MCP servers and skills: search, filter by where they run, and compare.
1–24 of 34 tools for “td-learning”
Clear allTabular Q-learning temporal difference agent with epsilon-greedy exploration and Bellman state-action updates.
SkillLink only★ 7
Tabular Q-learning temporal difference agent with epsilon-greedy exploration and Bellman state-action updates.
SkillLink only★ 7
A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI like Codex CLI and Claude Code through a gated LaTeX workflow with verified BibTeX citation
SkillMIT★ 466No key
TouchDesigner Documentation MCP Server v2.6.1 - FIXED Python API tools! Features 629 operators + 14 tutorials + 69 Python API classes with working get_python_api & search_python_api tools. Zero-config
Node.jsMIT★ 80No key
Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
SkillMIT★ 7No key
Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
SkillMIT★ 7No key
Mergen is an MCP server that gives your AI a real red team brain. It doesn't just run tools, it picks the right ones, chains them together, and actually makes sense of the output. Built by pentesters,
SkillMIT★ 16No key
Venture is an entrepreneurship harness that turns idea work into an evidence-backed business plan. Focused skills, a repeatable workflow, persistent venture context, and verification help founders spe
SkillMIT★ 2Few starsNo key
Learn what you don't know yet from the code your AI agent writes. Free and secure by design, for Claude Code, Claude Desktop, Gemini CLI & Codex — one lesson at a time.
Node.jsAGPL-3.0★ 5No key
Setup instructions and agent skills for running GPU jobs from a phone through an always-on computer and a Windows/WSL or Linux worker.
SkillMIT★ 3Few starsNo key
Code Digger helps engineers navigate big repositories with semantic retrieval, system summaries, and reliable change-impact signals.
Node.jsMIT★ 3Few starsNo key
Paradigm is a procedural learning and trust layer for AI agents. It learns from validated deliberative decisions, compiles stable behaviors into specialized reflexes, and keeps uncertain or unsupporte
PythonMIT★ 1Few starsNo key
matdisc: an agent-drivable workflow for generative design, MLIP prescreening and DFT validation of inorganic semiconductors
SkillMITFew starsNo key
Transform PowerPoint presentations into LLM-optimized markdown while preserving instructional design narrative. Built for technical trainers.
Node.jsMIT★ 4Few starsNo key
A fun, Model Context Protocol (MCP) server and/or HTML generator that transforms code repositories into interactive adventures!
SkillMIT★ 8No key
A minimal terminal AI coding agent — LLM tool-use loop with sandboxed file/shell tools
SkillMIT★ 7No key
Use your IDE, agent to direcly create your custom flow without cloud
SkillGPL-3.0★ 5No key
Advantage Actor-Critic (A2C) tabular updates with TD error advantage estimation and softmax policy gradients.
SkillLink only★ 7
Advantage Actor-Critic (A2C) tabular updates with TD error advantage estimation and softmax policy gradients.
SkillLink only★ 7
面向 Agent 的研究生/本科生级源码学习 Skill：结合论文、真实代码证据与张量形状，按 Step 深入解析深度学习项目，并通过学习记录、反馈闭环和盲点审计持续复盘
SkillMIT★ 1Few starsNo key
RepoKit — a reusable repo standard + /new-repo scaffolder, packaged as a Claude Code plugin
SkillApache-2.0★ 1Few starsNo key
Lightweight project governance for AI coding agents — prevent intent drift, retry loops, working-set overload, and premature completion.
SkillMIT★ 1Few starsNo key
Agent Skill: plan GPU jobs on a shared cluster so they actually fill the cards they are given
SkillMIT★ 1Few starsNo key
Who stands behind it
