Independent by design · no pay-to-rank placements  · How we evaluate tools →
Anclum Submit
I

Ink01101011/bantamkit

Independent directory — not the official site. Details below come from the project's public repository.

Give your coding agent a memory that outlasts the session.

2 ★ measured · checked 2026-11-19

Before you install: command ownership unverified - shown for reference only · license MIT

First step (reference only, ownership unverified): npx -y bantamkit-mcp@latest --install claude # or claude-desktop, copilot, cursor

★ 2·updated 2026-11-19
View on GitHub ↗Direct link · no redirect page

We have no copy-paste install command and no public remote endpoint, so we do not print a config. The step above is reference only, not a command we can vouch for. A made-up one is worse than none. How each client wires MCP up →

Star count
2 ★ · Ink01101011/bantamkit · read from the GitHub search API · (checked 2026-11-19 20:00:48)
Source
collected from the punkpeye/awesome-mcp-servers list · type: MCP server
Harvest history
first seen 2026-11-18 · last seen 2026-11-20 · seen 3× · listed by 3 sources
Score
score 300 · 2 ★ · 3 sources · mcp
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: MCP servers. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository Ink01101011/bantamkit;first catalogued 2026-11-18;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.
README excerpt (English, untranslated) · Read the full README on GitHub →

# bantamkit — memory MCP server for Claude Code, Cursor, VS Code Copilot and Cla

Excerpted from the repository README (abridged)

Give your coding agent a memory that outlasts the session. bantamkit is an MCP server: the
agent saves what is worth keeping — a preference you stated, a decision, the fix that worked —
and recalls it next session instead of asking you again. It works with Claude Code, Claude
Desktop, Cursor, GitHub Copilot in VS Code and any stdio MCP client. Install it once
from npm or PyPI; after that it starts offline.
## 🚀 Quick start
bash
npx -y bantamkit-mcp@latest --install claude # or claude-desktop, copilot, cursor
Then restart the host (in Claude Code, open a new session) and ask the agent to call
bantamkit_status. Prefer Python? pip install "bantamkit[mcp]" into a venv you keep, then
bantamkit-mcp --install claude. Every route and host is below.
## ✨ What you get
Memory that persists. Facts are plain Markdown files under .bantamkit/memory, deduped
and held to a byte budget. memory_save and memory_recall do the work; memory_compact and
memory_dream keep the store tidy.
Layered by default. Recall reads the project store, any stores you grant in
.bantamkit/config.yaml, and your profile store ~/.bantamkit/memory. Saves go to the
project store.
One command per host. --install writes the entry for Claude Code, Claude Desktop, Cursor
or VS Code Copilot, backs up any file it edits, and never prompts.
Offline after one install. Both install routes record the server by absolute path, so no
launch needs the network or your shell's PATH.
Claude Code hooks, if you want them. --install-hooks puts the memory index in front of
each new session, surfaces matching facts on each prompt, and nudges a save at the end of a
long session that saved nothing (docs/hooks.md).
More than memory. JSON Schema validation, a token ledger read off the host's transcripts,
a skill-catalogue audit, and shift-work tools that plan and hand off multi-step jobs —
the sixteen tools.
Two runtimes, one store. Pure Node on npm and Python on PyPI read and write the same
files, and every surface is compared between both runtimes by a conformance suite
(node tools/conformance/run.mjs --all). The core logic is written once, in TypeScript: the
Python modules in bantamkit/_generated/ (the memory store, recall, layers and dream, the
fact-file codec, the event log, the token ledger and the work planner among them) are compiled
from it by tools/ts2py, a Rust compiler, and committed, so installing from PyPI or npm needs
no Rust. The public Python API is unchanged, and where the two runtimes still deliberately
differ is listed in docs/porting.md.
A Python library for small models, too. pip install bantamkit lifts small-model agents
(~1B–8B, any OpenAI-compatible endpoint): malformed output, unreviewed answers, forgotten
context and runaway loops are absorbed by code, and a bundled eval suite measures the uplift.
## 📑 Contents
| Topic | What you'll find |
| Install the MCP server | Three ways to set it up — pick one |
| Install once, run offline (recommended) | One command; later launches need no network |
| Run with npx at every launch | The online form, and why it hangs offline |
| Install with Python (PyPI) | A venv you keep; a wheelhouse for no-network machines |
| Connect to a host | The same five steps for every host |
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[![Listed on Anclum](https://anclum.com/badge/listed.svg)](https://anclum.com/en/s/ink01101011-bantamkit/)
Source
awesome · https://github.com/Ink01101011/bantamkit
Browse by field
MCP servers
Traction
2 ★
Listed by
3 independent sources
added
today

More MCP servers

All 6,555 →

Filed under

Every tag opens the full list for that filter. Counts are the live catalogue figures.

Browse all fields →

← Back to index