Power your agent
पब्लिशर की अपनी कमांड। PlugMCP एंडपॉइंट नहीं।
Host a copy with our keys and logs.
npx -y [email protected]Claude Code में लोकल कमांड के लिए इंस्टॉल लिंक नहीं है। नीचे दी गई कमांड कॉपी करें और टर्मिनल में चलाएँ।
claude mcp add bantamkit-mcp -- npx -y bantamkit-mcp@0.40.0टर्मिनल में चलाएँ।
{ "mcpServers": { "bantamkit-mcp": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
रिमोट URL या आपकी मशीन पर कमांड? दोनों इंस्टॉल में क्या अंतर है
PlugMCP पर चलाएँ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
लॉन्चपब्लिशर से
Persistent memory for coding agents: an MCP server for Claude Code, Claude Desktop, Cursor and VS Code Copilot. Layered project memory, Claude Code hooks, JSON Schema validation, token ledger and shift-work tools. Pure Node; install once with npx, run off
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.
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.
.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..bantamkit/config.yaml, and your profile store ~/.bantamkit/memory. Saves go to the
project store.--install writes the entry for Claude Code, Claude Desktop, Cursor
or VS Code Copilot, backs up any file it edits, and never prompts.--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).node tools/conformance/run.mjs --all).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.Two implementations of one server — Node on npm, Python on PyPI — share one memory store on disk. To just try it:
npx -y bantamkit-mcp --assets-root # Node, no Python required
pipx run --spec "bantamkit[mcp]" bantamkit-mcp --assets-root # Python
A host launches the server every session, so what matters is whether each launch needs the network. Pick one of the three ways below.
npx -y bantamkit-mcp@latest --install claude # or claude-desktop, copilot, cursor
This runs npm install --prefix ~/.bantamkit/mcp once and records
<the node that ran it> ~/.bantamkit/mcp/node_modules/bantamkit-mcp/dist/cli.js, both absolute.
No later launch needs npx, the registry or your PATH, and it never downgrades a newer kept
install.
--force.npx entry needs --force (Claude Code: claude mcp remove first).npx -y hangs before bantamkit starts.
Use npx --offline -y bantamkit-mcp@<version> --install <host>, or the kept install's own CLI:
<node> ~/.bantamkit/mcp/node_modules/bantamkit-mcp/dist/cli.js --install <host>.Measurements: docs/install.md → MCP server: measured install detail.
{"mcpServers": {"bantamkit": {"command": "npx", "args": ["-y", "bantamkit-mcp"]}}}
This asks the registry on every launch. Offline it fails silently: with a warm cache,
npx -y bantamkit-mcp, npx -y bantamkit-mcp@latest and a pinned version each hung to the 45 s
bound with 0 bytes on stdout, and the host reports only its own handshake timeout.
npx also caches what latest resolved to, so add @latest or pin a version
(why).
pip install "bantamkit[mcp]" # into a venv you keep, not a pipx run
bantamkit-mcp --install claude # or claude-desktop, copilot, cursor
--install records the venv's console script by absolute path with "args": [], so no launch
needs the network. With no network at all, pip download a wheelhouse on a machine with the
same OS, CPU architecture and Python version, then pip install --no-index --find-links:
steps.
--install <host> (claude, claude-desktop, copilot, cursor) writes the entry. It backs
the file up first, refuses an entry that differs unless you pass --force, and never prompts —
so it behaves the same in a terminal, in CI and inside another agent. With Python, run
bantamkit-mcp --install <host> from your venv instead of the npx line.
Each host below has the same steps: 1 command, 2 file, 3 entry, 4 confirm,
5 undo or re-run. The entry's command and args depend on the install route:
For JSON hosts, a quick check of the recorded command: run it in a terminal — with nothing on
stdin it prints usage: bantamkit-mcp … and exits 0.
Command: npx -y bantamkit-mcp@latest --install claude
File: none edited directly — it runs claude mcp add bantamkit -s user -- <command> <args>
(user scope, every project), because ~/.claude.json also holds host state that is not MCP config.
Entry: printed as ran : claude mcp add bantamkit -s user -- <node> <cli.js>.
