LLM Mart Basic

Audit game narrative systems for technical quality -- branching dialogue trees, state/flag tracking, quest systems, choice-consequence mapping, localization pipelines, voice-over integration, and cinematic scripting..

Feature discovery agent — mines project docs, memory, user feedback, and competitor gaps to surface the highest-leverage features to build next. Outputs a prioritized feature backlog.

Map a cloud system against NIST SP 800-53 Rev. 5 + FedRAMP baselines to produce the documentation an authorization needs — System Security Plan (SSP), Control Implementation Summary (CIS), Plan of Action and Milestones (POA&M), Continuous Monitoring (ConMon) Plan..

Audit patient-facing healthcare software for portal feature completeness, secure messaging, health literacy, telehealth readiness, consent management, and HIPAA compliance. Triggers: evaluating a patient portal, checking PHI exposure in notifications, auditing telehealth flows.

Generate a production-grade Product Detail Page (PDP) optimized for the 2026 conversion benchmarks — 4-8% target vs 1.5-3% average. Triggers: "product page", "PDP", "product detail page", "Shopify product page", "ecommerce conversion".

Audit academic peer review operations -- reviewer matching algorithms, conflict of interest detection, turnaround time optimization, review quality scoring, and editorial workflow management..

Audit game analytics and telemetry implementation -- event tracking completeness, FTUE and monetization funnel coverage, retention metric infrastructure, A/B testing framework, heatmap data collection, churn prediction signals, and LTV modeling support..

Audit a codebase for product-market fit readiness -- evaluate startup PMF signals, core value loop tightness, feature scatter vs focus ratio, user activation funnel friction, retention hook infrastructure, pricing flexibility, analytics event coverage, CI/CD iteration speed, and

Audio file → full publishing kit pipeline. From a single .mp3 or .wav per episode, generates Whisper-large-v3 transcript with word-level timestamps, automatic chapter detection (audio scene change + topic shift), two show-notes lengths (scannable summary + long-form SEO).

Audit investment portfolio management software for mean-variance optimization, Black-Litterman model, risk parity allocation, VaR/CVaR risk metrics, Brinson performance attribution, tax-loss harvesting rebalancing logic, Sharpe ratio calculations, efficient frontier accuracy.

Audit manufacturing predictive maintenance systems for OPC-UA/MQTT sensor data pipelines, time-series storage retention, ML model lifecycle (training-serving skew, drift detection, retraining triggers), MTBF/MTTF/MTTR reliability calculations, Weibull survival analysis.

Audit pricing research and sensitivity analysis systems for Van Westendorp price sensitivity meter (OPP/IDP/PMC/PME intersections), Gabor-Granger demand curves, Newton-Miller-Smith revenue extension, price elasticity econometric modeling, willingness-to-pay estimation.

Audit procurement and procure-to-pay systems for spend analytics (Pareto analysis, tail spend visibility), supplier consolidation opportunities, Kraljic matrix category management, maverick spending detection, contract compliance and utilization tracking, three-way PO matching.

Audit film, television, and digital content production budgets for above-the-line (ATL) and below-the-line (BTL) cost accuracy, SAG-AFTRA/DGA/WGA/IATSE union rate compliance, fringe and payroll tax calculations, VFX bid variance analysis, post-production cost validation.

Audit manufacturing production optimization systems for OEE (Overall Equipment Effectiveness) calculation accuracy, Six Big Losses categorization, job shop and flow shop scheduling algorithms (LP, MIP, constraint programming, genetic algorithm), Theory of Constraints bottleneck d

Audit factory production scheduling systems for finite capacity planning, Drum-Buffer-Rope (DBR) Theory of Constraints implementation, dispatching rules (EDD, SPT, critical ratio), sequence-dependent changeover optimization, MRP integration.

Audit real estate investment software for IRR/NPV/cap rate/cash-on-cash return calculations, pro forma income modeling (GPR, vacancy, rent growth, NNN pass-throughs), equity waterfall and promote structures, debt modeling (fixed/ARM/IO/construction loans).

Audit public sector and government resource allocation systems for budget optimization algorithms (zero-based, incremental, performance-based), service demand forecasting (ARIMA, Prophet, regression), equity-based distribution scoring (CDC SVI, environmental justice indices.

Audit a quoting or estimation system -- analyze labor hour estimation accuracy, material take-off completeness, pricing rule engines, markup and margin optimization, good-better-best tiered pricing, and quote-to-close win rates.

Audit a real estate analytics platform -- evaluate comparable sales and rental engines, automated valuation models (AVM), demographic and economic indicator pipelines, submarket scoring, gentrification detection, price forecasting accuracy, market cycle analysis, and risk modelin

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

`crabbox attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…