python agents

waterfeet/DoroPet_V3

Agent

Evaluate expectations against an execution transcript and outputs.

JosephOIbrahim/Comfy-Cozy

Agent Claude Code

Workflow execution and verification specialist. Runs validatebeforeexecute, executes, and verifies outputs. Tests only; never modifies.

JosephOIbrahim/Comfy-Cozy

Agent Claude Code

Asset acquisition specialist. Downloads, verifies, and registers models. Provisions assets only; never modifies workflows or executes.

JosephOIbrahim/Comfy-Cozy

Agent Claude Code

Reconnaissance specialist. Discovers ComfyUI environment — nodes, models, custom nodes, system stats. Read-only authority. Never mutates state.

beycom/onetool-mcp

Agent

Primary use: Load this file for immediate context about the project.

beycom/onetool-mcp

Agent

Quick reference files for AI agents working on OneTool.

beycom/onetool-mcp

Agent

MCP server with single run tool for LLM Python code execution.

andisab/swe-marketplace

Agent

Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in production-ready notebooks, version control, CI/CD integration, parameterization with Papermill, MLOps workflows, and JupyterLab 4.4+ modern features including…

ymm-oss/fsl

Agent Claude Code

Use PROACTIVELY after changing Rust FSL syntax, lowering, semantics, CLI commands, public Kernel contracts, or corpus specs. Reports missing coupled code, tests, docs, skills, generated artifacts, and changelog updates. Read-only.

ymm-oss/fsl

Agent Claude Code

Use PROACTIVELY after changing Rust core/runtime/verifier/solver/refinement semantics. Audits symbolic BMC versus the solver-independent Monitor/BFS, false-negative risk, dependency boundaries, and cross-implementation evidence. Read-only on source; may run focused tests.

ymm-oss/fsl

Agent Claude Code

Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.

bobmatnyc/mcp-skillset

Agent Claude Code

Use this agent when you need infrastructure management, deployment automation, or operational excellence. This agent specializes in DevOps practices, cloud operations, monitoring setup, and maintaining reliable production systems. Context: Unifying multiple build scripts user: "I need help with unifying multiple build…

bobmatnyc/mcp-skillset

Agent Claude Code

Use this agent when you need infrastructure management, deployment automation, or operational excellence. This agent specializes in DevOps practices, cloud operations, monitoring setup, and maintaining reliable production systems. Context: When you need to deploy or manage infrastructure. user: "I need to deploy my…

bobmatnyc/mcp-skillset

Agent Claude Code

Use this agent when you need specialized assistance with image optimization specialist using imagemagick for web performance, format conversion, and responsive image generation. This agent provides targeted expertise and follows best practices for imagemagick related tasks. Context: When user needs optimize.image…

DanielHashmi/Q4_learning

Agent

Implements the smallest safe fix for Project 4 and verifies it.

DanielHashmi/Q4_learning

Agent

Strict read-only checker for Project 4 fix candidates.

zhhjluka/hm-arch

Agent

Production benchmark runners invoke each host agent through its real CLI boundary. Deterministic mock runners (mock-synthetic) are reserved for offline harness tests only.

zhhjluka/hm-arch

Agent

Install HM-Arch and configure Hermes to use the native HM-Arch Memory Provider. Hermes integration uses native plugin registration. hm-arch install hermes creates the HM-Arch plugin bridge, updates $HERMESHOME/config.yaml, and initializes the SQLite database.

zhhjluka/hm-arch

Agent

Install HM-Arch as OpenClaw's native memory provider. OpenClaw integration uses the @hm-arch/openclaw-plugin TypeScript memory plugin backed by a persistent Python sidecar that exposes HM-Arch recall, capture, forget, and consolidation without per-query process startup.

MarcusJellinghaus/mcp-tools-py

Agent Claude Code

Commits and pushes code changes with pre-approved git operations.

MarcusJellinghaus/mcp-tools-py

Agent Claude Code

Approves issue for workflow status transition.

MarcusJellinghaus/mcp-tools-py

Agent Claude Code

Updates GitHub issue with refined content from analysis.

charles-adedotun/notifications-mcp-server

Agent Claude Code

Specialized agent for server-side development with modern backend frameworks, APIs, databases, and cloud infrastructure. Expert in building secure, scalable, and performant backend systems across multiple languages and platforms with comprehensive testing and monitoring strategies.

charles-adedotun/notifications-mcp-server

Agent Claude Code

Specialized agent for React frontend development with shadcn/ui, Tailwind CSS v4, and modern best practices. Expert in implementing design systems, ensuring accessibility, and building performant user interfaces following the 4-font-size, 2-weight typography system, 8pt grid spacing, and 60/30/10 color distribution…