Confirm: claude mcp list prints bantamkit: <node> <cli.js> - ✔ Connected (Claude Code
2.1.272; run it outside a project whose .mcp.json also names bantamkit, or it prints
[Conflicting scopes]). In a session, ask the agent to call bantamkit_status.
Undo / re-run: --force does not reach Claude Code, and a second add fails with
MCP server bantamkit already exists in user config. Remove first:
claude mcp remove bantamkit -s user
npx -y bantamkit-mcp@latest --install claude
Command: npx -y bantamkit-mcp@latest --install claude-desktop
File: macOS ~/Library/Application Support/Claude/claude_desktop_config.json ·
Windows %APPDATA%\Claude\claude_desktop_config.json ·
Linux ~/.config/Claude/claude_desktop_config.json
Entry (key mcpServers):
{"mcpServers": {"bantamkit": {"command": "/absolute/path/to/node", "args": ["/Users/you/.bantamkit/mcp/node_modules/bantamkit-mcp/dist/cli.js"]}}}
Confirm: it prints installed bantamkit into claude-desktop with file, key and command.
Fully quit and reopen Claude Desktop, then ask it to call bantamkit_status.
Undo / re-run: there is no uninstall flag — delete the bantamkit entry or restore
claude_desktop_config.json.backup-<date>. A matching re-run prints
bantamkit is already installed in claude-desktop and matches; a differing entry needs --force.
Command: npx -y bantamkit-mcp@latest --install cursor
File: ~/.cursor/mcp.json on every OS (%USERPROFILE%\.cursor\mcp.json on Windows);
.cursor/mcp.json for one project, by hand.
Entry (key mcpServers):
{"mcpServers": {"bantamkit": {"command": "/absolute/path/to/node", "args": ["/Users/you/.bantamkit/mcp/node_modules/bantamkit-mcp/dist/cli.js"]}}}
Confirm: it prints installed bantamkit into cursor and key : mcpServers. Restart
Cursor and ask the agent to call bantamkit_status.
Undo / re-run: delete the entry or restore mcp.json.backup-<date>. To replace a
differing entry, such as an old npx one:
npx -y bantamkit-mcp@latest --install cursor --force
Command: npx -y bantamkit-mcp@latest --install copilot
File: macOS ~/Library/Application Support/Code/User/mcp.json ·
Windows %APPDATA%\Code\User\mcp.json · Linux ~/.config/Code/User/mcp.json;
.vscode/mcp.json for one workspace, or MCP: Open User Configuration, by hand.
Entry — the key is servers, not mcpServers, plus "type": "stdio". This is the
detail that catches people out:
{"servers": {"bantamkit": {"type": "stdio", "command": "/absolute/path/to/node", "args": ["/Users/you/.bantamkit/mcp/node_modules/bantamkit-mcp/dist/cli.js"]}}}
Confirm: it prints installed bantamkit into copilot and key : servers. Restart
VS Code and ask Copilot to call bantamkit_status.
Undo / re-run: delete the entry or restore mcp.json.backup-<date>; --force replaces
a differing entry.
Any stdio MCP client runs the same command/args; nothing is host-specific. Codex and a
generic JSON config: docs/mcp.md → Client setup. Hand-written forms
for every host: npm README ·
Python README.
Flags go in the entry's args; environment variables in its env block (or
claude mcp add -e NAME=value). Both runtimes print the same --help.
Don't add --store by reflex: the layering is most of the value. One-shot commands that print
and exit: --install {claude,claude-desktop,copilot,cursor} (with --force),
--install-hooks / --remove-hooks (with --yes), --hook, --update,
--assets-root, --mcp-report, --statusline.
More: store binding ·
pinning ·
event log · prices.
npx -y bantamkit-mcp@latest --update # patches the kept install at ~/.bantamkit/mcp
npx -y bantamkit-mcp@latest --assets-root # npx CACHES; without @latest you get an old resolve
npm i -g bantamkit-mcp@latest # global npm install
pip install -U "bantamkit[mcp]" # PyPI (pipx upgrade bantamkit · uv tool upgrade bantamkit)
git pull && npm ci --prefix runtime-ts && npm run build --prefix runtime-ts # a checkout: dist/ is build output
--update (check the package index and update this install if it differs, then exit) patches a
registry install or a kept install to exactly the version it compared, and reports success only
after the install says so; any other shape it refuses with exit 1 and names the manual route.
