BotShelf Vampire BOTSHELF VAMPIRE Register

BUILD LIBRARY · AI TOOLKITS

Agent toolkits — by job, then by framework.

Original templates and starters for OpenAI Dots, Hugging Face (MCP, Spaces, Skills, Tiny Agents), LM Studio Bionic, smolagents, Letta and the OpenAI Agents SDK, plus LangGraph and CrewAI runners for each Library AI Team task. Part of the existing Build Library — the Ollama, LM Studio, Open WebUI, n8n, CrewAI, LangGraph and MCP recipes stay where they are.

17 toolkit items · 10 frameworks · Runtime-verified by BSV: 0 (every item shows its real status).

Summaries are public. Opening, copying or downloading the templates requires free email verification. Free stays free.

Browse by job

Always-on responsibilityResearch deskTool safety gateLocal / open-model workerLong-term project memoryGuarded agent orchestrationContext compressionHandoff between workers

Browse by framework

OpenAI Dots (3)Hugging Face (4)LM Studio Bionic (2)Hugging Face smolagents (1)Letta (1)OpenAI Agents SDK (2)LangGraph (1)CrewAI (1)n8n (1)Any framework (1)

Existing Library platforms

OllamaLM StudioOpen WebUIn8nCrewAILangGraphMCP

OpenAI Dots · Copy/paste template

Dots Custom Rules Starter

Starter rule set for a dot doing ongoing work: scope, what needs your approval, and when to stop. Not a system prompt that overrides safeguards.

Source prepared — not runtime testedAlways-on responsibility

OpenAI Dots · Copy/paste template

Dots Ongoing Responsibility Template

Fill-in structure for an ongoing responsibility: the outcome, what success means, which connected sources it may use, what it may do without asking, and what still needs your approval.

Source prepared — not runtime testedAlways-on responsibility

OpenAI Dots · Checklist

Dots Activity Review Checklist

Checklist for reviewing a dot that has worked in the background: check the result, not the activity.

Source prepared — not runtime testedAlways-on responsibility

Hugging Face · Workflow

Hugging Face MCP Research Desk

Inspectable Hub research workflow for an MCP-compatible assistant connected through Hugging Face's official MCP settings page.

Source prepared — not runtime testedResearch desk

Hugging Face · Workflow

Hugging Face Skills Workflow

Scope-and-approval pattern for Hugging Face Skills: install only the Skill a job needs, and keep paid jobs and repo writes behind your approval.

Source prepared — not runtime testedResearch desk

Hugging Face · Checklist

Hugging Face Space Safety Gate

Trust and data gate to run before enabling a community Space as an MCP tool: owner, inputs, data sent, and a synthetic first run.

Source prepared — not runtime testedTool safety gate

Hugging Face · Starter config

Local Tiny Agent Starter

Tiny Agent template where a local model stays the reasoning engine and each remote MCP server is an explicit, separate data boundary.

Not runtime testedLocal / open-model worker

LM Studio Bionic · Copy/paste template

Bionic Project Worker Template

Session template for one concrete deliverable in a Bionic project: read-first files, do / do-not lists and a fixed RESULT / TESTS / UNVERIFIED return format.

Source prepared — not runtime testedLocal / open-model worker

Hugging Face smolagents · Code

smolagents + LM Studio Local Worker

Python starter: smolagents ToolCallingAgent pointed at LM Studio's local OpenAI-compatible server, with no tools enabled by default.

Not runtime testedLocal / open-model worker

Letta · Copy/paste template

Stateful Project Memory Template

Memory hierarchy for a Letta stateful agent: identity, stable project truth, binding decisions, short current state and recurring failures.

Source prepared — not runtime testedLong-term project memory

OpenAI Agents SDK · Code

Guarded Agent Worker Starter

Python starter for the OpenAI Agents SDK: one worker, no side-effect tools, explicit UNVERIFIED output.

Not runtime testedGuarded agent orchestration

LangGraph · Code

LangGraph Team Runner (per-task, local model)

Runs any of the 10 Library AI Team tasks as a LangGraph graph on a local model (LM Studio or Ollama): produce, check the required sections, pause for your approval, then save. You paste the team prompt from its Library page.

Not runtime testedGuarded agent orchestration

CrewAI · Code

CrewAI Team Runner (per-task, local model)

Runs any of the 10 Library AI Team tasks as a two-agent CrewAI crew (lead + checker) on a local model, checks the required sections and saves only after your approval. You paste the team prompt from its Library page.

Not runtime testedGuarded agent orchestration

n8n · Code

n8n Team Runner (per-task workflows, local model)

Builds one importable n8n workflow per Library AI Team task (10 tasks): manual trigger, local OpenAI-compatible model over HTTP, a section check, then you review the result. No write, send or paid nodes. You paste the team prompt from its Library page.

Not runtime testedGuarded agent orchestration

OpenAI Agents SDK · Code

OpenAI Agents SDK Team Runner (per-task, local model)

Runs any of the 10 Library AI Team tasks with the OpenAI Agents SDK on a local model (LM Studio or Ollama), tracing disabled and no tools: produce, check the required sections, then save only after your approval. You paste the team prompt from its Library page.

Not runtime testedGuarded agent orchestration

LM Studio Bionic · Copy/paste template

Bionic Context Compressor

Local-model prompt that compresses long project material for another agent without making the local model the final reviewer.

Source prepared — not runtime testedContext compression

Any framework · Copy/paste template

AI Team Handoff Packet

Plain-text packet for handing a job between AI workers, frameworks or human reviewers without repeating finished work: scope and approval boundaries, current state, completed work, evidence, one next action and a do-not-repeat list.

Source prepared — not runtime testedHandoff between workers

Rule, responsibility and review templates for an always-on dot. They do not override OpenAI's built-in safeguards.

MCP research desk, community-Space safety gate, Skills workflow and a local Tiny Agent template — using Hugging Face's official setup flows.

Project-worker and context-compressor templates for LM Studio's agent for open models. Route cheap, checkable work locally; keep final review elsewhere.

Python ToolCallingAgent on LM Studio's local OpenAI-compatible endpoint, starting with no tools enabled.

Memory layout for stateful agents: durable project facts, not a dump of every chat message.

A guarded worker with no side-effect tools, ready to grow into agents-as-tools, guardrails, sessions or sandbox agents. The team runner runs each Library AI Team task on a local model with tracing disabled.

Graph runtime with checkpoints and human-in-the-loop interrupts. The team runner pauses before saving anything.

Role-based multi-agent crews. The team runner uses a lead and a checker on a local model, with your approval before saving.

Workflow automation. The team runner builds one importable workflow per Library AI Team task: manual trigger, local model over HTTP and a section check, with no write, send or paid nodes.

Framework-neutral plain text: paste it into any agent framework, chat or ticket, or hand it to a human reviewer.

Prefer a ready-made team? These are the existing Library AI Teams; each toolkit page links the ones for its job.

Bionic is an agent app/harness for open models; smolagents is a lightweight Python framework; Letta focuses on persistent state and memory; the OpenAI Agents SDK provides orchestration primitives (tools, handoffs, guardrails, sessions); Dots are always-on responsibilities inside OpenAI's product; Hugging Face provides MCP, Spaces, Skills and Tiny Agents; the LangGraph and CrewAI team runners run one Library AI Team task at a time with your approval before saving. Choose by job — they are not interchangeable.