Explore

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against m

Skill·AGPL-3.0·★ 245·No key

Community fork of DeusData/codebase-memory-mcp (MIT) — incremental-reindex CALLS-edge fix + 9 integrated upstream PRs. Pure-C code knowledge-graph MCP server.

in the readmewith ambiguity reporting ( #466 ); valid UTF-8 in `get_code_snippet` ( #526 ). > - **Robustness / build** — stack-buffer-overflow fix in `append_args_json` ( #475 ); JSON control-character

Skill·MIT·★ 242·No key

A lightweight Model Context Protocol (MCP) server for Stata. Execute commands, inspect data, retrieve stored results (r()/e()), and view graphs in your chat interface. Built for economists who want to

in the readmeskills catalog for workflows researchers use often: auditing data, replication and robustness checks, specification comparisons, publication QA, referee responses, and modernization of legacy code. Featured

Python·AGPL-3.0·★ 86·No key

MCP Server Semgrep is a [Model Context Protocol](https://modelcontextprotocol.io) compliant server that integrates the powerful Semgrep static analysis tool with AI assistants like Anthropic Claude. I

in the readmethe Project ![MCP Server Semgrep Logo ]( This project was initially inspired by robustness of Semgrep tool , The Replit Team and their Agent V2 , as well

Node.js·MIT·★ 28·No key

Local-first backtesting engine with built-in overfitting detection. Asset-class agnostic. MCP-native.

in the readmetrade-off: `pip install`, any numpy price array works, and the statistical robustness toolkit (PBO, deflated Sharpe, bootstrap CI, walk-forward) is the core feature, not

Python·Apache-2.0·★ 4·Few stars·No key

Agentic coding skills for backtesting trading strategies using VectorBT. Supports Indian, US, and Crypto markets with realistic transaction cost modeling, TA-Lib indicators, QuantStats tearsheets, and

Skill·Link only·★ 208

Agent skills built from Algorithms for Decision Making (Kochenderfer, Wheeler & Wray). Expected utility, value of information, bandits, robustness, belief filtering and game theory, as SKILL.md files

Skill·MIT·★ 13·No key

MCP server for AlbumentationsX image augmentation workflows

in the readmeand adjusted AlbumentationsX preview contact sheets Ask an MCP host for several robustness variants, reject an excessive result such as `too_noisy:high`, compare the adjusted

Python·AGPL-3.0·★ 6·No key

Classify GPU workloads as training, inference, or idle from telemetry alone, no self-reported labels.

in the readmejob labels.** WorkloadTruth classifying a synthetic training workload, then running the evasion-robustness benchmark Every GPU scheduler in common use today, including run:ai , Slurm, and

Python·Apache-2.0·Few stars·No key

A Model Context Protocol (MCP) server that exposes Specmatic's contract testing capabilities to AI coding agents like Claude Code. This server enables comprehensive API contract validation and mock se

in the readmeincluding edge case validation - **Use case**: Verify proper error handling and API robustness #### `manage_mock_server` Complete mock server lifecycle management for frontend development. - **Subcommands**: `start

Node.js·MIT·★ 12·No key

一个基于 Project Context 进行 Prompt优化 的 Claude Code SKILL，并配置有界面进行迭代优化；Advanced Claude Code skill for systematic prompt engineering. Optimizes prompts using project context, adversarial testing, and iterat

in the skill textQuantitative Evaluation**: Detailed scoring system (0-100) based on clarity, specificity, and robustness. - **Interactive Review (WebView)**: A native desktop UI (Wails) to diff, edit, and confirm

Skill·MIT·★ 16·No key

A research-stage registry where AI agents file falsifiable claims about systemic problems and run open-weights ensembles against them. Disagreement between models is the output

in the readmethe spread metric on its own. The lever is *more models* and robustness diagnostics (leave-one-out, simulated-N). aboard does not pick. It renders both

Node.js·Apache-2.0·★ 2·Few stars·No key

OpenAPI spec in, chaos test harness out: WireMock stubs, contract tests and failure scenarios from a team of local LLM agents.

in the readmeGet back a ready-to-run test harness: WireMock stubs, contract tests, robustness probes, and chaos scenarios, written by a team of LLM agents that review

Python·MIT·Few stars·No key

MCP server for the xAI Grok Build CLI (grok) — Grok for any MCP client

in the readmeGrok access. Responses are parsed from Grok's structured JSON output for robustness. ## Install Requires Grok Build (`grok`) installed and logged in: ```bash grok -p "say

Node.js·MIT·★ 1·Few stars·No key

TradeSearcher CLI, SDK, and MCP server for coding agents

in the readmeBTCUSD --sort roi tradesearcher search BTCUSD --sort latestTradeDate tradesearcher search BTCUSD --sort robustness ``` `--equity` can return large JSON arrays. Use it after narrowing to final candidates

Node.js·MIT·Few stars·Needs a key

Crypto backtesting tools: real backtests with robustness verdicts, daily signals and market data.

Hosted by author·No license·Few stars·No key

in the readmefor SDDrive, and convert PNG assets to C sprite headers. - **Robustness**: Native handling of timeouts (30s) and retry policy for unstable network environments (NAS). --- ## 🌐 Public MO5

Node.js·MIT·Few stars·No key

in the readmeapps. The system follows a two-component architecture that provides scalability and robustness. ## Architecture The project consists of two main components: 1. **Flutter Connector Server

Skill·MIT·★ 1·Few stars·No key

Research-only quantitative engine for AI clients: backtests, robustness testing, provenance, and audit-ready results via MCP.

MCP·Link only·Few stars

Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 data sources, 58 method modules, 18 AI skills, 30 journal templ

in the readmewith heterogeneous treatment effects, cluster-robust SEs at the firm level, 19 robustness checks, parallel-trend plots). - **43 MCP server directories** — covers A-share financials

Python·MIT·★ 108·No key

Build your own AI hedge fund with Claude, Codex, Cursor & OpenClaw. The agent-native skills directory for Trader Dev MCP — write Pine Script, backtest crypto strategies, optimize parameters.

in the skill textOptimizer — for free. | | Wonder if your backtest is curve-fit. | Built-in robustness discipline: multi-pair, multi-timeframe, drawdown control, honest verdict labels. | | Use

Skill·MIT·★ 68·No key

Automatic optimal discretization pipeline

in the readmecredit scoring, fraud detection, and risk modeling. ## 🆕 What's New **📊 Cross-validated robustness.** `fit` now accepts a `cv` argument for extra held-out robustness views

Python·MIT·★ 11·No key