It is the only network access here, and only when you type it.
Then restart the server in the host (/mcp → reconnect in Claude Code; a full restart of
Claude Desktop) — a running server keeps the code it started with. bantamkit_status prints the
version and the build_id of the code answering you; a new version with an old build_id
means an old process. Per-install table: npm README → Updating.
Both servers serve the same 15 tools, three prompts and two resource templates
(bantamkit://skills/{name}, bantamkit://rubrics/{name}). The prompts are what a person invokes from
the host's slash menu: bantamkit_status (the status report), skill_audit (#205: gathers the
skills this host loads, audits them, and inserts the report plus a proposed settings.json change
that is never applied for you; in Claude Code it is /mcp__bantamkit__skill_audit) and
skill_propose (#206: lists the skills bantamkit proposes from your repeated, successful work and
the ones it installed, and approves, rejects, undoes, promotes or demotes one; in Claude Code it is
/mcp__bantamkit__skill_propose, see docs/skills.md):
pip install bantamkit
Editable install and runtime differences: docs/install.md,
docs/porting.md. Copy-paste start: examples/.
from bantamkit import Agent, CritiqueGate, Memory, OpenAICompatible, Tool, ToolDef
client = OpenAICompatible(base_url="http://localhost:11434/v1", model="qwen2.5:7b-instruct")
price_lookup = ToolDef(
tool=Tool(
name="price_lookup",
description="Get the unit price of an item",
parameters={
"type": "object",
"required": ["item"],
"properties": {"item": {"type": "string"}},
},
),
handler=lambda item: f"{item} price: 25",
)
agent = Agent(client=client, tools=[price_lookup]).use(
Memory(store="./.bantam-memory"),
CritiqueGate("task-completion"),
)
result = agent.run("What does a widget cost? Remember it for next time.")
print(result.output, result.usage.total)
Measured on the bundled 22-task suite across four models, 528 runs each. Numbers and caveats: docs/usage.md → Recommended defaults.
Memory — the biggest single mover on every model measured.CritiqueGate on small instruct models — ≤6 passes at 2–3.5× bare's tokens.structured() for schema'd output — zero schema retries in 2,112 runs.FileAccessGraph when the agent reads files, on ~4B-class models.full (memory + schema + grounded critique) is a 4b-reference result — 66/66 there only.GroundedCritiqueGate over CritiqueGate when the agent has tools — same 4b scope.Design notes live in docs/superpowers/specs/.
Persistent memory for coding agents: an MCP server for Claude Code, Claude Desktop, Cursor and VS Code Copilot. Layered project memory, Claude Code hooks, JSON Schema validation, token ledger and shif
{ "mcpServers": { "bantamkit-mcp": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}ओवरव्यू
Persistent memory for coding agents: an MCP server for Claude Code, Claude Desktop, Cursor and VS Code Copilot. Layered project memory, Claude Code hooks, JSON Schema validation, token ledger and shift-work tools. Pure Node; install once with npx, run off
टूल
अभी टूल सूची नहीं है। रिमोट सर्वर को पहले हेल्थ चेक के बाद सूची मिलती है।
FAQ
इस पेज पर Cursor, Claude Desktop, Claude Code या VS Code के लिए stdio कॉन्फ़िग कॉपी करें। यह पब्लिशर का इंस्टॉल इस्तेमाल करता है, PlugMCP प्रॉक्सी नहीं।
इस रिकॉर्ड में कोई ज़रूरी एनवायरनमेंट वेरिएबल दर्ज नहीं है।
Bantamkit stdio पर लोकल चलता है।
पिछली जाँच 2026-11-15 को हुई। Persistent memory for coding agents: an MCP server for Claude Code, Claude Desktop, Cursor and VS Code Copilot. Layered project memory, Claude Code hooks, JSON Schema validation, token ledger and shift-work tools. Pure Node; install once with npx, run off