Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
1–24 of 29 tools for “decision-models”
Cloud & infrastructureFew stars, complete informationClear allLets Claude Code and Cursor drive Chrome. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -24% tool calls, +48% speed, 30/30. Direct CDP, a11y-tree refs, server-side plan executor. MIT, no p
Node.jsMIT★ 19No key
Self-hosted MCP server and Jev-compatible HTTP API for small decision models (Laya, Julia-1, clef-flash) on one GPU, in Docker
DockerApache-2.0Few starsNo key
Make the call. Run local Laya, Von, CLM or hosted Jev for typed classification and scoring through one HTTP and MCP API, with resource-aware batches.
DockerWTFPL★ 3Few starsNo key
Agent Personas as MCP Server — 16 tools, 13 personas (8 free: CEO, CFO, CTO, CMO, PM, Analyst, Support, Creative Director + 5 Pro specialists), 3 multi-persona workflows plus councils + ensembles. Zer
SkillMIT★ 4Few starsNo key
TuringCorp Decider — MCP server discovery metadata (registry manifest, listing docs)
Hosted by authorMITFew starsNo key
Agent-native MCP server for evidence-backed clinical calculators.
Node.jsApache-2.0★ 13No key
Analysis of alternatives for AI models: decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.
Hosted by authorMIT★ 2Few starsNo key
Human discovery through code analysis - VS Code extension that reveals team expertise.
SkillMIT★ 18No key
MCP server + web app for sailing passage planning, worldwide: per-leg ETA, 1-5 complexity score, multi-model winds (AROME 1.3 km in France). SHOM C2D and MARC PREVIMER tidal atlases on the French Atla
Hosted by authorAGPL-3.0★ 11No key
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Clau
Node.jsMIT★ 4Few starsNo key
Project Intelligence Layer for AI-assisted development. Preserve project decisions, reasoning, constraints, history, and evolving state across AI tools.
Node.jsMIT★ 7No key
A local-first Model Context Protocol server that detects, reviews and redacts sensitive information before prompts reach AI assistants.
PythonApache-2.0★ 2Few starsNo key
Local-first code context CLI + MCP server: discover, index, and search repos; generate task-aware context packs, code maps, agent harnesses, and PR-review/merge-readiness gates for coding agents and r
Node.jsMIT★ 2Few starsNo key
MCP server for Vidofy — generate video, images, audio and speech from Claude, ChatGPT, Cursor, Codex or any MCP client. Veo 3.1, Kling 3.0, Flux 2, Seedance 2.5 and 570+ models, billed to your own Vid
Node.jsMIT★ 2Few starsNeeds a key
MCP server for Wisepanel multi-agent deliberation platform
Node.jsMIT★ 3Few starsNeeds a key
Production-ready Claude Code skills for server-side Swift (Vapor, Hummingbird) and Xcode Cloud CI/CD
SkillMIT★ 13No key
Know what your AI agents cost, per project, without your prompts leaving the machine. CLI, MCP server and CI gate. Zero dependencies, offline.
Node.jsMIT★ 1Few starsNo key
A second opinion on your decisions, from a different AI company than the one you think with.
Node.jsMIT★ 1Few starsNo key
Portable memory for AI agents — enterprise-ready production thin-client. Seals agent memory client-side (ML-DSA-65 / AES-256-GCM / ML-KEM-768) and stores opaque ciphertext on the blind, non-custodial
Node.jsApache-2.0★ 1Few starsNo key
Pathmode plugin for Claude Code — MCP server + intent-engineering skill pack. Install: /plugin marketplace add pathmodeio/claude-plugin
SkillMIT★ 3Few starsNo key
Crash-test your AI agent on real professional decisions (MCP server)
PythonMITFew starsNeeds a key
Keeps your Mac roomy: finds what is safe to delete, warns before storage or memory runs out. CLI, TUI and MCP server for people and AI agents.
Node.jsApache-2.0Few starsNo key
Fmind freelance AI architecture portfolio, technical articles, and read-only MCP tools. Python on Google Cloud Run.
Hosted by authorMITFew starsNo key
The roundtable: adversarial review for any coding agent. Specialist seats find defects alone, attack each other's findings, and a clean-context judge rules. Claude Code, Codex, Gemini CLI, opencode —
SkillApache-2.0Few starsNo key
Who stands behind it