[bmdpat]

Tools

Local AI decisions first. Runtime guardrails second.

Local AI tools lead the shelf. Current shelf: 12 live from 12 public tools. Browser tools are first. AgentGuard is the pip-installable runtime guardrail.

Observed package downloads, updated hourly. SDK totals use Pepy first, then Pypistats no-mirror overall data when Pepy is unavailable; SDK recent-month counts use Pypistats; MCP recent-month counts use npm. Downloads are a usage signal, not an adoption proof. Tracked copy is shown when metric upstreams are unavailable.

12 live from 12 public tools.

01 / Local AI toolkit

Measure the rig. Pick the model. Keep the decision.

The first-dollar path: free fit tools lead into saved rig history in Pro.

LIVE

VRAM Calculator

Estimate GGUF VRAM fit, --n-gpu-layers 46 planning, and CPU offload risk from model, quant, GPU, and context presets.

5/day free22 model presets / 26 GPUs / 9 quant levels
No install
LIVE

Model Picker

Rank 25 local models across 6 workloads and 3 priorities for GPU fit.

5/day free25 models / 6 workloads / 3 priorities
No install
LIVE

Quantization Compare

Compare 9 GGUF quant levels by size, quality, speed, and 24GB GPU fit.

5/day free11 model families / 9 quant levels / 26 GPUs
No install
LIVE

Local LLM Toolkit Pro

Remove the 5 free runs per tool per day limit. Saved GPU rigs, Hugging Face model import, fit alerts, and benchmark history for local LLM builders.

$7/mo$49/year7-day trial4 Pro features
No install

02 / Runtime infrastructure

Control what the agent can spend and ship.

Guardrails and planning tools for the systems around the model.

LIVE

AgentGuard

Runtime guardrails for Python agents: budget, loop, timeout, and rate limits with MCP visibility for Claude Code, Cursor, and Codex.

6,443+ downloads171 downloads / last month342 MCP downloads / last monthMITv1.2.13
pip install agentguard47
LIVE

Agent Roadmap Scanner

Describe an AI agent workflow. Get risk score, top risks, architecture, first guardrails, and next steps.

5 roadmap outputs30+ char workflow6 scans/min
No install
LIVE

Agent Architect

Agent Architect scopes AI agent builds into DIY / Startup / Growth / Enterprise tiers with top 3 risks, cost, timeline, and architecture output.

5 scopes per month1st of every month
No install
LIVE

AgentFlow

Watch two AI agents coordinate through 5 pipeline steps, 1 tool call, and 1 handoff.

2 agents1 tool call1 handoff
No install
LIVE

Agent Memory API

Pay-per-call memory for agents. USDC on Base, no accounts.

from $0.001/callx402Base USDC
No install

03 / Lab archive

Useful experiments that remain public.

Smaller tools with a narrower job. Kept available without crowding the main product path.

LIVE

MarkUp

Paste a URL. Get summary, topics, sentiment, and entities plus saved history.

4 analysis fields20 recent annotations / 500 per URL
No install
LIVE

Sidecast

4 AI personas reacting to your live podcast in real time.

4 AI personastab audio + micwhisper-1 transcription
No install
LIVE

Dota 2 Stats

Look up public Dota 2 profiles, recent matches, ranks, hero performance, and 10-player breakdowns via OpenDota.

OpenDota5 min cache20 recent matches / 10-player breakdown / top 5 heroes per player
No install