup and memory_update for mutable fields
(context, confidence, provenance, and metadata). Content changes should use
memory_supersede so history remains intact. Use memory_unlink to correct a
relationship and memory_list_contexts to discover namespaces. memory_delete
is permanent, requires confirm=true, and supports an optional revision check;
prefer memory_suppress when retaining history is useful.
Pass --store to open a durable Polypack directory. Without it, the server uses
the in-memory reference backend, which is convenient for smoke tests.
The polypack extra requires polypack-db>=3.3.1 and uses its native
ActivationEngine.working_memory selector for context assembly.
Development
The test suite includes an MCP client/server protocol smoke test covering tool discovery, memory storage, recall, and resource reads.
Documentation
Source: README.md at commit 201feb8
Tools
0Version history
1- v0.1.31LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Memory integrations
Memory.fit
fit.memoryOfficial publisher
Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.
AIfa Memory
works.aifaOfficial publisher
AIfa Memory's hosted MCP server, published by aifa.works; credential required; Streamable HTTP; 15 tools.
pg.ddx.io: the PostgreSQL community's memory
io.ddx.pgOfficial publisher
pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.
var.gg Naming Memory
gg.varOfficial publisher
Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…
Counterparts
ai.counterparts
Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.