MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Standalone harness for structured-reasoning evals: register task suites, run any model callable, report accuracy, calibration, and failure taxonomy.
SkillMIT★ 1Few starsNo key
6 phase, 56 task agent workflow, consisting of; Operational Direction, Intelligence Collection, Collation & Entity Resolution, Chronological & Relational Processing, Hypothesis & Reasoning, concluding
PythonMIT★ 20No key
Ultra mode for GitHub Copilot CLI: maximum reasoning depth with automatic task delegation, modeled on Codex's ReasoningEffort::Ultra and Claude Code's /effort ultracode.
SkillMIT★ 1Few starsNo key
A tiny local classifier that decides how much reasoning effort your coding agent should spend on each task. Automatic reasoning-effort routing for Codex on macOS.
SkillMIT★ 2Few starsNo key
Model-selectable subagents with per-task reasoning effort for DeepSeek Harness (DSH) 0.2.x. Maintained continuation of CypherNaught-0x/DSH-Subagent-Model-Router.
SkillMITFew starsNo key
Pick the best AI model and reasoning effort for any task in ~1s. Plugin for Claude Code, Claude Desktop and Codex, powered by TypeSafe's Jev decision model and live OpenRouter pricing. Balance intelli
Node.jsMIT★ 2Few starsNo key
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aw
PythonApache-2.0★ 1.0kNo key
When Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill.
SkillMIT★ 958No key
AI model routing for Codex subagents. Let Jev choose the model and reasoning effort for each mission, using your own task profiles.
SkillMIT★ 1Few starsNo key
Local MCP work notes with persistent sessions, decisions, evidence and resumable tasks.
PythonMIT★ 959No key
Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents
SkillApache-2.0★ 1.8kNo key
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
GoAGPL-3.0★ 1.2kNo key
A privacy-first cross-platform productivity workspace for notes, sketching, planning, and local AI assistance.
SkillMIT★ 7No key
Codex ↔ Claude Code MCP bridge for AI agent orchestration: task delegation, event-driven handoffs, reasoning profiles and evidence reuse. Windows/macOS; optional Orca.｜Codex 指挥 Claude Code：会话管理、阶段交付与验
SkillMIT★ 6No key
A self-hosted personal knowledge management system that combines note-taking, knowledge graphs, vector search, and AI reasoning into a single application.
SkillMIT★ 1Few starsNo key
Task-aware reasoning-mode router for Codex + DeepSeek | Codex+DeepSeek 思维模式路由（spec/react/weak）
SkillMIT★ 1Few starsNo key
Compressed, single-companion-file version of ExpertLens — an AI thinking framework that forces expert-level reasoning on any task. Platform-agnostic.
SkillMIT★ 3Few starsNo key
Privacy-aware trajectory viewer for local Codex task logs
SkillMIT★ 250No key
AI Software Factory for Codex. Intelligent task routing, contextual orchestration, and automated Kanban workflows. Transform AI-powered development into a structured, scalable software production pipe
SkillMIT★ 6No key
MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.
Node.jsMIT★ 46No key
Use Claude subagents in Codex via an MCP server with parallel delegation across up to four concurrent agents.
PythonMITFew starsNo key
Reliability Harness v2 for OpenCode CLI — task contracts, least-privilege sub-agents, clean-checkout verification, and a deterministic done-gate. Orthogonal agents (scout/spec-critic/test-designer/lea
SkillMIT★ 3Few starsNo key
Agent Skills and a router that pick the model, reasoning effort and delegation a coding task deserves. Multi-harness, benchmarked.
SkillMIT★ 2Few starsNo key
Zero-token model router for Claude Code: deterministic classifier picks the cheapest capable model per task. /route skill + always-on hook + statusline telemetry + claude-code-router integration.
SkillMIT★ 1Few starsNo key
Who stands behind it
